Merge branch 'explosion:master' into master

.github/azure-steps.yml

@@ -52,17 +52,17 @@ steps:
       python -W error -c "import spacy"
     displayName: "Test import"
 
-#  - script: |
+  - script: |
-#      python -m spacy download ca_core_news_sm
+      python -m spacy download ca_core_news_sm
-#      python -m spacy download ca_core_news_md
+      python -m spacy download ca_core_news_md
-#      python -c "import spacy; nlp=spacy.load('ca_core_news_sm'); doc=nlp('test')"
+      python -c "import spacy; nlp=spacy.load('ca_core_news_sm'); doc=nlp('test')"
-#    displayName: 'Test download CLI'
+    displayName: 'Test download CLI'
-#    condition: eq(variables['python_version'], '3.8')
+    condition: eq(variables['python_version'], '3.8')
-#
+
-#  - script: |
+  - script: |
-#      python -W error -c "import ca_core_news_sm; nlp = ca_core_news_sm.load(); doc=nlp('test')"
+      python -W error -c "import ca_core_news_sm; nlp = ca_core_news_sm.load(); doc=nlp('test')"
-#    displayName: 'Test no warnings on load (#11713)'
+    displayName: 'Test no warnings on load (#11713)'
-#    condition: eq(variables['python_version'], '3.8')
+    condition: eq(variables['python_version'], '3.8')
 
   - script: |
       python -m spacy convert extra/example_data/ner_example_data/ner-token-per-line-conll2003.json .
@@ -86,17 +86,17 @@ steps:
     displayName: 'Test train CLI'
     condition: eq(variables['python_version'], '3.8')
 
-#  - script: |
+  - script: |
-#      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')"
+      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')"
-#      PYTHONWARNINGS="error,ignore::DeprecationWarning" python -m spacy assemble ner_source_sm.cfg output_dir
+      PYTHONWARNINGS="error,ignore::DeprecationWarning" python -m spacy assemble ner_source_sm.cfg output_dir
-#    displayName: 'Test assemble CLI'
+    displayName: 'Test assemble CLI'
-#    condition: eq(variables['python_version'], '3.8')
+    condition: eq(variables['python_version'], '3.8')
-#
+
-#  - script: |
+  - script: |
-#      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_md'}; config.to_disk('ner_source_md.cfg')"
+      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_md'}; config.to_disk('ner_source_md.cfg')"
-#      python -m spacy assemble ner_source_md.cfg output_dir 2>&1 | grep -q W113
+      python -m spacy assemble ner_source_md.cfg output_dir 2>&1 | grep -q W113
-#    displayName: 'Test assemble CLI vectors warning'
+    displayName: 'Test assemble CLI vectors warning'
-#    condition: eq(variables['python_version'], '3.8')
+    condition: eq(variables['python_version'], '3.8')
 
   - script: |
       python -m pip install -U -r requirements.txt
@@ -107,7 +107,7 @@ steps:
     displayName: "Run CPU tests"
 
   - script: |
-      python -m pip install --pre thinc-apple-ops
+      python -m pip install 'spacy[apple]'
       python -m pytest --pyargs spacy
     displayName: "Run CPU tests with thinc-apple-ops"
     condition: and(startsWith(variables['imageName'], 'macos'), eq(variables['python.version'], '3.11'))

.github/workflows/lock.yml

@@ -15,7 +15,7 @@ jobs:
   action:
     runs-on: ubuntu-latest
     steps:
-      - uses: dessant/lock-threads@v3
+      - uses: dessant/lock-threads@v4
         with:
           process-only: 'issues'
           issue-inactive-days: '30'

.gitignore

@@ -10,16 +10,6 @@ spacy/tests/package/setup.cfg
 spacy/tests/package/pyproject.toml
 spacy/tests/package/requirements.txt
 
-# Website
-website/.cache/
-website/public/
-website/node_modules
-website/.npm
-website/logs
-*.log
-npm-debug.log*
-quickstart-training-generator.js
-
 # Cython / C extensions
 cythonize.json
 spacy/*.html

README.md

@@ -14,9 +14,9 @@ parsing, **named entity recognition**, **text classification** and more,
 multi-task learning with pretrained **transformers** like BERT, as well as a
 production-ready [**training system**](https://spacy.io/usage/training) and easy
 model packaging, deployment and workflow management. spaCy is commercial
-open-source software, released under the MIT license.
+open-source software, released under the [MIT license](https://github.com/explosion/spaCy/blob/master/LICENSE).
 
-💫 **Version 3.4 out now!**
+💫 **Version 3.5 out now!**
 [Check out the release notes here.](https://github.com/explosion/spaCy/releases)
 
 [![Azure Pipelines](https://img.shields.io/azure-devops/build/explosion-ai/public/8/master.svg?logo=azure-pipelines&style=flat-square&label=build)](https://dev.azure.com/explosion-ai/public/_build?definitionId=8)
@@ -46,6 +46,7 @@ open-source software, released under the MIT license.
 | 🛠 **[Changelog]**                                                                                                                                                                                                         | Changes and version history.                                                                                                                                                                                                                                                                                                 |
 | 💝 **[Contribute]**                                                                                                                                                                                                       | How to contribute to the spaCy project and code base.                                                                                                                                                                                                                                                                        |
 | <a href="https://explosion.ai/spacy-tailored-pipelines"><img src="https://user-images.githubusercontent.com/13643239/152853098-1c761611-ccb0-4ec6-9066-b234552831fe.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Get a custom spaCy pipeline, tailor-made for your NLP problem by spaCy's core developers. Streamlined, production-ready, predictable and maintainable. Start by completing our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more &rarr;](https://explosion.ai/spacy-tailored-pipelines)** |
+| <a href="https://explosion.ai/spacy-tailored-analysis"><img src="https://user-images.githubusercontent.com/1019791/206151300-b00cd189-e503-4797-aa1e-1bb6344062c5.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Bespoke advice for problem solving, strategy and analysis for applied NLP projects. Services include data strategy, code reviews, pipeline design and annotation coaching. Curious? Fill in our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more &rarr;](https://explosion.ai/spacy-tailored-analysis)** |
 
 [spacy 101]: https://spacy.io/usage/spacy-101
 [new in v3.0]: https://spacy.io/usage/v3
@@ -59,6 +60,7 @@ open-source software, released under the MIT license.
 [changelog]: https://spacy.io/usage#changelog
 [contribute]: https://github.com/explosion/spaCy/blob/master/CONTRIBUTING.md
 
+
 ## 💬 Where to ask questions
 
 The spaCy project is maintained by the [spaCy team](https://explosion.ai/about).

azure-pipelines.yml

@@ -41,7 +41,7 @@ jobs:
       matrix:
         # We're only running one platform per Python version to speed up builds
         Python36Linux:
-          imageName: "ubuntu-latest"
+          imageName: "ubuntu-20.04"
           python.version: "3.6"
         #        Python36Windows:
         #          imageName: "windows-latest"
@@ -50,7 +50,7 @@ jobs:
         #          imageName: "macos-latest"
         #          python.version: "3.6"
         #        Python37Linux:
-        #          imageName: "ubuntu-latest"
+        #          imageName: "ubuntu-20.04"
         #          python.version: "3.7"
         Python37Windows:
           imageName: "windows-latest"

build-constraints.txt

@@ -5,4 +5,5 @@ numpy==1.17.3; python_version=='3.8' and platform_machine!='aarch64'
 numpy==1.19.2; python_version=='3.8' and platform_machine=='aarch64'
 numpy==1.19.3; python_version=='3.9'
 numpy==1.21.3; python_version=='3.10'
-numpy; python_version>='3.11'
+numpy==1.23.2; python_version=='3.11'
+numpy; python_version>='3.12'

requirements.txt

@@ -1,12 +1,12 @@
 # Our libraries
-spacy-legacy>=3.0.10,<3.1.0
+spacy-legacy>=3.0.11,<3.1.0
 spacy-loggers>=1.0.0,<2.0.0
 cymem>=2.0.2,<2.1.0
 preshed>=3.0.2,<3.1.0
 thinc>=8.1.0,<8.2.0
 ml_datasets>=0.2.0,<0.3.0
 murmurhash>=0.28.0,<1.1.0
-wasabi>=0.9.1,<1.1.0
+wasabi>=0.9.1,<1.2.0
 srsly>=2.4.3,<3.0.0
 catalogue>=2.0.6,<2.1.0
 typer>=0.3.0,<0.8.0
@@ -22,7 +22,7 @@ langcodes>=3.2.0,<4.0.0
 # Official Python utilities
 setuptools
 packaging>=20.0
-typing_extensions>=3.7.4.1,<4.2.0; python_version < "3.8"
+typing_extensions>=3.7.4.1,<4.5.0; python_version < "3.8"
 # Development dependencies
 pre-commit>=2.13.0
 cython>=0.25,<3.0

setup.cfg

@@ -22,6 +22,7 @@ classifiers =
     Programming Language :: Python :: 3.8
     Programming Language :: Python :: 3.9
     Programming Language :: Python :: 3.10
+    Programming Language :: Python :: 3.11
     Topic :: Scientific/Engineering
 project_urls =
     Release notes = https://github.com/explosion/spaCy/releases
@@ -41,13 +42,13 @@ setup_requires =
     thinc>=8.1.0,<8.2.0
 install_requires =
     # Our libraries
-    spacy-legacy>=3.0.10,<3.1.0
+    spacy-legacy>=3.0.11,<3.1.0
     spacy-loggers>=1.0.0,<2.0.0
     murmurhash>=0.28.0,<1.1.0
     cymem>=2.0.2,<2.1.0
     preshed>=3.0.2,<3.1.0
     thinc>=8.1.0,<8.2.0
-    wasabi>=0.9.1,<1.1.0
+    wasabi>=0.9.1,<1.2.0
     srsly>=2.4.3,<3.0.0
     catalogue>=2.0.6,<2.1.0
     # Third-party dependencies
@@ -62,7 +63,7 @@ install_requires =
     # Official Python utilities
     setuptools
     packaging>=20.0
-    typing_extensions>=3.7.4,<4.2.0; python_version < "3.8"
+    typing_extensions>=3.7.4.1,<4.5.0; python_version < "3.8"
     langcodes>=3.2.0,<4.0.0
 
 [options.entry_points]
@@ -73,7 +74,7 @@ console_scripts =
 lookups =
     spacy_lookups_data>=1.0.3,<1.1.0
 transformers =
-    spacy_transformers>=1.1.2,<1.2.0
+    spacy_transformers>=1.1.2,<1.3.0
 ray =
     spacy_ray>=0.1.0,<1.0.0
 cuda =

spacy/cli/__init__.py

@@ -4,6 +4,7 @@ from ._util import app, setup_cli  # noqa: F401
 
 # These are the actual functions, NOT the wrapped CLI commands. The CLI commands
 # are registered automatically and won't have to be imported here.
+from .benchmark_speed import benchmark_speed_cli  # noqa: F401
 from .download import download  # noqa: F401
 from .info import info  # noqa: F401
 from .package import package  # noqa: F401
@@ -16,6 +17,7 @@ from .debug_config import debug_config  # noqa: F401
 from .debug_model import debug_model  # noqa: F401
 from .debug_diff import debug_diff  # noqa: F401
 from .evaluate import evaluate  # noqa: F401
+from .apply import apply  # noqa: F401
 from .convert import convert  # noqa: F401
 from .init_pipeline import init_pipeline_cli  # noqa: F401
 from .init_config import init_config, fill_config  # noqa: F401

spacy/cli/_util.py

@@ -46,6 +46,7 @@ DEBUG_HELP = """Suite of helpful commands for debugging and profiling. Includes
 commands to check and validate your config files, training and evaluation data,
 and custom model implementations.
 """
+BENCHMARK_HELP = """Commands for benchmarking pipelines."""
 INIT_HELP = """Commands for initializing configs and pipeline packages."""
 
 # Wrappers for Typer's annotations. Initially created to set defaults and to
@@ -54,12 +55,14 @@ Arg = typer.Argument
 Opt = typer.Option
 
 app = typer.Typer(name=NAME, help=HELP)
+benchmark_cli = typer.Typer(name="benchmark", help=BENCHMARK_HELP, no_args_is_help=True)
 project_cli = typer.Typer(name="project", help=PROJECT_HELP, no_args_is_help=True)
 debug_cli = typer.Typer(name="debug", help=DEBUG_HELP, no_args_is_help=True)
 init_cli = typer.Typer(name="init", help=INIT_HELP, no_args_is_help=True)
 
 app.add_typer(project_cli)
 app.add_typer(debug_cli)
+app.add_typer(benchmark_cli)
 app.add_typer(init_cli)
 
 
@@ -158,15 +161,15 @@ def load_project_config(
         sys.exit(1)
     validate_project_version(config)
     validate_project_commands(config)
+    if interpolate:
+        err = f"{PROJECT_FILE} validation error"
+        with show_validation_error(title=err, hint_fill=False):
+            config = substitute_project_variables(config, overrides)
     # Make sure directories defined in config exist
     for subdir in config.get("directories", []):
         dir_path = path / subdir
         if not dir_path.exists():
             dir_path.mkdir(parents=True)
-    if interpolate:
-        err = f"{PROJECT_FILE} validation error"
-        with show_validation_error(title=err, hint_fill=False):
-            config = substitute_project_variables(config, overrides)
     return config
 
 
@@ -582,6 +585,33 @@ def setup_gpu(use_gpu: int, silent=None) -> None:
             local_msg.info("To switch to GPU 0, use the option: --gpu-id 0")
 
 
+def walk_directory(path: Path, suffix: Optional[str] = None) -> List[Path]:
+    """Given a directory and a suffix, recursively find all files matching the suffix.
+    Directories or files with names beginning with a . are ignored, but hidden flags on
+    filesystems are not checked.
+    When provided with a suffix `None`, there is no suffix-based filtering."""
+    if not path.is_dir():
+        return [path]
+    paths = [path]
+    locs = []
+    seen = set()
+    for path in paths:
+        if str(path) in seen:
+            continue
+        seen.add(str(path))
+        if path.parts[-1].startswith("."):
+            continue
+        elif path.is_dir():
+            paths.extend(path.iterdir())
+        elif suffix is not None and not path.parts[-1].endswith(suffix):
+            continue
+        else:
+            locs.append(path)
+    # It's good to sort these, in case the ordering messes up cache.
+    locs.sort()
+    return locs
+
+
 def _format_number(number: Union[int, float], ndigits: int = 2) -> str:
     """Formats a number (float or int) rounding to `ndigits`, without truncating trailing 0s,
     as happens with `round(number, ndigits)`"""

spacy/cli/apply.py

@@ -0,0 +1,143 @@
+import tqdm
+import srsly
+
+from itertools import chain
+from pathlib import Path
+from typing import Optional, List, Iterable, cast, Union
+
+from wasabi import msg
+
+from ._util import app, Arg, Opt, setup_gpu, import_code, walk_directory
+
+from ..tokens import Doc, DocBin
+from ..vocab import Vocab
+from ..util import ensure_path, load_model
+
+
+path_help = """Location of the documents to predict on.
+Can be a single file in .spacy format or a .jsonl file.
+Files with other extensions are treated as single plain text documents.
+If a directory is provided it is traversed recursively to grab
+all files to be processed.
+The files can be a mixture of .spacy, .jsonl and text files.
+If .jsonl is provided the specified field is going
+to be grabbed ("text" by default)."""
+
+out_help = "Path to save the resulting .spacy file"
+code_help = (
+    "Path to Python file with additional " "code (registered functions) to be imported"
+)
+gold_help = "Use gold preprocessing provided in the .spacy files"
+force_msg = (
+    "The provided output file already exists. "
+    "To force overwriting the output file, set the --force or -F flag."
+)
+
+
+DocOrStrStream = Union[Iterable[str], Iterable[Doc]]
+
+
+def _stream_docbin(path: Path, vocab: Vocab) -> Iterable[Doc]:
+    """
+    Stream Doc objects from DocBin.
+    """
+    docbin = DocBin().from_disk(path)
+    for doc in docbin.get_docs(vocab):
+        yield doc
+
+
+def _stream_jsonl(path: Path, field: str) -> Iterable[str]:
+    """
+    Stream "text" field from JSONL. If the field "text" is
+    not found it raises error.
+    """
+    for entry in srsly.read_jsonl(path):
+        if field not in entry:
+            msg.fail(f"{path} does not contain the required '{field}' field.", exits=1)
+        else:
+            yield entry[field]
+
+
+def _stream_texts(paths: Iterable[Path]) -> Iterable[str]:
+    """
+    Yields strings from text files in paths.
+    """
+    for path in paths:
+        with open(path, "r") as fin:
+            text = fin.read()
+            yield text
+
+
+@app.command("apply")
+def apply_cli(
+    # fmt: off
+    model: str = Arg(..., help="Model name or path"),
+    data_path: Path = Arg(..., help=path_help, exists=True),
+    output_file: Path = Arg(..., help=out_help, dir_okay=False),
+    code_path: Optional[Path] = Opt(None, "--code", "-c", help=code_help),
+    text_key: str = Opt("text", "--text-key", "-tk", help="Key containing text string for JSONL"),
+    force_overwrite: bool = Opt(False, "--force", "-F", help="Force overwriting the output file"),
+    use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU."),
+    batch_size: int = Opt(1, "--batch-size", "-b", help="Batch size."),
+    n_process: int = Opt(1, "--n-process", "-n", help="number of processors to use.")
+):
+    """
+    Apply a trained pipeline to documents to get predictions.
+    Expects a loadable spaCy pipeline and path to the data, which
+    can be a directory or a file.
+    The data files can be provided in multiple formats:
+        1. .spacy files
+        2. .jsonl files with a specified "field" to read the text from.
+        3. Files with any other extension are assumed to be containing
+           a single document.
+    DOCS: https://spacy.io/api/cli#apply
+    """
+    data_path = ensure_path(data_path)
+    output_file = ensure_path(output_file)
+    code_path = ensure_path(code_path)
+    if output_file.exists() and not force_overwrite:
+        msg.fail(force_msg, exits=1)
+    if not data_path.exists():
+        msg.fail(f"Couldn't find data path: {data_path}", exits=1)
+    import_code(code_path)
+    setup_gpu(use_gpu)
+    apply(data_path, output_file, model, text_key, batch_size, n_process)
+
+
+def apply(
+    data_path: Path,
+    output_file: Path,
+    model: str,
+    json_field: str,
+    batch_size: int,
+    n_process: int,
+):
+    docbin = DocBin(store_user_data=True)
+    paths = walk_directory(data_path)
+    if len(paths) == 0:
+        docbin.to_disk(output_file)
+        msg.warn(
+            "Did not find data to process,"
+            f" {data_path} seems to be an empty directory."
+        )
+        return
+    nlp = load_model(model)
+    msg.good(f"Loaded model {model}")
+    vocab = nlp.vocab
+    streams: List[DocOrStrStream] = []
+    text_files = []
+    for path in paths:
+        if path.suffix == ".spacy":
+            streams.append(_stream_docbin(path, vocab))
+        elif path.suffix == ".jsonl":
+            streams.append(_stream_jsonl(path, json_field))
+        else:
+            text_files.append(path)
+    if len(text_files) > 0:
+        streams.append(_stream_texts(text_files))
+    datagen = cast(DocOrStrStream, chain(*streams))
+    for doc in tqdm.tqdm(nlp.pipe(datagen, batch_size=batch_size, n_process=n_process)):
+        docbin.add(doc)
+    if output_file.suffix == "":
+        output_file = output_file.with_suffix(".spacy")
+    docbin.to_disk(output_file)

spacy/cli/benchmark_speed.py

@@ -0,0 +1,174 @@
+from typing import Iterable, List, Optional
+import random
+from itertools import islice
+import numpy
+from pathlib import Path
+import time
+from tqdm import tqdm
+import typer
+from wasabi import msg
+
+from .. import util
+from ..language import Language
+from ..tokens import Doc
+from ..training import Corpus
+from ._util import Arg, Opt, benchmark_cli, setup_gpu
+
+
+@benchmark_cli.command(
+    "speed",
+    context_settings={"allow_extra_args": True, "ignore_unknown_options": True},
+)
+def benchmark_speed_cli(
+    # fmt: off
+    ctx: typer.Context,
+    model: str = Arg(..., help="Model name or path"),
+    data_path: Path = Arg(..., help="Location of binary evaluation data in .spacy format", exists=True),
+    batch_size: Optional[int] = Opt(None, "--batch-size", "-b", min=1, help="Override the pipeline batch size"),
+    no_shuffle: bool = Opt(False, "--no-shuffle", help="Do not shuffle benchmark data"),
+    use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU"),
+    n_batches: int = Opt(50, "--batches", help="Minimum number of batches to benchmark", min=30,),
+    warmup_epochs: int = Opt(3, "--warmup", "-w", min=0, help="Number of iterations over the data for warmup"),
+    # fmt: on
+):
+    """
+    Benchmark a pipeline. Expects a loadable spaCy pipeline and benchmark
+    data in the binary .spacy format.
+    """
+    setup_gpu(use_gpu=use_gpu, silent=False)
+
+    nlp = util.load_model(model)
+    batch_size = batch_size if batch_size is not None else nlp.batch_size
+    corpus = Corpus(data_path)
+    docs = [eg.predicted for eg in corpus(nlp)]
+
+    if len(docs) == 0:
+        msg.fail("Cannot benchmark speed using an empty corpus.", exits=1)
+
+    print(f"Warming up for {warmup_epochs} epochs...")
+    warmup(nlp, docs, warmup_epochs, batch_size)
+
+    print()
+    print(f"Benchmarking {n_batches} batches...")
+    wps = benchmark(nlp, docs, n_batches, batch_size, not no_shuffle)
+
+    print()
+    print_outliers(wps)
+    print_mean_with_ci(wps)
+
+
+# Lowercased, behaves as a context manager function.
+class time_context:
+    """Register the running time of a context."""
+
+    def __enter__(self):
+        self.start = time.perf_counter()
+        return self
+
+    def __exit__(self, type, value, traceback):
+        self.elapsed = time.perf_counter() - self.start
+
+
+class Quartiles:
+    """Calculate the q1, q2, q3 quartiles and the inter-quartile range (iqr)
+    of a sample."""
+
+    q1: float
+    q2: float
+    q3: float
+    iqr: float
+
+    def __init__(self, sample: numpy.ndarray) -> None:
+        self.q1 = numpy.quantile(sample, 0.25)
+        self.q2 = numpy.quantile(sample, 0.5)
+        self.q3 = numpy.quantile(sample, 0.75)
+        self.iqr = self.q3 - self.q1
+
+
+def annotate(
+    nlp: Language, docs: List[Doc], batch_size: Optional[int]
+) -> numpy.ndarray:
+    docs = nlp.pipe(tqdm(docs, unit="doc"), batch_size=batch_size)
+    wps = []
+    while True:
+        with time_context() as elapsed:
+            batch_docs = list(
+                islice(docs, batch_size if batch_size else nlp.batch_size)
+            )
+        if len(batch_docs) == 0:
+            break
+        n_tokens = count_tokens(batch_docs)
+        wps.append(n_tokens / elapsed.elapsed)
+
+    return numpy.array(wps)
+
+
+def benchmark(
+    nlp: Language,
+    docs: List[Doc],
+    n_batches: int,
+    batch_size: int,
+    shuffle: bool,
+) -> numpy.ndarray:
+    if shuffle:
+        bench_docs = [
+            nlp.make_doc(random.choice(docs).text)
+            for _ in range(n_batches * batch_size)
+        ]
+    else:
+        bench_docs = [
+            nlp.make_doc(docs[i % len(docs)].text)
+            for i in range(n_batches * batch_size)
+        ]
+
+    return annotate(nlp, bench_docs, batch_size)
+
+
+def bootstrap(x, statistic=numpy.mean, iterations=10000) -> numpy.ndarray:
+    """Apply a statistic to repeated random samples of an array."""
+    return numpy.fromiter(
+        (
+            statistic(numpy.random.choice(x, len(x), replace=True))
+            for _ in range(iterations)
+        ),
+        numpy.float64,
+    )
+
+
+def count_tokens(docs: Iterable[Doc]) -> int:
+    return sum(len(doc) for doc in docs)
+
+
+def print_mean_with_ci(sample: numpy.ndarray):
+    mean = numpy.mean(sample)
+    bootstrap_means = bootstrap(sample)
+    bootstrap_means.sort()
+
+    # 95% confidence interval
+    low = bootstrap_means[int(len(bootstrap_means) * 0.025)]
+    high = bootstrap_means[int(len(bootstrap_means) * 0.975)]
+
+    print(f"Mean: {mean:.1f} words/s (95% CI: {low-mean:.1f} +{high-mean:.1f})")
+
+
+def print_outliers(sample: numpy.ndarray):
+    quartiles = Quartiles(sample)
+
+    n_outliers = numpy.sum(
+        (sample < (quartiles.q1 - 1.5 * quartiles.iqr))
+        | (sample > (quartiles.q3 + 1.5 * quartiles.iqr))
+    )
+    n_extreme_outliers = numpy.sum(
+        (sample < (quartiles.q1 - 3.0 * quartiles.iqr))
+        | (sample > (quartiles.q3 + 3.0 * quartiles.iqr))
+    )
+    print(
+        f"Outliers: {(100 * n_outliers) / len(sample):.1f}%, extreme outliers: {(100 * n_extreme_outliers) / len(sample)}%"
+    )
+
+
+def warmup(
+    nlp: Language, docs: List[Doc], warmup_epochs: int, batch_size: Optional[int]
+) -> numpy.ndarray:
+    docs = warmup_epochs * docs
+    return annotate(nlp, docs, batch_size)

spacy/cli/convert.py

@@ -1,4 +1,4 @@
-from typing import Callable, Iterable, Mapping, Optional, Any, List, Union
+from typing import Callable, Iterable, Mapping, Optional, Any, Union
 from enum import Enum
 from pathlib import Path
 from wasabi import Printer
@@ -7,7 +7,7 @@ import re
 import sys
 import itertools
 
-from ._util import app, Arg, Opt
+from ._util import app, Arg, Opt, walk_directory
 from ..training import docs_to_json
 from ..tokens import Doc, DocBin
 from ..training.converters import iob_to_docs, conll_ner_to_docs, json_to_docs
@@ -28,6 +28,8 @@ CONVERTERS: Mapping[str, Callable[..., Iterable[Doc]]] = {
     "json": json_to_docs,
 }
 
+AUTO = "auto"
+
 
 # File types that can be written to stdout
 FILE_TYPES_STDOUT = ("json",)
@@ -49,7 +51,7 @@ def convert_cli(
     model: Optional[str] = Opt(None, "--model", "--base", "-b", help="Trained spaCy pipeline for sentence segmentation to use as base (for --seg-sents)"),
     morphology: bool = Opt(False, "--morphology", "-m", help="Enable appending morphology to tags"),
     merge_subtokens: bool = Opt(False, "--merge-subtokens", "-T", help="Merge CoNLL-U subtokens"),
-    converter: str = Opt("auto", "--converter", "-c", help=f"Converter: {tuple(CONVERTERS.keys())}"),
+    converter: str = Opt(AUTO, "--converter", "-c", help=f"Converter: {tuple(CONVERTERS.keys())}"),
     ner_map: Optional[Path] = Opt(None, "--ner-map", "-nm", help="NER tag mapping (as JSON-encoded dict of entity types)", exists=True),
     lang: Optional[str] = Opt(None, "--lang", "-l", help="Language (if tokenizer required)"),
     concatenate: bool = Opt(None, "--concatenate", "-C", help="Concatenate output to a single file"),
@@ -70,8 +72,8 @@ def convert_cli(
     output_dir: Union[str, Path] = "-" if output_dir == Path("-") else output_dir
     silent = output_dir == "-"
     msg = Printer(no_print=silent)
-    verify_cli_args(msg, input_path, output_dir, file_type.value, converter, ner_map)
     converter = _get_converter(msg, converter, input_path)
+    verify_cli_args(msg, input_path, output_dir, file_type.value, converter, ner_map)
     convert(
         input_path,
         output_dir,
@@ -100,7 +102,7 @@ def convert(
     model: Optional[str] = None,
     morphology: bool = False,
     merge_subtokens: bool = False,
-    converter: str = "auto",
+    converter: str,
     ner_map: Optional[Path] = None,
     lang: Optional[str] = None,
     concatenate: bool = False,
@@ -189,33 +191,6 @@ def autodetect_ner_format(input_data: str) -> Optional[str]:
     return None
 
 
-def walk_directory(path: Path, converter: str) -> List[Path]:
-    if not path.is_dir():
-        return [path]
-    paths = [path]
-    locs = []
-    seen = set()
-    for path in paths:
-        if str(path) in seen:
-            continue
-        seen.add(str(path))
-        if path.parts[-1].startswith("."):
-            continue
-        elif path.is_dir():
-            paths.extend(path.iterdir())
-        elif converter == "json" and not path.parts[-1].endswith("json"):
-            continue
-        elif converter == "conll" and not path.parts[-1].endswith("conll"):
-            continue
-        elif converter == "iob" and not path.parts[-1].endswith("iob"):
-            continue
-        else:
-            locs.append(path)
-    # It's good to sort these, in case the ordering messes up cache.
-    locs.sort()
-    return locs
-
-
 def verify_cli_args(
     msg: Printer,
     input_path: Path,
@@ -239,18 +214,22 @@ def verify_cli_args(
         input_locs = walk_directory(input_path, converter)
         if len(input_locs) == 0:
             msg.fail("No input files in directory", input_path, exits=1)
-        file_types = list(set([loc.suffix[1:] for loc in input_locs]))
+    if converter not in CONVERTERS:
-        if converter == "auto" and len(file_types) >= 2:
-            file_types_str = ",".join(file_types)
-            msg.fail("All input files must be same type", file_types_str, exits=1)
-    if converter != "auto" and converter not in CONVERTERS:
         msg.fail(f"Can't find converter for {converter}", exits=1)
 
 
 def _get_converter(msg, converter, input_path: Path):
     if input_path.is_dir():
-        input_path = walk_directory(input_path, converter)[0]
+        if converter == AUTO:
-    if converter == "auto":
+            input_locs = walk_directory(input_path, suffix=None)
+            file_types = list(set([loc.suffix[1:] for loc in input_locs]))
+            if len(file_types) >= 2:
+                file_types_str = ",".join(file_types)
+                msg.fail("All input files must be same type", file_types_str, exits=1)
+            input_path = input_locs[0]
+        else:
+            input_path = walk_directory(input_path, suffix=converter)[0]
+    if converter == AUTO:
         converter = input_path.suffix[1:]
     if converter == "ner" or converter == "iob":
         with input_path.open(encoding="utf8") as file_:

spacy/cli/evaluate.py

@@ -7,12 +7,15 @@ from thinc.api import fix_random_seed
 
 from ..training import Corpus
 from ..tokens import Doc
-from ._util import app, Arg, Opt, setup_gpu, import_code
+from ._util import app, Arg, Opt, setup_gpu, import_code, benchmark_cli
 from ..scorer import Scorer
 from .. import util
 from .. import displacy
 
 
+@benchmark_cli.command(
+    "accuracy",
+)
 @app.command("evaluate")
 def evaluate_cli(
     # fmt: off
@@ -36,7 +39,7 @@ def evaluate_cli(
     dependency parses in a HTML file, set as output directory as the
     displacy_path argument.
 
-    DOCS: https://spacy.io/api/cli#evaluate
+    DOCS: https://spacy.io/api/cli#benchmark-accuracy
     """
     import_code(code_path)
     evaluate(

spacy/cli/project/run.py

@@ -101,8 +101,8 @@ def project_run(
             if not (project_dir / dep).exists():
                 err = f"Missing dependency specified by command '{subcommand}': {dep}"
                 err_help = "Maybe you forgot to run the 'project assets' command or a previous step?"
-                err_kwargs = {"exits": 1} if not dry else {}
+                err_exits = 1 if not dry else None
-                msg.fail(err, err_help, **err_kwargs)
+                msg.fail(err, err_help, exits=err_exits)
         check_spacy_commit = check_bool_env_var(ENV_VARS.PROJECT_USE_GIT_VERSION)
         with working_dir(project_dir) as current_dir:
             msg.divider(subcommand)

spacy/cli/templates/quickstart_training.jinja

@@ -1,7 +1,7 @@
 {# This is a template for training configs used for the quickstart widget in
 the docs and the init config command. It encodes various best practices and
 can help generate the best possible configuration, given a user's requirements. #}
-{%- set use_transformer = hardware != "cpu" -%}
+{%- set use_transformer = hardware != "cpu" and transformer_data -%}
 {%- set transformer = transformer_data[optimize] if use_transformer else {} -%}
 {%- set listener_components = ["tagger", "morphologizer", "parser", "ner", "textcat", "textcat_multilabel", "entity_linker", "spancat", "trainable_lemmatizer"] -%}
 [paths]

spacy/displacy/__init__.py

@@ -11,6 +11,7 @@ from .render import DependencyRenderer, EntityRenderer, SpanRenderer
 from ..tokens import Doc, Span
 from ..errors import Errors, Warnings
 from ..util import is_in_jupyter
+from ..util import find_available_port
 
 
 _html = {}
@@ -36,7 +37,7 @@ def render(
     jupyter (bool): Override Jupyter auto-detection.
     options (dict): Visualiser-specific options, e.g. colors.
     manual (bool): Don't parse `Doc` and instead expect a dict/list of dicts.
-    RETURNS (str): Rendered HTML markup.
+    RETURNS (str): Rendered SVG or HTML markup.
 
     DOCS: https://spacy.io/api/top-level#displacy.render
     USAGE: https://spacy.io/usage/visualizers
@@ -82,6 +83,7 @@ def serve(
     manual: bool = False,
     port: int = 5000,
     host: str = "0.0.0.0",
+    auto_select_port: bool = False,
 ) -> None:
     """Serve displaCy visualisation.
 
@@ -93,12 +95,15 @@ def serve(
     manual (bool): Don't parse `Doc` and instead expect a dict/list of dicts.
     port (int): Port to serve visualisation.
     host (str): Host to serve visualisation.
+    auto_select_port (bool): Automatically select a port if the specified port is in use.
 
     DOCS: https://spacy.io/api/top-level#displacy.serve
     USAGE: https://spacy.io/usage/visualizers
     """
     from wsgiref import simple_server
 
+    port = find_available_port(port, host, auto_select_port)
+
     if is_in_jupyter():
         warnings.warn(Warnings.W011)
     render(docs, style=style, page=page, minify=minify, options=options, manual=manual)

spacy/displacy/render.py

@@ -94,7 +94,7 @@ class SpanRenderer:
         parsed (list): Dependency parses to render.
         page (bool): Render parses wrapped as full HTML page.
         minify (bool): Minify HTML markup.
-        RETURNS (str): Rendered HTML markup.
+        RETURNS (str): Rendered SVG or HTML markup.
         """
         rendered = []
         for i, p in enumerate(parsed):
@@ -510,7 +510,7 @@ class EntityRenderer:
         parsed (list): Dependency parses to render.
         page (bool): Render parses wrapped as full HTML page.
         minify (bool): Minify HTML markup.
-        RETURNS (str): Rendered HTML markup.
+        RETURNS (str): Rendered SVG or HTML markup.
         """
         rendered = []
         for i, p in enumerate(parsed):

spacy/errors.py

@@ -214,6 +214,7 @@ class Warnings(metaclass=ErrorsWithCodes):
             "is a Cython extension type.")
     W123 = ("Argument `enable` with value {enable} does not contain all values specified in the config option "
             "`enabled` ({enabled}). Be aware that this might affect other components in your pipeline.")
+    W124 = ("{host}:{port} is already in use, using the nearest available port {serve_port} as an alternative.")
 
 
 class Errors(metaclass=ErrorsWithCodes):
@@ -345,6 +346,11 @@ class Errors(metaclass=ErrorsWithCodes):
             "clear the existing vectors and resize the table.")
     E074 = ("Error interpreting compiled match pattern: patterns are expected "
             "to end with the attribute {attr}. Got: {bad_attr}.")
+    E079 = ("Error computing states in beam: number of predicted beams "
+            "({pbeams}) does not equal number of gold beams ({gbeams}).")
+    E080 = ("Duplicate state found in beam: {key}.")
+    E081 = ("Error getting gradient in beam: number of histories ({n_hist}) "
+            "does not equal number of losses ({losses}).")
     E082 = ("Error deprojectivizing parse: number of heads ({n_heads}), "
             "projective heads ({n_proj_heads}) and labels ({n_labels}) do not "
             "match.")
@@ -957,6 +963,11 @@ class Errors(metaclass=ErrorsWithCodes):
     E1046 = ("{cls_name} is an abstract class and cannot be instantiated. If you are looking for spaCy's default "
              "knowledge base, use `InMemoryLookupKB`.")
     E1047 = ("`find_threshold()` only supports components with a `scorer` attribute.")
+    E1048 = ("Got '{unexpected}' as console progress bar type, but expected one of the following: {expected}")
+    E1049 = ("No available port found for displaCy on host {host}. Please specify an available port "
+             "with `displacy.serve(doc, port=port)`")
+    E1050 = ("Port {port} is already in use. Please specify an available port with `displacy.serve(doc, port=port)` "
+             "or use `auto_switch_port=True` to pick an available port automatically.")
 
 
 # Deprecated model shortcuts, only used in errors and warnings

spacy/kb/kb_in_memory.pyx

@@ -25,7 +25,7 @@ cdef class InMemoryLookupKB(KnowledgeBase):
     """An `InMemoryLookupKB` instance stores unique identifiers for entities and their textual aliases,
     to support entity linking of named entities to real-world concepts.
 
-    DOCS: https://spacy.io/api/kb_in_memory
+    DOCS: https://spacy.io/api/inmemorylookupkb
     """
 
     def __init__(self, Vocab vocab, entity_vector_length):

spacy/lang/nl/stop_words.py

@@ -15,7 +15,7 @@
 
 STOP_WORDS = set(
     """
-aan af al alle alles allebei alleen allen als altijd ander anders andere anderen aangaangde aangezien achter achterna
+aan af al alle alles allebei alleen allen als altijd ander anders andere anderen aangaande aangezien achter achterna
 afgelopen aldus alhoewel anderzijds
 
 ben bij bijna bijvoorbeeld behalve beide beiden beneden bent bepaald beter betere betreffende binnen binnenin boven

spacy/matcher/levenshtein.pyx

@@ -4,6 +4,8 @@ from libc.stdint cimport int64_t
 
 from typing import Optional
 
+from ..util import registry
+
 
 cdef extern from "polyleven.c":
     int64_t polyleven(PyObject *o1, PyObject *o2, int64_t k)
@@ -13,3 +15,18 @@ cpdef int64_t levenshtein(a: str, b: str, k: Optional[int] = None):
     if k is None:
         k = -1
     return polyleven(<PyObject*>a, <PyObject*>b, k)
+
+
+cpdef bint levenshtein_compare(input_text: str, pattern_text: str, fuzzy: int = -1):
+    if fuzzy >= 0:
+        max_edits = fuzzy
+    else:
+        # allow at least two edits (to allow at least one transposition) and up
+        # to 30% of the pattern string length
+        max_edits = max(2, round(0.3 * len(pattern_text)))
+    return levenshtein(input_text, pattern_text, max_edits) <= max_edits
+
+
+@registry.misc("spacy.levenshtein_compare.v1")
+def make_levenshtein_compare():
+    return levenshtein_compare

spacy/matcher/matcher.pxd

@@ -77,3 +77,4 @@ cdef class Matcher:
     cdef public object _extensions
     cdef public object _extra_predicates
     cdef public object _seen_attrs
+    cdef public object _fuzzy_compare

spacy/matcher/matcher.pyi

@@ -5,7 +5,12 @@ from ..vocab import Vocab
 from ..tokens import Doc, Span
 
 class Matcher:
-    def __init__(self, vocab: Vocab, validate: bool = ...) -> None: ...
+    def __init__(
+        self,
+        vocab: Vocab,
+        validate: bool = ...,
+        fuzzy_compare: Callable[[str, str, int], bool] = ...,
+    ) -> None: ...
     def __reduce__(self) -> Any: ...
     def __len__(self) -> int: ...
     def __contains__(self, key: str) -> bool: ...

spacy/matcher/matcher.pyx

@@ -1,4 +1,4 @@
-# cython: infer_types=True, profile=True
+# cython: binding=True, infer_types=True, profile=True
 from typing import List, Iterable
 
 from libcpp.vector cimport vector
@@ -20,10 +20,12 @@ from ..tokens.token cimport Token
 from ..tokens.morphanalysis cimport MorphAnalysis
 from ..attrs cimport ID, attr_id_t, NULL_ATTR, ORTH, POS, TAG, DEP, LEMMA, MORPH, ENT_IOB
 
+from .levenshtein import levenshtein_compare
 from ..schemas import validate_token_pattern
 from ..errors import Errors, MatchPatternError, Warnings
 from ..strings import get_string_id
 from ..attrs import IDS
+from ..util import registry
 
 
 DEF PADDING = 5
@@ -36,11 +38,13 @@ cdef class Matcher:
     USAGE: https://spacy.io/usage/rule-based-matching
     """
 
-    def __init__(self, vocab, validate=True):
+    def __init__(self, vocab, validate=True, *, fuzzy_compare=levenshtein_compare):
         """Create the Matcher.
 
         vocab (Vocab): The vocabulary object, which must be shared with the
-            documents the matcher will operate on.
+        validate (bool): Validate all patterns added to this matcher.
+        fuzzy_compare (Callable[[str, str, int], bool]): The comparison method
+            for the FUZZY operators.
         """
         self._extra_predicates = []
         self._patterns = {}
@@ -51,9 +55,10 @@ cdef class Matcher:
         self.vocab = vocab
         self.mem = Pool()
         self.validate = validate
+        self._fuzzy_compare = fuzzy_compare
 
     def __reduce__(self):
-        data = (self.vocab, self._patterns, self._callbacks)
+        data = (self.vocab, self._patterns, self._callbacks, self.validate, self._fuzzy_compare)
         return (unpickle_matcher, data, None, None)
 
     def __len__(self):
@@ -128,7 +133,7 @@ cdef class Matcher:
         for pattern in patterns:
             try:
                 specs = _preprocess_pattern(pattern, self.vocab,
-                    self._extensions, self._extra_predicates)
+                    self._extensions, self._extra_predicates, self._fuzzy_compare)
                 self.patterns.push_back(init_pattern(self.mem, key, specs))
                 for spec in specs:
                     for attr, _ in spec[1]:
@@ -326,8 +331,8 @@ cdef class Matcher:
             return key
 
 
-def unpickle_matcher(vocab, patterns, callbacks):
+def unpickle_matcher(vocab, patterns, callbacks, validate, fuzzy_compare):
-    matcher = Matcher(vocab)
+    matcher = Matcher(vocab, validate=validate, fuzzy_compare=fuzzy_compare)
     for key, pattern in patterns.items():
         callback = callbacks.get(key, None)
         matcher.add(key, pattern, on_match=callback)
@@ -754,7 +759,7 @@ cdef attr_t get_ent_id(const TokenPatternC* pattern) nogil:
     return id_attr.value
 
 
-def _preprocess_pattern(token_specs, vocab, extensions_table, extra_predicates):
+def _preprocess_pattern(token_specs, vocab, extensions_table, extra_predicates, fuzzy_compare):
     """This function interprets the pattern, converting the various bits of
     syntactic sugar before we compile it into a struct with init_pattern.
 
@@ -781,7 +786,7 @@ def _preprocess_pattern(token_specs, vocab, extensions_table, extra_predicates):
         ops = _get_operators(spec)
         attr_values = _get_attr_values(spec, string_store)
         extensions = _get_extensions(spec, string_store, extensions_table)
-        predicates = _get_extra_predicates(spec, extra_predicates, vocab)
+        predicates = _get_extra_predicates(spec, extra_predicates, vocab, fuzzy_compare)
         for op in ops:
             tokens.append((op, list(attr_values), list(extensions), list(predicates), token_idx))
     return tokens
@@ -826,16 +831,45 @@ def _get_attr_values(spec, string_store):
 # These predicate helper classes are used to match the REGEX, IN, >= etc
 # extensions to the matcher introduced in #3173.
 
+class _FuzzyPredicate:
+    operators = ("FUZZY", "FUZZY1", "FUZZY2", "FUZZY3", "FUZZY4", "FUZZY5",
+                 "FUZZY6", "FUZZY7", "FUZZY8", "FUZZY9")
+
+    def __init__(self, i, attr, value, predicate, is_extension=False, vocab=None,
+                 regex=False, fuzzy=None, fuzzy_compare=None):
+        self.i = i
+        self.attr = attr
+        self.value = value
+        self.predicate = predicate
+        self.is_extension = is_extension
+        if self.predicate not in self.operators:
+            raise ValueError(Errors.E126.format(good=self.operators, bad=self.predicate))
+        fuzz = self.predicate[len("FUZZY"):] # number after prefix
+        self.fuzzy = int(fuzz) if fuzz else -1
+        self.fuzzy_compare = fuzzy_compare
+        self.key = (self.attr, self.fuzzy, self.predicate, srsly.json_dumps(value, sort_keys=True))
+
+    def __call__(self, Token token):
+        if self.is_extension:
+            value = token._.get(self.attr)
+        else:
+            value = token.vocab.strings[get_token_attr_for_matcher(token.c, self.attr)]
+        if self.value == value:
+            return True
+        return self.fuzzy_compare(value, self.value, self.fuzzy)
+
+
 class _RegexPredicate:
     operators = ("REGEX",)
 
-    def __init__(self, i, attr, value, predicate, is_extension=False, vocab=None):
+    def __init__(self, i, attr, value, predicate, is_extension=False, vocab=None,
+                 regex=False, fuzzy=None, fuzzy_compare=None):
         self.i = i
         self.attr = attr
         self.value = re.compile(value)
         self.predicate = predicate
         self.is_extension = is_extension
-        self.key = (attr, self.predicate, srsly.json_dumps(value, sort_keys=True))
+        self.key = (self.attr, self.predicate, srsly.json_dumps(value, sort_keys=True))
         if self.predicate not in self.operators:
             raise ValueError(Errors.E126.format(good=self.operators, bad=self.predicate))
 
@@ -850,18 +884,28 @@ class _RegexPredicate:
 class _SetPredicate:
     operators = ("IN", "NOT_IN", "IS_SUBSET", "IS_SUPERSET", "INTERSECTS")
 
-    def __init__(self, i, attr, value, predicate, is_extension=False, vocab=None):
+    def __init__(self, i, attr, value, predicate, is_extension=False, vocab=None,
+                 regex=False, fuzzy=None, fuzzy_compare=None):
         self.i = i
         self.attr = attr
         self.vocab = vocab
+        self.regex = regex
+        self.fuzzy = fuzzy
+        self.fuzzy_compare = fuzzy_compare
         if self.attr == MORPH:
             # normalize morph strings
             self.value = set(self.vocab.morphology.add(v) for v in value)
+        else:
+            if self.regex:
+                self.value = set(re.compile(v) for v in value)
+            elif self.fuzzy is not None:
+                # add to string store
+                self.value = set(self.vocab.strings.add(v) for v in value)
             else:
                 self.value = set(get_string_id(v) for v in value)
         self.predicate = predicate
         self.is_extension = is_extension
-        self.key = (attr, self.predicate, srsly.json_dumps(value, sort_keys=True))
+        self.key = (self.attr, self.regex, self.fuzzy, self.predicate, srsly.json_dumps(value, sort_keys=True))
         if self.predicate not in self.operators:
             raise ValueError(Errors.E126.format(good=self.operators, bad=self.predicate))
 
@@ -889,9 +933,29 @@ class _SetPredicate:
                 return False
 
         if self.predicate == "IN":
-            return value in self.value
+            if self.regex:
+                value = self.vocab.strings[value]
+                return any(bool(v.search(value)) for v in self.value)
+            elif self.fuzzy is not None:
+                value = self.vocab.strings[value]
+                return any(self.fuzzy_compare(value, self.vocab.strings[v], self.fuzzy)
+                           for v in self.value)
+            elif value in self.value:
+                return True
+            else:
+                return False
         elif self.predicate == "NOT_IN":
-            return value not in self.value
+            if self.regex:
+                value = self.vocab.strings[value]
+                return not any(bool(v.search(value)) for v in self.value)
+            elif self.fuzzy is not None:
+                value = self.vocab.strings[value]
+                return not any(self.fuzzy_compare(value, self.vocab.strings[v], self.fuzzy)
+                               for v in self.value)
+            elif value in self.value:
+                return False
+            else:
+                return True
         elif self.predicate == "IS_SUBSET":
             return value <= self.value
         elif self.predicate == "IS_SUPERSET":
@@ -906,13 +970,14 @@ class _SetPredicate:
 class _ComparisonPredicate:
     operators = ("==", "!=", ">=", "<=", ">", "<")
 
-    def __init__(self, i, attr, value, predicate, is_extension=False, vocab=None):
+    def __init__(self, i, attr, value, predicate, is_extension=False, vocab=None,
+                 regex=False, fuzzy=None, fuzzy_compare=None):
         self.i = i
         self.attr = attr
         self.value = value
         self.predicate = predicate
         self.is_extension = is_extension
-        self.key = (attr, self.predicate, srsly.json_dumps(value, sort_keys=True))
+        self.key = (self.attr, self.predicate, srsly.json_dumps(value, sort_keys=True))
         if self.predicate not in self.operators:
             raise ValueError(Errors.E126.format(good=self.operators, bad=self.predicate))
 
@@ -935,7 +1000,7 @@ class _ComparisonPredicate:
             return value < self.value
 
 
-def _get_extra_predicates(spec, extra_predicates, vocab):
+def _get_extra_predicates(spec, extra_predicates, vocab, fuzzy_compare):
     predicate_types = {
         "REGEX": _RegexPredicate,
         "IN": _SetPredicate,
@@ -949,6 +1014,16 @@ def _get_extra_predicates(spec, extra_predicates, vocab):
         "<=": _ComparisonPredicate,
         ">": _ComparisonPredicate,
         "<": _ComparisonPredicate,
+        "FUZZY": _FuzzyPredicate,
+        "FUZZY1": _FuzzyPredicate,
+        "FUZZY2": _FuzzyPredicate,
+        "FUZZY3": _FuzzyPredicate,
+        "FUZZY4": _FuzzyPredicate,
+        "FUZZY5": _FuzzyPredicate,
+        "FUZZY6": _FuzzyPredicate,
+        "FUZZY7": _FuzzyPredicate,
+        "FUZZY8": _FuzzyPredicate,
+        "FUZZY9": _FuzzyPredicate,
     }
     seen_predicates = {pred.key: pred.i for pred in extra_predicates}
     output = []
@@ -966,12 +1041,40 @@ def _get_extra_predicates(spec, extra_predicates, vocab):
                 attr = "ORTH"
             attr = IDS.get(attr.upper())
         if isinstance(value, dict):
-            processed = False
+            output.extend(_get_extra_predicates_dict(attr, value, vocab, predicate_types,
-            value_with_upper_keys = {k.upper(): v for k, v in value.items()}
+                                                     extra_predicates, seen_predicates, fuzzy_compare=fuzzy_compare))
-            for type_, cls in predicate_types.items():
+    return output
-                if type_ in value_with_upper_keys:
+
-                    predicate = cls(len(extra_predicates), attr, value_with_upper_keys[type_], type_, vocab=vocab)
+
-                    # Don't create a redundant predicates.
+def _get_extra_predicates_dict(attr, value_dict, vocab, predicate_types,
+                               extra_predicates, seen_predicates, regex=False, fuzzy=None, fuzzy_compare=None):
+    output = []
+    for type_, value in value_dict.items():
+        type_ = type_.upper()
+        cls = predicate_types.get(type_)
+        if cls is None:
+            warnings.warn(Warnings.W035.format(pattern=value_dict))
+            # ignore unrecognized predicate type
+            continue
+        elif cls == _RegexPredicate:
+            if isinstance(value, dict):
+                # add predicates inside regex operator
+                output.extend(_get_extra_predicates_dict(attr, value, vocab, predicate_types,
+                                                         extra_predicates, seen_predicates,
+                                                         regex=True))
+                continue
+        elif cls == _FuzzyPredicate:
+            if isinstance(value, dict):
+                # add predicates inside fuzzy operator
+                fuzz = type_[len("FUZZY"):] # number after prefix
+                fuzzy_val = int(fuzz) if fuzz else -1
+                output.extend(_get_extra_predicates_dict(attr, value, vocab, predicate_types,
+                                                         extra_predicates, seen_predicates,
+                                                         fuzzy=fuzzy_val, fuzzy_compare=fuzzy_compare))
+                continue
+        predicate = cls(len(extra_predicates), attr, value, type_, vocab=vocab,
+                        regex=regex, fuzzy=fuzzy, fuzzy_compare=fuzzy_compare)
+        # Don't create redundant predicates.
         # This helps with efficiency, as we're caching the results.
         if predicate.key in seen_predicates:
             output.append(seen_predicates[predicate.key])
@@ -979,9 +1082,6 @@ def _get_extra_predicates(spec, extra_predicates, vocab):
             extra_predicates.append(predicate)
             output.append(predicate.i)
             seen_predicates[predicate.key] = predicate.i
-                    processed = True
-            if not processed:
-                warnings.warn(Warnings.W035.format(pattern=value))
     return output
 
 

spacy/pipeline/edit_tree_lemmatizer.py

@@ -128,7 +128,7 @@ class EditTreeLemmatizer(TrainablePipe):
             for (predicted, gold_lemma) in zip(
                 eg.predicted, eg.get_aligned("LEMMA", as_string=True)
             ):
-                if gold_lemma is None:
+                if gold_lemma is None or gold_lemma == "":
                     label = -1
                 else:
                     tree_id = self.trees.add(predicted.text, gold_lemma)
@@ -328,9 +328,9 @@ class EditTreeLemmatizer(TrainablePipe):
 
             tree = dict(tree)
             if "orig" in tree:
-                tree["orig"] = self.vocab.strings[tree["orig"]]
+                tree["orig"] = self.vocab.strings.add(tree["orig"])
             if "orig" in tree:
-                tree["subst"] = self.vocab.strings[tree["subst"]]
+                tree["subst"] = self.vocab.strings.add(tree["subst"])
 
             trees.append(tree)
 

spacy/pipeline/entityruler.py

@@ -11,6 +11,7 @@ from ..errors import Errors, Warnings
 from ..util import ensure_path, to_disk, from_disk, SimpleFrozenList, registry
 from ..tokens import Doc, Span
 from ..matcher import Matcher, PhraseMatcher
+from ..matcher.levenshtein import levenshtein_compare
 from ..scorer import get_ner_prf
 
 
@@ -23,6 +24,7 @@ PatternType = Dict[str, Union[str, List[Dict[str, Any]]]]
     assigns=["doc.ents", "token.ent_type", "token.ent_iob"],
     default_config={
         "phrase_matcher_attr": None,
+        "matcher_fuzzy_compare": {"@misc": "spacy.levenshtein_compare.v1"},
         "validate": False,
         "overwrite_ents": False,
         "ent_id_sep": DEFAULT_ENT_ID_SEP,
@@ -39,6 +41,7 @@ def make_entity_ruler(
     nlp: Language,
     name: str,
     phrase_matcher_attr: Optional[Union[int, str]],
+    matcher_fuzzy_compare: Callable,
     validate: bool,
     overwrite_ents: bool,
     ent_id_sep: str,
@@ -48,6 +51,7 @@ def make_entity_ruler(
         nlp,
         name,
         phrase_matcher_attr=phrase_matcher_attr,
+        matcher_fuzzy_compare=matcher_fuzzy_compare,
         validate=validate,
         overwrite_ents=overwrite_ents,
         ent_id_sep=ent_id_sep,
@@ -81,6 +85,7 @@ class EntityRuler(Pipe):
         name: str = "entity_ruler",
         *,
         phrase_matcher_attr: Optional[Union[int, str]] = None,
+        matcher_fuzzy_compare: Callable = levenshtein_compare,
         validate: bool = False,
         overwrite_ents: bool = False,
         ent_id_sep: str = DEFAULT_ENT_ID_SEP,
@@ -99,7 +104,10 @@ class EntityRuler(Pipe):
             added. Used to disable the current entity ruler while creating
             phrase patterns with the nlp object.
         phrase_matcher_attr (int / str): Token attribute to match on, passed
-            to the internal PhraseMatcher as `attr`
+            to the internal PhraseMatcher as `attr`.
+        matcher_fuzzy_compare (Callable): The fuzzy comparison method for the
+            internal Matcher. Defaults to
+            spacy.matcher.levenshtein.levenshtein_compare.
         validate (bool): Whether patterns should be validated, passed to
             Matcher and PhraseMatcher as `validate`
         patterns (iterable): Optional patterns to load in.
@@ -117,7 +125,10 @@ class EntityRuler(Pipe):
         self.token_patterns = defaultdict(list)  # type: ignore
         self.phrase_patterns = defaultdict(list)  # type: ignore
         self._validate = validate
-        self.matcher = Matcher(nlp.vocab, validate=validate)
+        self.matcher_fuzzy_compare = matcher_fuzzy_compare
+        self.matcher = Matcher(
+            nlp.vocab, validate=validate, fuzzy_compare=self.matcher_fuzzy_compare
+        )
         self.phrase_matcher_attr = phrase_matcher_attr
         self.phrase_matcher = PhraseMatcher(
             nlp.vocab, attr=self.phrase_matcher_attr, validate=validate
@@ -337,7 +348,11 @@ class EntityRuler(Pipe):
         self.token_patterns = defaultdict(list)
         self.phrase_patterns = defaultdict(list)
         self._ent_ids = defaultdict(tuple)
-        self.matcher = Matcher(self.nlp.vocab, validate=self._validate)
+        self.matcher = Matcher(
+            self.nlp.vocab,
+            validate=self._validate,
+            fuzzy_compare=self.matcher_fuzzy_compare,
+        )
         self.phrase_matcher = PhraseMatcher(
             self.nlp.vocab, attr=self.phrase_matcher_attr, validate=self._validate
         )
@@ -431,7 +446,8 @@ class EntityRuler(Pipe):
             self.overwrite = cfg.get("overwrite", False)
             self.phrase_matcher_attr = cfg.get("phrase_matcher_attr", None)
             self.phrase_matcher = PhraseMatcher(
-                self.nlp.vocab, attr=self.phrase_matcher_attr
+                self.nlp.vocab,
+                attr=self.phrase_matcher_attr,
             )
             self.ent_id_sep = cfg.get("ent_id_sep", DEFAULT_ENT_ID_SEP)
         else:

spacy/pipeline/span_ruler.py

@@ -13,6 +13,7 @@ from ..util import ensure_path, SimpleFrozenList, registry
 from ..tokens import Doc, Span
 from ..scorer import Scorer
 from ..matcher import Matcher, PhraseMatcher
+from ..matcher.levenshtein import levenshtein_compare
 from .. import util
 
 PatternType = Dict[str, Union[str, List[Dict[str, Any]]]]
@@ -28,6 +29,7 @@ DEFAULT_SPANS_KEY = "ruler"
         "overwrite_ents": False,
         "scorer": {"@scorers": "spacy.entity_ruler_scorer.v1"},
         "ent_id_sep": "__unused__",
+        "matcher_fuzzy_compare": {"@misc": "spacy.levenshtein_compare.v1"},
     },
     default_score_weights={
         "ents_f": 1.0,
@@ -40,6 +42,7 @@ def make_entity_ruler(
     nlp: Language,
     name: str,
     phrase_matcher_attr: Optional[Union[int, str]],
+    matcher_fuzzy_compare: Callable,
     validate: bool,
     overwrite_ents: bool,
     scorer: Optional[Callable],
@@ -57,6 +60,7 @@ def make_entity_ruler(
         annotate_ents=True,
         ents_filter=ents_filter,
         phrase_matcher_attr=phrase_matcher_attr,
+        matcher_fuzzy_compare=matcher_fuzzy_compare,
         validate=validate,
         overwrite=False,
         scorer=scorer,
@@ -72,6 +76,7 @@ def make_entity_ruler(
         "annotate_ents": False,
         "ents_filter": {"@misc": "spacy.first_longest_spans_filter.v1"},
         "phrase_matcher_attr": None,
+        "matcher_fuzzy_compare": {"@misc": "spacy.levenshtein_compare.v1"},
         "validate": False,
         "overwrite": True,
         "scorer": {
@@ -94,6 +99,7 @@ def make_span_ruler(
     annotate_ents: bool,
     ents_filter: Callable[[Iterable[Span], Iterable[Span]], Iterable[Span]],
     phrase_matcher_attr: Optional[Union[int, str]],
+    matcher_fuzzy_compare: Callable,
     validate: bool,
     overwrite: bool,
     scorer: Optional[Callable],
@@ -106,6 +112,7 @@ def make_span_ruler(
         annotate_ents=annotate_ents,
         ents_filter=ents_filter,
         phrase_matcher_attr=phrase_matcher_attr,
+        matcher_fuzzy_compare=matcher_fuzzy_compare,
         validate=validate,
         overwrite=overwrite,
         scorer=scorer,
@@ -170,7 +177,7 @@ def prioritize_existing_ents_filter(
 
 
 @registry.misc("spacy.prioritize_existing_ents_filter.v1")
-def make_preverse_existing_ents_filter():
+def make_preserve_existing_ents_filter():
     return prioritize_existing_ents_filter
 
 
@@ -216,6 +223,7 @@ class SpanRuler(Pipe):
             [Iterable[Span], Iterable[Span]], Iterable[Span]
         ] = util.filter_chain_spans,
         phrase_matcher_attr: Optional[Union[int, str]] = None,
+        matcher_fuzzy_compare: Callable = levenshtein_compare,
         validate: bool = False,
         overwrite: bool = False,
         scorer: Optional[Callable] = partial(
@@ -246,6 +254,9 @@ class SpanRuler(Pipe):
         phrase_matcher_attr (Optional[Union[int, str]]): Token attribute to
             match on, passed to the internal PhraseMatcher as `attr`. Defaults
             to `None`.
+        matcher_fuzzy_compare (Callable): The fuzzy comparison method for the
+            internal Matcher. Defaults to
+            spacy.matcher.levenshtein.levenshtein_compare.
         validate (bool): Whether patterns should be validated, passed to
             Matcher and PhraseMatcher as `validate`.
         overwrite (bool): Whether to remove any existing spans under this spans
@@ -266,6 +277,7 @@ class SpanRuler(Pipe):
         self.spans_filter = spans_filter
         self.ents_filter = ents_filter
         self.scorer = scorer
+        self.matcher_fuzzy_compare = matcher_fuzzy_compare
         self._match_label_id_map: Dict[int, Dict[str, str]] = {}
         self.clear()
 
@@ -451,7 +463,11 @@ class SpanRuler(Pipe):
         DOCS: https://spacy.io/api/spanruler#clear
         """
         self._patterns: List[PatternType] = []
-        self.matcher: Matcher = Matcher(self.nlp.vocab, validate=self.validate)
+        self.matcher: Matcher = Matcher(
+            self.nlp.vocab,
+            validate=self.validate,
+            fuzzy_compare=self.matcher_fuzzy_compare,
+        )
         self.phrase_matcher: PhraseMatcher = PhraseMatcher(
             self.nlp.vocab,
             attr=self.phrase_matcher_attr,

spacy/pipeline/spancat.py

@@ -272,6 +272,9 @@ class SpanCategorizer(TrainablePipe):
         DOCS: https://spacy.io/api/spancategorizer#predict
         """
         indices = self.suggester(docs, ops=self.model.ops)
+        if indices.lengths.sum() == 0:
+            scores = self.model.ops.alloc2f(0, 0)
+        else:
             scores = self.model.predict((docs, indices))  # type: ignore
         return indices, scores
 

spacy/pipeline/textcat.py

@@ -74,7 +74,7 @@ subword_features = true
     default_config={
         "threshold": 0.0,
         "model": DEFAULT_SINGLE_TEXTCAT_MODEL,
-        "scorer": {"@scorers": "spacy.textcat_scorer.v1"},
+        "scorer": {"@scorers": "spacy.textcat_scorer.v2"},
     },
     default_score_weights={
         "cats_score": 1.0,
@@ -117,7 +117,7 @@ def textcat_score(examples: Iterable[Example], **kwargs) -> Dict[str, Any]:
     )
 
 
-@registry.scorers("spacy.textcat_scorer.v1")
+@registry.scorers("spacy.textcat_scorer.v2")
 def make_textcat_scorer():
     return textcat_score
 

spacy/pipeline/textcat_multilabel.py

@@ -74,7 +74,7 @@ subword_features = true
     default_config={
         "threshold": 0.5,
         "model": DEFAULT_MULTI_TEXTCAT_MODEL,
-        "scorer": {"@scorers": "spacy.textcat_multilabel_scorer.v1"},
+        "scorer": {"@scorers": "spacy.textcat_multilabel_scorer.v2"},
     },
     default_score_weights={
         "cats_score": 1.0,
@@ -120,7 +120,7 @@ def textcat_multilabel_score(examples: Iterable[Example], **kwargs) -> Dict[str,
     )
 
 
-@registry.scorers("spacy.textcat_multilabel_scorer.v1")
+@registry.scorers("spacy.textcat_multilabel_scorer.v2")
 def make_textcat_multilabel_scorer():
     return textcat_multilabel_score
 

spacy/schemas.py

@@ -156,12 +156,40 @@ def validate_token_pattern(obj: list) -> List[str]:
 
 
 class TokenPatternString(BaseModel):
-    REGEX: Optional[StrictStr] = Field(None, alias="regex")
+    REGEX: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="regex")
     IN: Optional[List[StrictStr]] = Field(None, alias="in")
     NOT_IN: Optional[List[StrictStr]] = Field(None, alias="not_in")
     IS_SUBSET: Optional[List[StrictStr]] = Field(None, alias="is_subset")
     IS_SUPERSET: Optional[List[StrictStr]] = Field(None, alias="is_superset")
     INTERSECTS: Optional[List[StrictStr]] = Field(None, alias="intersects")
+    FUZZY: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy")
+    FUZZY1: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy1"
+    )
+    FUZZY2: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy2"
+    )
+    FUZZY3: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy3"
+    )
+    FUZZY4: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy4"
+    )
+    FUZZY5: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy5"
+    )
+    FUZZY6: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy6"
+    )
+    FUZZY7: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy7"
+    )
+    FUZZY8: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy8"
+    )
+    FUZZY9: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy9"
+    )
 
     class Config:
         extra = "forbid"

spacy/scorer.py

@@ -174,7 +174,7 @@ class Scorer:
             prf_score.score_set(pred_spans, gold_spans)
         if len(acc_score) > 0:
             return {
-                "token_acc": acc_score.fscore,
+                "token_acc": acc_score.precision,
                 "token_p": prf_score.precision,
                 "token_r": prf_score.recall,
                 "token_f": prf_score.fscore,
@@ -476,14 +476,12 @@ class Scorer:
         f_per_type = {label: PRFScore() for label in labels}
         auc_per_type = {label: ROCAUCScore() for label in labels}
         labels = set(labels)
-        if labels:
-            for eg in examples:
-                labels.update(eg.predicted.cats.keys())
-                labels.update(eg.reference.cats.keys())
         for example in examples:
             # Through this loop, None in the gold_cats indicates missing label.
             pred_cats = getter(example.predicted, attr)
+            pred_cats = {k: v for k, v in pred_cats.items() if k in labels}
             gold_cats = getter(example.reference, attr)
+            gold_cats = {k: v for k, v in gold_cats.items() if k in labels}
 
             for label in labels:
                 pred_score = pred_cats.get(label, 0.0)

spacy/tests/doc/test_array.py

@@ -123,14 +123,14 @@ def test_doc_from_array_heads_in_bounds(en_vocab):
 
     # head before start
     arr = doc.to_array(["HEAD"])
-    arr[0] = -1
+    arr[0] = numpy.int32(-1).astype(numpy.uint64)
     doc_from_array = Doc(en_vocab, words=words)
     with pytest.raises(ValueError):
         doc_from_array.from_array(["HEAD"], arr)
 
     # head after end
     arr = doc.to_array(["HEAD"])
-    arr[0] = 5
+    arr[0] = numpy.int32(5).astype(numpy.uint64)
     doc_from_array = Doc(en_vocab, words=words)
     with pytest.raises(ValueError):
         doc_from_array.from_array(["HEAD"], arr)

spacy/tests/doc/test_span_group.py

@@ -1,7 +1,10 @@
+from typing import List
+
 import pytest
 from random import Random
 from spacy.matcher import Matcher
-from spacy.tokens import Span, SpanGroup
+from spacy.tokens import Span, SpanGroup, Doc
+from spacy.util import filter_spans
 
 
 @pytest.fixture
@@ -240,3 +243,13 @@ def test_span_group_extend(doc):
 def test_span_group_dealloc(span_group):
     with pytest.raises(AttributeError):
         print(span_group.doc)
+
+
+@pytest.mark.issue(11975)
+def test_span_group_typing(doc: Doc):
+    """Tests whether typing of `SpanGroup` as `Iterable[Span]`-like object is accepted by mypy."""
+    span_group: SpanGroup = doc.spans["SPANS"]
+    spans: List[Span] = list(span_group)
+    for i, span in enumerate(span_group):
+        assert span == span_group[i] == spans[i]
+    filter_spans(span_group)

spacy/tests/matcher/test_levenshtein.py

@@ -1,5 +1,6 @@
 import pytest
 from spacy.matcher import levenshtein
+from spacy.matcher.levenshtein import levenshtein_compare
 
 
 # empty string plus 10 random ASCII, 10 random unicode, and 2 random long tests
@@ -42,3 +43,31 @@ from spacy.matcher import levenshtein
 )
 def test_levenshtein(dist, a, b):
     assert levenshtein(a, b) == dist
+
+
+@pytest.mark.parametrize(
+    "a,b,fuzzy,expected",
+    [
+        ("a", "a", 1, True),
+        ("a", "a", 0, True),
+        ("a", "a", -1, True),
+        ("a", "ab", 1, True),
+        ("a", "ab", 0, False),
+        ("a", "ab", -1, True),
+        ("ab", "ac", 1, True),
+        ("ab", "ac", -1, True),
+        ("abc", "cde", 4, True),
+        ("abc", "cde", -1, False),
+        ("abcdef", "cdefgh", 4, True),
+        ("abcdef", "cdefgh", 3, False),
+        ("abcdef", "cdefgh", -1, False),  # default (2 for length 6)
+        ("abcdefgh", "cdefghijk", 5, True),
+        ("abcdefgh", "cdefghijk", 4, False),
+        ("abcdefgh", "cdefghijk", -1, False),  # default (2)
+        ("abcdefgh", "cdefghijkl", 6, True),
+        ("abcdefgh", "cdefghijkl", 5, False),
+        ("abcdefgh", "cdefghijkl", -1, False),  # default (2)
+    ],
+)
+def test_levenshtein_compare(a, b, fuzzy, expected):
+    assert levenshtein_compare(a, b, fuzzy) == expected

spacy/tests/matcher/test_matcher_api.py

@@ -118,6 +118,155 @@ def test_matcher_match_multi(matcher):
     ]
 
 
+@pytest.mark.parametrize(
+    "rules,match_locs",
+    [
+        (
+            {
+                "GoogleNow": [[{"ORTH": {"FUZZY": "Google"}}, {"ORTH": "Now"}]],
+            },
+            [(2, 4)],
+        ),
+        (
+            {
+                "Java": [[{"LOWER": {"FUZZY": "java"}}]],
+            },
+            [(5, 6)],
+        ),
+        (
+            {
+                "JS": [[{"ORTH": {"FUZZY": "JavaScript"}}]],
+                "GoogleNow": [[{"ORTH": {"FUZZY": "Google"}}, {"ORTH": "Now"}]],
+                "Java": [[{"LOWER": {"FUZZY": "java"}}]],
+            },
+            [(2, 4), (5, 6), (8, 9)],
+        ),
+        # only the second pattern matches (check that predicate keys used for
+        # caching don't collide)
+        (
+            {
+                "A": [[{"ORTH": {"FUZZY": "Javascripts"}}]],
+                "B": [[{"ORTH": {"FUZZY5": "Javascripts"}}]],
+            },
+            [(8, 9)],
+        ),
+    ],
+)
+def test_matcher_match_fuzzy(en_vocab, rules, match_locs):
+    words = ["They", "like", "Goggle", "Now", "and", "Jav", "but", "not", "JvvaScrpt"]
+    doc = Doc(en_vocab, words=words)
+
+    matcher = Matcher(en_vocab)
+    for key, patterns in rules.items():
+        matcher.add(key, patterns)
+    assert match_locs == [(start, end) for m_id, start, end in matcher(doc)]
+
+
+@pytest.mark.parametrize("set_op", ["IN", "NOT_IN"])
+def test_matcher_match_fuzzy_set_op_longest(en_vocab, set_op):
+    rules = {
+        "GoogleNow": [[{"ORTH": {"FUZZY": {set_op: ["Google", "Now"]}}, "OP": "+"}]]
+    }
+    matcher = Matcher(en_vocab)
+    for key, patterns in rules.items():
+        matcher.add(key, patterns, greedy="LONGEST")
+
+    words = ["They", "like", "Goggle", "Noo"]
+    doc = Doc(en_vocab, words=words)
+    assert len(matcher(doc)) == 1
+
+
+def test_matcher_match_fuzzy_set_multiple(en_vocab):
+    rules = {
+        "GoogleNow": [
+            [
+                {
+                    "ORTH": {"FUZZY": {"IN": ["Google", "Now"]}, "NOT_IN": ["Goggle"]},
+                    "OP": "+",
+                }
+            ]
+        ]
+    }
+    matcher = Matcher(en_vocab)
+    for key, patterns in rules.items():
+        matcher.add(key, patterns, greedy="LONGEST")
+
+    words = ["They", "like", "Goggle", "Noo"]
+    doc = Doc(matcher.vocab, words=words)
+    assert matcher(doc) == [
+        (doc.vocab.strings["GoogleNow"], 3, 4),
+    ]
+
+
+@pytest.mark.parametrize("fuzzyn", range(1, 10))
+def test_matcher_match_fuzzyn_all_insertions(en_vocab, fuzzyn):
+    matcher = Matcher(en_vocab)
+    matcher.add("GoogleNow", [[{"ORTH": {f"FUZZY{fuzzyn}": "GoogleNow"}}]])
+    # words with increasing edit distance
+    words = ["GoogleNow" + "a" * i for i in range(0, 10)]
+    doc = Doc(en_vocab, words)
+    assert len(matcher(doc)) == fuzzyn + 1
+
+
+@pytest.mark.parametrize("fuzzyn", range(1, 6))
+def test_matcher_match_fuzzyn_various_edits(en_vocab, fuzzyn):
+    matcher = Matcher(en_vocab)
+    matcher.add("GoogleNow", [[{"ORTH": {f"FUZZY{fuzzyn}": "GoogleNow"}}]])
+    # words with increasing edit distance of different edit types
+    words = [
+        "GoogleNow",
+        "GoogleNuw",
+        "GoogleNuew",
+        "GoogleNoweee",
+        "GiggleNuw3",
+        "gouggle5New",
+    ]
+    doc = Doc(en_vocab, words)
+    assert len(matcher(doc)) == fuzzyn + 1
+
+
+@pytest.mark.parametrize("greedy", ["FIRST", "LONGEST"])
+@pytest.mark.parametrize("set_op", ["IN", "NOT_IN"])
+def test_matcher_match_fuzzyn_set_op_longest(en_vocab, greedy, set_op):
+    rules = {
+        "GoogleNow": [[{"ORTH": {"FUZZY2": {set_op: ["Google", "Now"]}}, "OP": "+"}]]
+    }
+    matcher = Matcher(en_vocab)
+    for key, patterns in rules.items():
+        matcher.add(key, patterns, greedy=greedy)
+
+    words = ["They", "like", "Goggle", "Noo"]
+    doc = Doc(matcher.vocab, words=words)
+    spans = matcher(doc, as_spans=True)
+    assert len(spans) == 1
+    if set_op == "IN":
+        assert spans[0].text == "Goggle Noo"
+    else:
+        assert spans[0].text == "They like"
+
+
+def test_matcher_match_fuzzyn_set_multiple(en_vocab):
+    rules = {
+        "GoogleNow": [
+            [
+                {
+                    "ORTH": {"FUZZY1": {"IN": ["Google", "Now"]}, "NOT_IN": ["Goggle"]},
+                    "OP": "+",
+                }
+            ]
+        ]
+    }
+    matcher = Matcher(en_vocab)
+    for key, patterns in rules.items():
+        matcher.add(key, patterns, greedy="LONGEST")
+
+    words = ["They", "like", "Goggle", "Noo"]
+    doc = Doc(matcher.vocab, words=words)
+    assert matcher(doc) == [
+        (doc.vocab.strings["GoogleNow"], 3, 4),
+    ]
+
+
 def test_matcher_empty_dict(en_vocab):
     """Test matcher allows empty token specs, meaning match on any token."""
     matcher = Matcher(en_vocab)
@@ -437,6 +586,30 @@ def test_matcher_regex(en_vocab):
     assert len(matches) == 0
 
 
+def test_matcher_regex_set_in(en_vocab):
+    matcher = Matcher(en_vocab)
+    pattern = [{"ORTH": {"REGEX": {"IN": [r"(?:a)", r"(?:an)"]}}}]
+    matcher.add("A_OR_AN", [pattern])
+    doc = Doc(en_vocab, words=["an", "a", "hi"])
+    matches = matcher(doc)
+    assert len(matches) == 2
+    doc = Doc(en_vocab, words=["bye"])
+    matches = matcher(doc)
+    assert len(matches) == 0
+
+
+def test_matcher_regex_set_not_in(en_vocab):
+    matcher = Matcher(en_vocab)
+    pattern = [{"ORTH": {"REGEX": {"NOT_IN": [r"(?:a)", r"(?:an)"]}}}]
+    matcher.add("A_OR_AN", [pattern])
+    doc = Doc(en_vocab, words=["an", "a", "hi"])
+    matches = matcher(doc)
+    assert len(matches) == 1
+    doc = Doc(en_vocab, words=["bye"])
+    matches = matcher(doc)
+    assert len(matches) == 1
+
+
 def test_matcher_regex_shape(en_vocab):
     matcher = Matcher(en_vocab)
     pattern = [{"SHAPE": {"REGEX": r"^[^x]+$"}}]

spacy/tests/pipeline/test_edit_tree_lemmatizer.py

@@ -60,10 +60,45 @@ def test_initialize_from_labels():
     nlp2 = Language()
     lemmatizer2 = nlp2.add_pipe("trainable_lemmatizer")
     lemmatizer2.initialize(
-        get_examples=lambda: train_examples,
+        # We want to check that the strings in replacement nodes are
+        # added to the string store. Avoid that they get added through
+        # the examples.
+        get_examples=lambda: train_examples[:1],
         labels=lemmatizer.label_data,
     )
     assert lemmatizer2.tree2label == {1: 0, 3: 1, 4: 2, 6: 3}
+    assert lemmatizer2.label_data == {
+        "trees": [
+            {"orig": "S", "subst": "s"},
+            {
+                "prefix_len": 1,
+                "suffix_len": 0,
+                "prefix_tree": 0,
+                "suffix_tree": 4294967295,
+            },
+            {"orig": "s", "subst": ""},
+            {
+                "prefix_len": 0,
+                "suffix_len": 1,
+                "prefix_tree": 4294967295,
+                "suffix_tree": 2,
+            },
+            {
+                "prefix_len": 0,
+                "suffix_len": 0,
+                "prefix_tree": 4294967295,
+                "suffix_tree": 4294967295,
+            },
+            {"orig": "E", "subst": "e"},
+            {
+                "prefix_len": 1,
+                "suffix_len": 0,
+                "prefix_tree": 5,
+                "suffix_tree": 4294967295,
+            },
+        ],
+        "labels": (1, 3, 4, 6),
+    }
 
 
 def test_no_data():
@@ -104,6 +139,20 @@ def test_incomplete_data():
     assert doc[1].lemma_ == "like"
     assert doc[2].lemma_ == "blue"
 
+    # Check that incomplete annotations are ignored.
+    scores, _ = lemmatizer.model([eg.predicted for eg in train_examples], is_train=True)
+    _, dX = lemmatizer.get_loss(train_examples, scores)
+    xp = lemmatizer.model.ops.xp
+
+    # Missing annotations.
+    assert xp.count_nonzero(dX[0][0]) == 0
+    assert xp.count_nonzero(dX[0][3]) == 0
+    assert xp.count_nonzero(dX[1][0]) == 0
+    assert xp.count_nonzero(dX[1][3]) == 0
+
+    # Misaligned annotations.
+    assert xp.count_nonzero(dX[1][1]) == 0
+
 
 def test_overfitting_IO():
     nlp = English()

spacy/tests/pipeline/test_entity_ruler.py

@@ -382,6 +382,43 @@ def test_entity_ruler_overlapping_spans(nlp, entity_ruler_factory):
     assert doc.ents[0].label_ == "FOOBAR"
 
 
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_entity_ruler_fuzzy_pipe(nlp, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
+    patterns = [{"label": "HELLO", "pattern": [{"LOWER": {"FUZZY": "hello"}}]}]
+    ruler.add_patterns(patterns)
+    doc = nlp("helloo")
+    assert len(doc.ents) == 1
+    assert doc.ents[0].label_ == "HELLO"
+
+
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_entity_ruler_fuzzy(nlp, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
+    patterns = [{"label": "HELLO", "pattern": [{"LOWER": {"FUZZY": "hello"}}]}]
+    ruler.add_patterns(patterns)
+    doc = nlp("helloo")
+    assert len(doc.ents) == 1
+    assert doc.ents[0].label_ == "HELLO"
+
+
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_entity_ruler_fuzzy_disabled(nlp, entity_ruler_factory):
+    @registry.misc("test_fuzzy_compare_disabled")
+    def make_test_fuzzy_compare_disabled():
+        return lambda x, y, z: False
+
+    ruler = nlp.add_pipe(
+        entity_ruler_factory,
+        name="entity_ruler",
+        config={"matcher_fuzzy_compare": {"@misc": "test_fuzzy_compare_disabled"}},
+    )
+    patterns = [{"label": "HELLO", "pattern": [{"LOWER": {"FUZZY": "hello"}}]}]
+    ruler.add_patterns(patterns)
+    doc = nlp("helloo")
+    assert len(doc.ents) == 0
+
+
 @pytest.mark.parametrize("n_process", [1, 2])
 @pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
 def test_entity_ruler_multiprocessing(nlp, n_process, entity_ruler_factory):

spacy/tests/pipeline/test_spancat.py

@@ -372,24 +372,39 @@ def test_overfitting_IO_overlapping():
 
 
 def test_zero_suggestions():
-    # Test with a suggester that returns 0 suggestions
+    # Test with a suggester that can return 0 suggestions
 
-    @registry.misc("test_zero_suggester")
+    @registry.misc("test_mixed_zero_suggester")
-    def make_zero_suggester():
+    def make_mixed_zero_suggester():
-        def zero_suggester(docs, *, ops=None):
+        def mixed_zero_suggester(docs, *, ops=None):
             if ops is None:
                 ops = get_current_ops()
-            return Ragged(
+            spans = []
-                ops.xp.zeros((0, 0), dtype="i"), ops.xp.zeros((len(docs),), dtype="i")
+            lengths = []
-            )
+            for doc in docs:
+                if len(doc) > 0 and len(doc) % 2 == 0:
+                    spans.append((0, 1))
+                    lengths.append(1)
+                else:
+                    lengths.append(0)
+            spans = ops.asarray2i(spans)
+            lengths_array = ops.asarray1i(lengths)
+            if len(spans) > 0:
+                output = Ragged(ops.xp.vstack(spans), lengths_array)
+            else:
+                output = Ragged(ops.xp.zeros((0, 0), dtype="i"), lengths_array)
+            return output
 
-        return zero_suggester
+        return mixed_zero_suggester
 
     fix_random_seed(0)
     nlp = English()
     spancat = nlp.add_pipe(
         "spancat",
-        config={"suggester": {"@misc": "test_zero_suggester"}, "spans_key": SPAN_KEY},
+        config={
+            "suggester": {"@misc": "test_mixed_zero_suggester"},
+            "spans_key": SPAN_KEY,
+        },
     )
     train_examples = make_examples(nlp)
     optimizer = nlp.initialize(get_examples=lambda: train_examples)
@@ -397,6 +412,16 @@ def test_zero_suggestions():
     assert set(spancat.labels) == {"LOC", "PERSON"}
 
     nlp.update(train_examples, sgd=optimizer)
+    # empty doc
+    nlp("")
+    # single doc with zero suggestions
+    nlp("one")
+    # single doc with one suggestion
+    nlp("two two")
+    # batch with mixed zero/one suggestions
+    list(nlp.pipe(["one", "two two", "three three three", "", "four four four four"]))
+    # batch with no suggestions
+    list(nlp.pipe(["", "one", "three three three"]))
 
 
 def test_set_candidates():

spacy/tests/pipeline/test_textcat.py

@@ -895,3 +895,26 @@ def test_textcat_multi_threshold():
 
     scores = nlp.evaluate(train_examples, scorer_cfg={"threshold": 0})
     assert scores["cats_f_per_type"]["POSITIVE"]["r"] == 1.0
+
+
+@pytest.mark.parametrize(
+    "component_name,scorer",
+    [
+        ("textcat", "spacy.textcat_scorer.v1"),
+        ("textcat_multilabel", "spacy.textcat_multilabel_scorer.v1"),
+    ],
+)
+def test_textcat_legacy_scorers(component_name, scorer):
+    """Check that legacy scorers are registered and produce the expected score
+    keys."""
+    nlp = English()
+    nlp.add_pipe(component_name, config={"scorer": {"@scorers": scorer}})
+
+    train_examples = []
+    for text, annotations in TRAIN_DATA_SINGLE_LABEL:
+        train_examples.append(Example.from_dict(nlp.make_doc(text), annotations))
+    nlp.initialize(get_examples=lambda: train_examples)
+
+    # score the model (it's not actually trained but that doesn't matter)
+    scores = nlp.evaluate(train_examples)
+    assert 0 <= scores["cats_score"] <= 1

spacy/tests/test_cli.py

@@ -4,7 +4,9 @@ from collections import Counter
 from typing import Tuple, List, Dict, Any
 import pkg_resources
 import time
+from pathlib import Path
 
+import spacy
 import numpy
 import pytest
 import srsly
@@ -14,7 +16,7 @@ from thinc.api import Config, ConfigValidationError
 
 from spacy import about
 from spacy.cli import info
-from spacy.cli._util import is_subpath_of, load_project_config
+from spacy.cli._util import is_subpath_of, load_project_config, walk_directory
 from spacy.cli._util import parse_config_overrides, string_to_list
 from spacy.cli._util import substitute_project_variables
 from spacy.cli._util import validate_project_commands
@@ -32,6 +34,7 @@ from spacy.cli.package import _is_permitted_package_name
 from spacy.cli.project.remote_storage import RemoteStorage
 from spacy.cli.project.run import _check_requirements
 from spacy.cli.validate import get_model_pkgs
+from spacy.cli.apply import apply
 from spacy.cli.find_threshold import find_threshold
 from spacy.lang.en import English
 from spacy.lang.nl import Dutch
@@ -123,6 +126,25 @@ def test_issue7055():
     assert "model" in filled_cfg["components"]["ner"]
 
 
+@pytest.mark.issue(11235)
+def test_issue11235():
+    """
+    Test that the cli handles interpolation in the directory names correctly when loading project config.
+    """
+    lang_var = "en"
+    variables = {"lang": lang_var}
+    commands = [{"name": "x", "script": ["hello ${vars.lang}"]}]
+    directories = ["cfg", "${vars.lang}_model"]
+    project = {"commands": commands, "vars": variables, "directories": directories}
+    with make_tempdir() as d:
+        srsly.write_yaml(d / "project.yml", project)
+        cfg = load_project_config(d)
+        # Check that the directories are interpolated and created correctly
+        assert os.path.exists(d / "cfg")
+        assert os.path.exists(d / f"{lang_var}_model")
+    assert cfg["commands"][0]["script"][0] == f"hello {lang_var}"
+
+
 def test_cli_info():
     nlp = Dutch()
     nlp.add_pipe("textcat")
@@ -596,7 +618,6 @@ def test_string_to_list_intify(value):
     assert string_to_list(value, intify=True) == [1, 2, 3]
 
 
-@pytest.mark.skip(reason="Temporarily skip for dev version")
 def test_download_compatibility():
     spec = SpecifierSet("==" + about.__version__)
     spec.prereleases = False
@@ -607,7 +628,6 @@ def test_download_compatibility():
         assert get_minor_version(about.__version__) == get_minor_version(version)
 
 
-@pytest.mark.skip(reason="Temporarily skip for dev version")
 def test_validate_compatibility_table():
     spec = SpecifierSet("==" + about.__version__)
     spec.prereleases = False
@@ -866,6 +886,82 @@ def test_span_length_freq_dist_output_must_be_correct():
     assert list(span_freqs.keys()) == [3, 1, 4, 5, 2]
 
 
+def test_applycli_empty_dir():
+    with make_tempdir() as data_path:
+        output = data_path / "test.spacy"
+        apply(data_path, output, "blank:en", "text", 1, 1)
+
+
+def test_applycli_docbin():
+    with make_tempdir() as data_path:
+        output = data_path / "testout.spacy"
+        nlp = spacy.blank("en")
+        doc = nlp("testing apply cli.")
+        # test empty DocBin case
+        docbin = DocBin()
+        docbin.to_disk(data_path / "testin.spacy")
+        apply(data_path, output, "blank:en", "text", 1, 1)
+        docbin.add(doc)
+        docbin.to_disk(data_path / "testin.spacy")
+        apply(data_path, output, "blank:en", "text", 1, 1)
+
+
+def test_applycli_jsonl():
+    with make_tempdir() as data_path:
+        output = data_path / "testout.spacy"
+        data = [{"field": "Testing apply cli.", "key": 234}]
+        data2 = [{"field": "234"}]
+        srsly.write_jsonl(data_path / "test.jsonl", data)
+        apply(data_path, output, "blank:en", "field", 1, 1)
+        srsly.write_jsonl(data_path / "test2.jsonl", data2)
+        apply(data_path, output, "blank:en", "field", 1, 1)
+
+
+def test_applycli_txt():
+    with make_tempdir() as data_path:
+        output = data_path / "testout.spacy"
+        with open(data_path / "test.foo", "w") as ftest:
+            ftest.write("Testing apply cli.")
+        apply(data_path, output, "blank:en", "text", 1, 1)
+
+
+def test_applycli_mixed():
+    with make_tempdir() as data_path:
+        output = data_path / "testout.spacy"
+        text = "Testing apply cli"
+        nlp = spacy.blank("en")
+        doc = nlp(text)
+        jsonl_data = [{"text": text}]
+        srsly.write_jsonl(data_path / "test.jsonl", jsonl_data)
+        docbin = DocBin()
+        docbin.add(doc)
+        docbin.to_disk(data_path / "testin.spacy")
+        with open(data_path / "test.txt", "w") as ftest:
+            ftest.write(text)
+        apply(data_path, output, "blank:en", "text", 1, 1)
+        # Check whether it worked
+        result = list(DocBin().from_disk(output).get_docs(nlp.vocab))
+        assert len(result) == 3
+        for doc in result:
+            assert doc.text == text
+
+
+def test_applycli_user_data():
+    Doc.set_extension("ext", default=0)
+    val = ("ext", 0)
+    with make_tempdir() as data_path:
+        output = data_path / "testout.spacy"
+        nlp = spacy.blank("en")
+        doc = nlp("testing apply cli.")
+        doc._.ext = val
+        docbin = DocBin(store_user_data=True)
+        docbin.add(doc)
+        docbin.to_disk(data_path / "testin.spacy")
+        apply(data_path, output, "blank:en", "", 1, 1)
+        result = list(DocBin().from_disk(output).get_docs(nlp.vocab))
+        assert result[0]._.ext == val
+
+
 def test_local_remote_storage():
     with make_tempdir() as d:
         filename = "a.txt"
@@ -1088,3 +1184,26 @@ def test_upload_download_local_file():
         download_file(remote_file, local_file)
         with local_file.open(mode="r") as file_:
             assert file_.read() == content
+
+
+def test_walk_directory():
+    with make_tempdir() as d:
+        files = [
+            "data1.iob",
+            "data2.iob",
+            "data3.json",
+            "data4.conll",
+            "data5.conll",
+            "data6.conll",
+            "data7.txt",
+        ]
+
+        for f in files:
+            Path(d / f).touch()
+
+        assert (len(walk_directory(d))) == 7
+        assert (len(walk_directory(d, suffix=None))) == 7
+        assert (len(walk_directory(d, suffix="json"))) == 1
+        assert (len(walk_directory(d, suffix="iob"))) == 2
+        assert (len(walk_directory(d, suffix="conll"))) == 3
+        assert (len(walk_directory(d, suffix="pdf"))) == 0

spacy/tests/test_cli_app.py

@@ -0,0 +1,42 @@
+import os
+from pathlib import Path
+from typer.testing import CliRunner
+
+from spacy.cli._util import app
+from .util import make_tempdir
+
+
+def test_convert_auto():
+    with make_tempdir() as d_in, make_tempdir() as d_out:
+        for f in ["data1.iob", "data2.iob", "data3.iob"]:
+            Path(d_in / f).touch()
+
+        # ensure that "automatic" suffix detection works
+        result = CliRunner().invoke(app, ["convert", str(d_in), str(d_out)])
+        assert "Generated output file" in result.stdout
+        out_files = os.listdir(d_out)
+        assert len(out_files) == 3
+        assert "data1.spacy" in out_files
+        assert "data2.spacy" in out_files
+        assert "data3.spacy" in out_files
+
+
+def test_convert_auto_conflict():
+    with make_tempdir() as d_in, make_tempdir() as d_out:
+        for f in ["data1.iob", "data2.iob", "data3.json"]:
+            Path(d_in / f).touch()
+
+        # ensure that "automatic" suffix detection warns when there are different file types
+        result = CliRunner().invoke(app, ["convert", str(d_in), str(d_out)])
+        assert "All input files must be same type" in result.stdout
+        out_files = os.listdir(d_out)
+        assert len(out_files) == 0
+
+
+def test_benchmark_accuracy_alias():
+    # Verify that the `evaluate` alias works correctly.
+    result_benchmark = CliRunner().invoke(app, ["benchmark", "accuracy", "--help"])
+    result_evaluate = CliRunner().invoke(app, ["evaluate", "--help"])
+    assert result_benchmark.stdout == result_evaluate.stdout.replace(
+        "spacy evaluate", "spacy benchmark accuracy"
+    )

spacy/tests/test_language.py

@@ -3,6 +3,7 @@ import logging
 from unittest import mock
 import pytest
 from spacy.language import Language
+from spacy.scorer import Scorer
 from spacy.tokens import Doc, Span
 from spacy.vocab import Vocab
 from spacy.training import Example
@@ -126,6 +127,112 @@ def test_evaluate_no_pipe(nlp):
     nlp.evaluate([Example.from_dict(doc, annots)])
 
 
+def test_evaluate_textcat_multilabel(en_vocab):
+    """Test that evaluate works with a multilabel textcat pipe."""
+    nlp = Language(en_vocab)
+    textcat_multilabel = nlp.add_pipe("textcat_multilabel")
+    for label in ("FEATURE", "REQUEST", "BUG", "QUESTION"):
+        textcat_multilabel.add_label(label)
+    nlp.initialize()
+
+    annots = {"cats": {"FEATURE": 1.0, "QUESTION": 1.0}}
+    doc = nlp.make_doc("hello world")
+    example = Example.from_dict(doc, annots)
+    scores = nlp.evaluate([example])
+    labels = nlp.get_pipe("textcat_multilabel").labels
+    for label in labels:
+        assert scores["cats_f_per_type"].get(label) is not None
+    for key in example.reference.cats.keys():
+        if key not in labels:
+            assert scores["cats_f_per_type"].get(key) is None
+
+
+def test_evaluate_multiple_textcat_final(en_vocab):
+    """Test that evaluate evaluates the final textcat component in a pipeline
+    with more than one textcat or textcat_multilabel."""
+    nlp = Language(en_vocab)
+    textcat = nlp.add_pipe("textcat")
+    for label in ("POSITIVE", "NEGATIVE"):
+        textcat.add_label(label)
+    textcat_multilabel = nlp.add_pipe("textcat_multilabel")
+    for label in ("FEATURE", "REQUEST", "BUG", "QUESTION"):
+        textcat_multilabel.add_label(label)
+    nlp.initialize()
+
+    annots = {
+        "cats": {
+            "POSITIVE": 1.0,
+            "NEGATIVE": 0.0,
+            "FEATURE": 1.0,
+            "QUESTION": 1.0,
+            "POSITIVE": 1.0,
+            "NEGATIVE": 0.0,
+        }
+    }
+    doc = nlp.make_doc("hello world")
+    example = Example.from_dict(doc, annots)
+    scores = nlp.evaluate([example])
+    # get the labels from the final pipe
+    labels = nlp.get_pipe(nlp.pipe_names[-1]).labels
+    for label in labels:
+        assert scores["cats_f_per_type"].get(label) is not None
+    for key in example.reference.cats.keys():
+        if key not in labels:
+            assert scores["cats_f_per_type"].get(key) is None
+
+
+def test_evaluate_multiple_textcat_separate(en_vocab):
+    """Test that evaluate can evaluate multiple textcat components separately
+    with custom scorers."""
+
+    def custom_textcat_score(examples, **kwargs):
+        scores = Scorer.score_cats(
+            examples,
+            "cats",
+            multi_label=False,
+            **kwargs,
+        )
+        return {f"custom_{k}": v for k, v in scores.items()}
+
+    @spacy.registry.scorers("test_custom_textcat_scorer")
+    def make_custom_textcat_scorer():
+        return custom_textcat_score
+
+    nlp = Language(en_vocab)
+    textcat = nlp.add_pipe(
+        "textcat",
+        config={"scorer": {"@scorers": "test_custom_textcat_scorer"}},
+    )
+    for label in ("POSITIVE", "NEGATIVE"):
+        textcat.add_label(label)
+    textcat_multilabel = nlp.add_pipe("textcat_multilabel")
+    for label in ("FEATURE", "REQUEST", "BUG", "QUESTION"):
+        textcat_multilabel.add_label(label)
+    nlp.initialize()
+
+    annots = {
+        "cats": {
+            "POSITIVE": 1.0,
+            "NEGATIVE": 0.0,
+            "FEATURE": 1.0,
+            "QUESTION": 1.0,
+            "POSITIVE": 1.0,
+            "NEGATIVE": 0.0,
+        }
+    }
+    doc = nlp.make_doc("hello world")
+    example = Example.from_dict(doc, annots)
+    scores = nlp.evaluate([example])
+    # check custom scores for the textcat pipe
+    assert "custom_cats_f_per_type" in scores
+    labels = nlp.get_pipe("textcat").labels
+    assert set(scores["custom_cats_f_per_type"].keys()) == set(labels)
+    # check default scores for the textcat_multilabel pipe
+    assert "cats_f_per_type" in scores
+    labels = nlp.get_pipe("textcat_multilabel").labels
+    assert set(scores["cats_f_per_type"].keys()) == set(labels)
+
+
 def vector_modification_pipe(doc):
     doc.vector += 1
     return doc

spacy/tests/test_misc.py

@@ -8,7 +8,7 @@ from spacy import prefer_gpu, require_gpu, require_cpu
 from spacy.ml._precomputable_affine import PrecomputableAffine
 from spacy.ml._precomputable_affine import _backprop_precomputable_affine_padding
 from spacy.util import dot_to_object, SimpleFrozenList, import_file
-from spacy.util import to_ternary_int
+from spacy.util import to_ternary_int, find_available_port
 from thinc.api import Config, Optimizer, ConfigValidationError
 from thinc.api import get_current_ops, set_current_ops, NumpyOps, CupyOps, MPSOps
 from thinc.compat import has_cupy_gpu, has_torch_mps_gpu
@@ -434,3 +434,16 @@ def test_to_ternary_int():
     assert to_ternary_int(-10) == -1
     assert to_ternary_int("string") == -1
     assert to_ternary_int([0, "string"]) == -1
+
+
+def test_find_available_port():
+    host = "0.0.0.0"
+    port = 5000
+    assert find_available_port(port, host) == port, "Port 5000 isn't free"
+
+    from wsgiref.simple_server import make_server, demo_app
+
+    with make_server(host, port, demo_app) as httpd:
+        with pytest.warns(UserWarning, match="already in use"):
+            found_port = find_available_port(port, host, auto_select=True)
+        assert found_port == port + 1, "Didn't find next port"

spacy/tests/test_scorer.py

@@ -110,7 +110,7 @@ def test_tokenization(sented_doc):
     )
     example.predicted[1].is_sent_start = False
     scores = scorer.score([example])
-    assert scores["token_acc"] == approx(0.66666666)
+    assert scores["token_acc"] == 0.5
     assert scores["token_p"] == 0.5
     assert scores["token_r"] == approx(0.33333333)
     assert scores["token_f"] == 0.4

spacy/tokens/doc.pyx

@@ -359,6 +359,7 @@ cdef class Doc:
             for annot in annotations:
                 if annot:
                     if annot is heads or annot is sent_starts or annot is ent_iobs:
+                        annot = numpy.array(annot, dtype=numpy.int32).astype(numpy.uint64)
                         for i in range(len(words)):
                             if attrs.ndim == 1:
                                 attrs[i] = annot[i]
@@ -1558,6 +1559,7 @@ cdef class Doc:
 
             for j, (attr, annot) in enumerate(token_annotations.items()):
                 if attr is HEAD:
+                    annot = numpy.array(annot, dtype=numpy.int32).astype(numpy.uint64)
                     for i in range(len(words)):
                         array[i, j] = annot[i]
                 elif attr is MORPH:

spacy/tokens/span.pyi

@@ -95,8 +95,8 @@ class Span:
         self,
         start_idx: int,
         end_idx: int,
-        label: int = ...,
+        label: Union[int, str] = ...,
-        kb_id: int = ...,
+        kb_id: Union[int, str] = ...,
         vector: Optional[Floats1d] = ...,
     ) -> Span: ...
     @property

spacy/tokens/span.pyx

@@ -299,7 +299,7 @@ cdef class Span:
                     for ancestor in ancestors:
                         ancestor_i = ancestor.i - self.c.start
                         if ancestor_i in range(length):
-                            array[i, head_col] = ancestor_i - i
+                            array[i, head_col] = numpy.int32(ancestor_i - i).astype(numpy.uint64)
 
                 # if there is no appropriate ancestor, define a new artificial root
                 value = array[i, head_col]
@@ -307,7 +307,7 @@ cdef class Span:
                     new_root = old_to_new_root.get(ancestor_i, None)
                     if new_root is not None:
                         # take the same artificial root as a previous token from the same sentence
-                        array[i, head_col] = new_root - i
+                        array[i, head_col] = numpy.int32(new_root - i).astype(numpy.uint64)
                     else:
                         # set this token as the new artificial root
                         array[i, head_col] = 0

spacy/tokens/span_group.pyi

@@ -18,6 +18,7 @@ class SpanGroup:
     def doc(self) -> Doc: ...
     @property
     def has_overlap(self) -> bool: ...
+    def __iter__(self): ...
     def __len__(self) -> int: ...
     def append(self, span: Span) -> None: ...
     def extend(self, spans: Iterable[Span]) -> None: ...

spacy/tokens/span_group.pyx

@@ -158,6 +158,16 @@ cdef class SpanGroup:
             return self._concat(other)
         return NotImplemented
 
+    def __iter__(self):
+        """
+        Iterate over the spans in this SpanGroup.
+        YIELDS (Span): A span in this SpanGroup.
+
+        DOCS: https://spacy.io/api/spangroup#iter
+        """
+        for i in range(self.c.size()):
+            yield self[i]
+
     def append(self, Span span):
         """Add a span to the group. The span must refer to the same Doc
         object as the span group.

spacy/training/example.pyx

@@ -443,26 +443,27 @@ def _annot2array(vocab, tok_annot, doc_annot):
         if key not in IDS:
             raise ValueError(Errors.E974.format(obj="token", key=key))
         elif key in ["ORTH", "SPACY"]:
-            pass
+            continue
         elif key == "HEAD":
             attrs.append(key)
-            values.append([h-i if h is not None else 0 for i, h in enumerate(value)])
+            row = [h-i if h is not None else 0 for i, h in enumerate(value)]
         elif key == "DEP":
             attrs.append(key)
-            values.append([vocab.strings.add(h) if h is not None else MISSING_DEP for h in value])
+            row = [vocab.strings.add(h) if h is not None else MISSING_DEP for h in value]
         elif key == "SENT_START":
             attrs.append(key)
-            values.append([to_ternary_int(v) for v in value])
+            row = [to_ternary_int(v) for v in value]
         elif key == "MORPH":
             attrs.append(key)
-            values.append([vocab.morphology.add(v) for v in value])
+            row = [vocab.morphology.add(v) for v in value]
         else:
             attrs.append(key)
             if not all(isinstance(v, str) for v in value):
                 types = set([type(v) for v in value])
                 raise TypeError(Errors.E969.format(field=key, types=types)) from None
-            values.append([vocab.strings.add(v) for v in value])
+            row = [vocab.strings.add(v) for v in value]
-    array = numpy.asarray(values, dtype="uint64")
+        values.append([numpy.array(v, dtype=numpy.int32).astype(numpy.uint64) if v < 0 else v for v in row])
+    array = numpy.array(values, dtype=numpy.uint64)
     return attrs, array.T
 
 

spacy/training/loggers.py

@@ -26,6 +26,8 @@ def setup_table(
     return final_cols, final_widths, ["r" for _ in final_widths]
 
 
+# We cannot rename this method as it's directly imported
+# and used by external packages such as spacy-loggers.
 @registry.loggers("spacy.ConsoleLogger.v2")
 def console_logger(
     progress_bar: bool = False,
@@ -33,7 +35,27 @@ def console_logger(
     output_file: Optional[Union[str, Path]] = None,
 ):
     """The ConsoleLogger.v2 prints out training logs in the console and/or saves them to a jsonl file.
-    progress_bar (bool): Whether the logger should print the progress bar.
+    progress_bar (bool): Whether the logger should print a progress bar tracking the steps till the next evaluation pass.
+    console_output (bool): Whether the logger should print the logs on the console.
+    output_file (Optional[Union[str, Path]]): The file to save the training logs to.
+    """
+    return console_logger_v3(
+        progress_bar=None if progress_bar is False else "eval",
+        console_output=console_output,
+        output_file=output_file,
+    )
+
+
+@registry.loggers("spacy.ConsoleLogger.v3")
+def console_logger_v3(
+    progress_bar: Optional[str] = None,
+    console_output: bool = True,
+    output_file: Optional[Union[str, Path]] = None,
+):
+    """The ConsoleLogger.v3 prints out training logs in the console and/or saves them to a jsonl file.
+    progress_bar (Optional[str]): Type of progress bar to show in the console. Allowed values:
+        train - Tracks the number of steps from the beginning of training until the full training run is complete (training.max_steps is reached).
+        eval - Tracks the number of steps between the previous and next evaluation (training.eval_frequency is reached).
     console_output (bool): Whether the logger should print the logs on the console.
     output_file (Optional[Union[str, Path]]): The file to save the training logs to.
     """
@@ -70,6 +92,7 @@ def console_logger(
             for name, proc in nlp.pipeline
             if hasattr(proc, "is_trainable") and proc.is_trainable
         ]
+        max_steps = nlp.config["training"]["max_steps"]
         eval_frequency = nlp.config["training"]["eval_frequency"]
         score_weights = nlp.config["training"]["score_weights"]
         score_cols = [col for col, value in score_weights.items() if value is not None]
@@ -84,6 +107,13 @@ def console_logger(
             write(msg.row(table_header, widths=table_widths, spacing=spacing))
             write(msg.row(["-" * width for width in table_widths], spacing=spacing))
         progress = None
+        expected_progress_types = ("train", "eval")
+        if progress_bar is not None and progress_bar not in expected_progress_types:
+            raise ValueError(
+                Errors.E1048.format(
+                    unexpected=progress_bar, expected=expected_progress_types
+                )
+            )
 
         def log_step(info: Optional[Dict[str, Any]]) -> None:
             nonlocal progress
@@ -141,11 +171,23 @@ def console_logger(
                     )
                 )
                 if progress_bar:
+                    if progress_bar == "train":
+                        total = max_steps
+                        desc = f"Last Eval Epoch: {info['epoch']}"
+                        initial = info["step"]
+                    else:
+                        total = eval_frequency
+                        desc = f"Epoch {info['epoch']+1}"
+                        initial = 0
                     # Set disable=None, so that it disables on non-TTY
                     progress = tqdm.tqdm(
-                        total=eval_frequency, disable=None, leave=False, file=stderr
+                        total=total,
+                        disable=None,
+                        leave=False,
+                        file=stderr,
+                        initial=initial,
                     )
-                    progress.set_description(f"Epoch {info['epoch']+1}")
+                    progress.set_description(desc)
 
         def finalize() -> None:
             if output_stream:

spacy/util.py

@@ -31,6 +31,7 @@ import shlex
 import inspect
 import pkgutil
 import logging
+import socket
 
 try:
     import cupy.random
@@ -1643,7 +1644,9 @@ def _pipe(
     docs: Iterable["Doc"],
     proc: "PipeCallable",
     name: str,
-    default_error_handler: Callable[[str, "PipeCallable", List["Doc"], Exception], NoReturn],
+    default_error_handler: Callable[
+        [str, "PipeCallable", List["Doc"], Exception], NoReturn
+    ],
     kwargs: Mapping[str, Any],
 ) -> Iterator["Doc"]:
     if hasattr(proc, "pipe"):
@@ -1734,3 +1737,50 @@ def all_equal(iterable):
     (or if the input is an empty sequence), False otherwise."""
     g = itertools.groupby(iterable)
     return next(g, True) and not next(g, False)
+
+
+def _is_port_in_use(port: int, host: str = "localhost") -> bool:
+    """Check if 'host:port' is in use. Return True if it is, False otherwise.
+
+    port (int): the port to check
+    host (str): the host to check (default "localhost")
+    RETURNS (bool): Whether 'host:port' is in use.
+    """
+    s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+    try:
+        s.bind((host, port))
+        return False
+    except socket.error:
+        return True
+    finally:
+        s.close()
+
+
+def find_available_port(start: int, host: str, auto_select: bool = False) -> int:
+    """Given a starting port and a host, handle finding a port.
+
+    If `auto_select` is False, a busy port will raise an error.
+
+    If `auto_select` is True, the next free higher port will be used.
+
+    start (int): the port to start looking from
+    host (str): the host to find a port on
+    auto_select (bool): whether to automatically select a new port if the given port is busy (default False)
+    RETURNS (int): The port to use.
+    """
+    if not _is_port_in_use(start, host):
+        return start
+
+    port = start
+    if not auto_select:
+        raise ValueError(Errors.E1050.format(port=port))
+
+    while _is_port_in_use(port, host) and port < 65535:
+        port += 1
+
+    if port == 65535 and _is_port_in_use(port, host):
+        raise ValueError(Errors.E1049.format(host=host))
+
+    # if we get here, the port changed
+    warnings.warn(Warnings.W124.format(host=host, port=start, serve_port=port))
+    return port

website/.dockerignore

@@ -0,0 +1,9 @@
+.cache/
+.next/
+public/
+node_modules
+.npm
+logs
+*.log
+npm-debug.log*
+quickstart-training-generator.js

website/.eslintrc.json

@@ -0,0 +1,3 @@
+{
+    "extends": "next/core-web-vitals"
+}

website/.gitignore

@@ -0,0 +1,46 @@
+# See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
+
+quickstart-training-generator.js
+
+# dependencies
+/node_modules
+/.pnp
+.pnp.js
+
+# testing
+/coverage
+
+# next.js
+/.next/
+/out/
+
+# production
+/build
+
+# misc
+.DS_Store
+*.pem
+
+# debug
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+.pnpm-debug.log*
+
+# local env files
+.env*.local
+
+# vercel
+.vercel
+
+# typescript
+*.tsbuildinfo
+next-env.d.ts
+
+!.vscode/extensions.json
+!public
+
+public/robots.txt
+public/sitemap*
+public/sw.js*
+public/workbox*

website/.nvmrc

@@ -0,0 +1 @@
+18

website/.prettierignore

@@ -0,0 +1 @@
+.next

website/.prettierrc

@@ -20,12 +20,11 @@
             }
         },
         {
-            "files": "*.md",
+            "files": ["package.json", "package-lock.json"],
             "options": {
                 "tabWidth": 2,
                 "printWidth": 80,
-                "proseWrap": "always",
+                "proseWrap": "always"
-                "htmlWhitespaceSensitivity": "strict"
             }
         },
         {

website/.vscode/extensions.json

@@ -0,0 +1,8 @@
+{
+    "recommendations": [
+        "dbaeumer.vscode-eslint",
+        "unifiedjs.vscode-mdx",
+        "esbenp.prettier-vscode",
+        "syler.sass-indented"
+    ]
+}

website/Dockerfile

@@ -1,16 +1,14 @@
-FROM node:11.15.0 
+FROM node:18
 
-WORKDIR /spacy-io
+USER node
-
-RUN npm install -g gatsby-cli@2.7.4
-
-COPY package.json .
-COPY package-lock.json . 
-
-RUN npm install
 
 # This is so the installed node_modules will be up one directory
 # from where a user mounts files, so that they don't accidentally mount
 # their own node_modules from a different build
 # https://nodejs.org/api/modules.html#modules_loading_from_node_modules_folders
-WORKDIR /spacy-io/website/
+WORKDIR /home/node
+COPY --chown=node package.json .
+COPY --chown=node package-lock.json .
+RUN npm install
+
+WORKDIR /home/node/website/

website/README.md

@@ -7,17 +7,16 @@ The styleguide for the spaCy website is available at
 
 ## Setup and installation
 
-Before running the setup, make sure your versions of
-[Node](https://nodejs.org/en/) and [npm](https://www.npmjs.com/) are up to date.
-Node v10.15 or later is required.
-
 ```bash
 # Clone the repository
 git clone https://github.com/explosion/spaCy
 cd spaCy/website
 
-# Install Gatsby's command-line tool
+# Switch to the correct Node version
-npm install --global gatsby-cli
+#
+# If you don't have NVM and don't want to use it, you can manually switch to the Node version
+# stated in /.nvmrc and skip this step
+nvm use
 
 # Install the dependencies
 npm install
@@ -36,52 +35,47 @@ file in the root defines the settings used in this codebase.
 
 ## Building & developing the site with Docker
 
-Sometimes it's hard to get a local environment working due to rapid updates to
+While it shouldn't be necessary and is not recommended you can run this site in a Docker container.
-node dependencies, so it may be easier to use docker for building the docs.
 
 If you'd like to do this, **be sure you do _not_ include your local
 `node_modules` folder**, since there are some dependencies that need to be built
 for the image system. Rename it before using.
 
-```bash
+First build the Docker image. This only needs to be done on the first run
-docker run -it \
+or when changes are made to `Dockerfile` or the website dependencies:
-  -v $(pwd):/spacy-io/website \
-  -p 8000:8000 \
-  ghcr.io/explosion/spacy-io \
-  gatsby develop -H 0.0.0.0
-```
-
-This will allow you to access the built website at http://0.0.0.0:8000/ in your
-browser, and still edit code in your editor while having the site reflect those
-changes.
-
-**Note**: If you're working on a Mac with an M1 processor, you might see
-segfault errors from `qemu` if you use the default image. To fix this use the
-`arm64` tagged image in the `docker run` command
-(ghcr.io/explosion/spacy-io:arm64).
-
-### Building the Docker image
-
-If you'd like to build the image locally, you can do so like this:
 
 ```bash
 docker build -t spacy-io .
 ```
 
-This will take some time, so if you want to use the prebuilt image you'll save a
+You can then build and run the website with:
-bit of time.
+
+```bash
+docker run -it \
+  --rm \
+  -v $(pwd):/home/node/website \
+  -p 3000:3000 \
+  spacy-io \
+  npm run dev -- -H 0.0.0.0
+```
+
+This will allow you to access the built website at http://0.0.0.0:3000/ in your
+browser, and still edit code in your editor while having the site reflect those
+changes.
 
 ## Project structure
 
 ```yaml
 ├── docs                 # the actual markdown content
 ├── meta                 # JSON-formatted site metadata
+|   ├── dynamicMeta.js   # At build time generated meta data
 |   ├── languages.json   # supported languages and statistical models
 |   ├── sidebars.json    # sidebar navigations for different sections
 |   ├── site.json        # general site metadata
 |   ├── type-annotations.json # Type annotations
 |   └── universe.json    # data for the spaCy universe section
-├── public               # compiled site
+├── pages                # Next router pages
+├── public               # static images and other assets
 ├── setup                # Jinja setup
 ├── src                  # source
 |   ├── components       # React components
@@ -96,9 +90,11 @@ bit of time.
 |   |   └── universe.js  # layout templates for universe
 |   └── widgets          # non-reusable components with content, e.g. changelog
 ├── .eslintrc.json       # ESLint config file
+├── .nvmrc               # NVM config file
+|                        # (to support "nvm use" to switch to correct Node version)
+|
 ├── .prettierrc          # Prettier config file
-├── gatsby-browser.js    # browser-specific hooks for Gatsby
+├── next.config.mjs      # Next config file
-├── gatsby-config.js     # Gatsby configuration
+├── package.json         # package settings and dependencies
-├── gatsby-node.js       # Node-specific hooks for Gatsby
+└── tsconfig.json        # TypeScript config file
-└── package.json         # package settings and dependencies
 ```

website/UNIVERSE.md

@@ -2,9 +2,10 @@
 
 # spaCy Universe
 
-The [spaCy Universe](https://spacy.io/universe) collects the many great resources developed with or for spaCy. It
+The [spaCy Universe](https://spacy.io/universe) collects the many great
-includes standalone packages, plugins, extensions, educational materials,
+resources developed with or for spaCy. It includes standalone packages, plugins,
-operational utilities and bindings for other languages.
+extensions, educational materials, operational utilities and bindings for other
+languages.
 
 If you have a project that you want the spaCy community to make use of, you can
 suggest it by submitting a pull request to this repository. The Universe
@@ -18,26 +19,35 @@ discussion forum.
 
 ### Projects
 
-✅ Libraries and packages should be **open-source** (with a user-friendly license) and at least somewhat **documented** (e.g. a simple `README` with usage instructions).
+✅ Libraries and packages should be **open-source** (with a user-friendly
+license) and at least somewhat **documented** (e.g. a simple `README` with usage
+instructions).
 
-✅ We're happy to include work in progress and prereleases, but we'd like to keep the emphasis on projects that should be useful to the community **right away**.
+✅ We're happy to include work in progress and prereleases, but we'd like to
+keep the emphasis on projects that should be useful to the community **right
+away**.
 
 ✅ Demos and visualizers should be available via a **public URL**.
 
 ### Educational Materials
 
-✅ Books should be **available for purchase or download** (not just pre-order). Ebooks and self-published books are fine, too, if they include enough substantial content.
+✅ Books should be **available for purchase or download** (not just pre-order).
+Ebooks and self-published books are fine, too, if they include enough
+substantial content.
 
-✅ The `"url"` of book entries should either point to the publisher's website or a reseller of your choice (ideally one that ships worldwide or as close as possible).
+✅ The `"url"` of book entries should either point to the publisher's website or
+a reseller of your choice (ideally one that ships worldwide or as close as
+possible).
 
-✅ If an online course is only available behind a paywall, it should at least have a **free excerpt** or chapter available, so users know what to expect.
+✅ If an online course is only available behind a paywall, it should at least
+have a **free excerpt** or chapter available, so users know what to expect.
 
 ## JSON format
 
-To add a project, fork this repository, edit the [`universe.json`](meta/universe.json)
+To add a project, fork this repository, edit the
-and add an object of the following format to the list of `"resources"`. Before
+[`universe.json`](meta/universe.json) and add an object of the following format
-you submit your pull request, make sure to use a linter to verify that your
+to the list of `"resources"`. Before you submit your pull request, make sure to
-markup is correct.
+use a linter to verify that your markup is correct.
 
 ```json
 {
@@ -70,7 +80,7 @@ markup is correct.
 ```
 
 | Field           | Type   | Description                                                                                                                             |
-| --- | --- | --- |
+| --------------- | ------ | --------------------------------------------------------------------------------------------------------------------------------------- |
 | `id`            | string | Unique ID of the project.                                                                                                               |
 | `title`         | string | Project title. If not set, the `id` will be used as the display title.                                                                  |
 | `slogan`        | string | A short description of the project. Displayed in the overview and under the title.                                                      |
@@ -89,6 +99,6 @@ markup is correct.
 | `tags`          | list   | Still experimental and not used for filtering: one or more tags to assign to project.                                                   |
 
 To separate them from the projects, educational materials also specify
-`"type": "education`. Books can also set a `"cover"` field containing a URL
+`"type": "education`. Books can also set a `"cover"` field containing a URL to a
-to a cover image. If available, it's used in the overview and displayed on
+cover image. If available, it's used in the overview and displayed on the
-the individual book page.
+individual book page.

website/docs/api/architectures.mdx

@@ -26,9 +26,9 @@ part of the [training config](/usage/training#custom-functions). Also see the
 usage documentation on
 [layers and model architectures](/usage/layers-architectures).
 
-## Tok2Vec architectures {#tok2vec-arch source="spacy/ml/models/tok2vec.py"}
+## Tok2Vec architectures {id="tok2vec-arch",source="spacy/ml/models/tok2vec.py"}
 
-### spacy.Tok2Vec.v2 {#Tok2Vec}
+### spacy.Tok2Vec.v2 {id="Tok2Vec"}
 
 > #### Example config
 >
@@ -56,7 +56,7 @@ blog post for background.
 | `encode`    | Encode context into the embeddings, using an architecture such as a CNN, BiLSTM or transformer. For example, [MaxoutWindowEncoder](/api/architectures#MaxoutWindowEncoder). ~~Model[List[Floats2d], List[Floats2d]]~~            |
 | **CREATES** | The model using the architecture. ~~Model[List[Doc], List[Floats2d]]~~                                                                                                                                                           |
 
-### spacy.HashEmbedCNN.v2 {#HashEmbedCNN}
+### spacy.HashEmbedCNN.v2 {id="HashEmbedCNN"}
 
 > #### Example Config
 >
@@ -89,7 +89,7 @@ consisting of a CNN and a layer-normalized maxout activation function.
 | `pretrained_vectors` | Whether to also use static vectors. ~~bool~~                                                                                                                                                                                                                                  |
 | **CREATES**          | The model using the architecture. ~~Model[List[Doc], List[Floats2d]]~~                                                                                                                                                                                                        |
 
-### spacy.Tok2VecListener.v1 {#Tok2VecListener}
+### spacy.Tok2VecListener.v1 {id="Tok2VecListener"}
 
 > #### Example config
 >
@@ -139,7 +139,7 @@ the `Tok2Vec` component.
 | `upstream`  | A string to identify the "upstream" `Tok2Vec` component to communicate with. By default, the upstream name is the wildcard string `"*"`, but you could also specify the name of the `Tok2Vec` component. You'll almost never have multiple upstream `Tok2Vec` components, so the wildcard string will almost always be fine. ~~str~~ |
 | **CREATES** | The model using the architecture. ~~Model[List[Doc], List[Floats2d]]~~                                                                                                                                                                                                                                                               |
 
-### spacy.MultiHashEmbed.v2 {#MultiHashEmbed}
+### spacy.MultiHashEmbed.v2 {id="MultiHashEmbed"}
 
 > #### Example config
 >
@@ -170,7 +170,7 @@ updated).
 | `include_static_vectors` | Whether to also use static word vectors. Requires a vectors table to be loaded in the [`Doc`](/api/doc) objects' vocab. ~~bool~~                                                                                                                                                                                                                                                                                                                   |
 | **CREATES**              | The model using the architecture. ~~Model[List[Doc], List[Floats2d]]~~                                                                                                                                                                                                                                                                                                                                                                             |
 
-### spacy.CharacterEmbed.v2 {#CharacterEmbed}
+### spacy.CharacterEmbed.v2 {id="CharacterEmbed"}
 
 > #### Example config
 >
@@ -207,7 +207,7 @@ network to construct a single vector to represent the information.
 | `nC`        | The number of UTF-8 bytes to embed per word. Recommended values are between `3` and `8`, although it may depend on the length of words in the language. ~~int~~ |
 | **CREATES** | The model using the architecture. ~~Model[List[Doc], List[Floats2d]]~~                                                                                          |
 
-### spacy.MaxoutWindowEncoder.v2 {#MaxoutWindowEncoder}
+### spacy.MaxoutWindowEncoder.v2 {id="MaxoutWindowEncoder"}
 
 > #### Example config
 >
@@ -231,7 +231,7 @@ and residual connections.
 | `depth`         | The number of convolutional layers. Recommended value is `4`. ~~int~~                                                                                                                                          |
 | **CREATES**     | The model using the architecture. ~~Model[List[Floats2d], List[Floats2d]]~~                                                                                                                                    |
 
-### spacy.MishWindowEncoder.v2 {#MishWindowEncoder}
+### spacy.MishWindowEncoder.v2 {id="MishWindowEncoder"}
 
 > #### Example config
 >
@@ -254,7 +254,7 @@ and residual connections.
 | `depth`       | The number of convolutional layers. Recommended value is `4`. ~~int~~                                                                                                                                          |
 | **CREATES**   | The model using the architecture. ~~Model[List[Floats2d], List[Floats2d]]~~                                                                                                                                    |
 
-### spacy.TorchBiLSTMEncoder.v1 {#TorchBiLSTMEncoder}
+### spacy.TorchBiLSTMEncoder.v1 {id="TorchBiLSTMEncoder"}
 
 > #### Example config
 >
@@ -276,7 +276,7 @@ Encode context using bidirectional LSTM layers. Requires
 | `dropout`   | Creates a Dropout layer on the outputs of each LSTM layer except the last layer. Set to 0.0 to disable this functionality. ~~float~~                                                                           |
 | **CREATES** | The model using the architecture. ~~Model[List[Floats2d], List[Floats2d]]~~                                                                                                                                    |
 
-### spacy.StaticVectors.v2 {#StaticVectors}
+### spacy.StaticVectors.v2 {id="StaticVectors"}
 
 > #### Example config
 >
@@ -306,7 +306,7 @@ mapped to a zero vector. See the documentation on
 | `key_attr`  | Defaults to `"ORTH"`. ~~str~~                                                                                                                                                                                           |
 | **CREATES** | The model using the architecture. ~~Model[List[Doc], Ragged]~~                                                                                                                                                          |
 
-### spacy.FeatureExtractor.v1 {#FeatureExtractor}
+### spacy.FeatureExtractor.v1 {id="FeatureExtractor"}
 
 > #### Example config
 >
@@ -324,7 +324,7 @@ of feature names to extract, which should refer to token attributes.
 | `columns`   | The token attributes to extract. ~~List[Union[int, str]]~~               |
 | **CREATES** | The created feature extraction layer. ~~Model[List[Doc], List[Ints2d]]~~ |
 
-## Transformer architectures {#transformers source="github.com/explosion/spacy-transformers/blob/master/spacy_transformers/architectures.py"}
+## Transformer architectures {id="transformers",source="github.com/explosion/spacy-transformers/blob/master/spacy_transformers/architectures.py"}
 
 The following architectures are provided by the package
 [`spacy-transformers`](https://github.com/explosion/spacy-transformers). See the
@@ -341,7 +341,7 @@ for details and system requirements.
 
 </Infobox>
 
-### spacy-transformers.TransformerModel.v3 {#TransformerModel}
+### spacy-transformers.TransformerModel.v3 {id="TransformerModel"}
 
 > #### Example Config
 >
@@ -404,7 +404,7 @@ The other arguments are shared between all versions.
 
 </Accordion>
 
-### spacy-transformers.TransformerListener.v1 {#TransformerListener}
+### spacy-transformers.TransformerListener.v1 {id="TransformerListener"}
 
 > #### Example Config
 >
@@ -434,7 +434,7 @@ a single token vector given zero or more wordpiece vectors.
 | `upstream`    | A string to identify the "upstream" `Transformer` component to communicate with. By default, the upstream name is the wildcard string `"*"`, but you could also specify the name of the `Transformer` component. You'll almost never have multiple upstream `Transformer` components, so the wildcard string will almost always be fine. ~~str~~ |
 | **CREATES**   | The model using the architecture. ~~Model[List[Doc], List[Floats2d]]~~                                                                                                                                                                                                                                                                           |
 
-### spacy-transformers.Tok2VecTransformer.v3 {#Tok2VecTransformer}
+### spacy-transformers.Tok2VecTransformer.v3 {id="Tok2VecTransformer"}
 
 > #### Example Config
 >
@@ -481,7 +481,7 @@ The other arguments are shared between all versions.
 
 </Accordion>
 
-## Pretraining architectures {#pretrain source="spacy/ml/models/multi_task.py"}
+## Pretraining architectures {id="pretrain",source="spacy/ml/models/multi_task.py"}
 
 The spacy `pretrain` command lets you initialize a `Tok2Vec` layer in your
 pipeline with information from raw text. To this end, additional layers are
@@ -494,7 +494,7 @@ BERT.
 For more information, see the section on
 [pretraining](/usage/embeddings-transformers#pretraining).
 
-### spacy.PretrainVectors.v1 {#pretrain_vectors}
+### spacy.PretrainVectors.v1 {id="pretrain_vectors"}
 
 > #### Example config
 >
@@ -525,7 +525,7 @@ vectors.
 | `loss`          | The loss function can be either "cosine" or "L2". We typically recommend to use "cosine". ~~~str~~                                                        |
 | **CREATES**     | A callable function that can create the Model, given the `vocab` of the pipeline and the `tok2vec` layer to pretrain. ~~Callable[[Vocab, Model], Model]~~ |
 
-### spacy.PretrainCharacters.v1 {#pretrain_chars}
+### spacy.PretrainCharacters.v1 {id="pretrain_chars"}
 
 > #### Example config
 >
@@ -551,9 +551,9 @@ for a Tok2Vec layer.
 | `n_characters`  | The window of characters - e.g. if `n_characters = 2`, the model will try to predict the first two and last two characters of the word. ~~int~~           |
 | **CREATES**     | A callable function that can create the Model, given the `vocab` of the pipeline and the `tok2vec` layer to pretrain. ~~Callable[[Vocab, Model], Model]~~ |
 
-## Parser & NER architectures {#parser}
+## Parser & NER architectures {id="parser"}
 
-### spacy.TransitionBasedParser.v2 {#TransitionBasedParser source="spacy/ml/models/parser.py"}
+### spacy.TransitionBasedParser.v2 {id="TransitionBasedParser",source="spacy/ml/models/parser.py"}
 
 > #### Example Config
 >
@@ -612,9 +612,9 @@ same signature, but the `use_upper` argument was `True` by default.
 
 </Accordion>
 
-## Tagging architectures {#tagger source="spacy/ml/models/tagger.py"}
+## Tagging architectures {id="tagger",source="spacy/ml/models/tagger.py"}
 
-### spacy.Tagger.v2 {#Tagger}
+### spacy.Tagger.v2 {id="Tagger"}
 
 > #### Example Config
 >
@@ -648,7 +648,7 @@ The other arguments are shared between all versions.
 
 </Accordion>
 
-## Text classification architectures {#textcat source="spacy/ml/models/textcat.py"}
+## Text classification architectures {id="textcat",source="spacy/ml/models/textcat.py"}
 
 A text classification architecture needs to take a [`Doc`](/api/doc) as input,
 and produce a score for each potential label class. Textcat challenges can be
@@ -672,7 +672,7 @@ single-label use-cases where `exclusive_classes = true`, while the
 
 </Infobox>
 
-### spacy.TextCatEnsemble.v2 {#TextCatEnsemble}
+### spacy.TextCatEnsemble.v2 {id="TextCatEnsemble"}
 
 > #### Example Config
 >
@@ -737,7 +737,7 @@ but used an internal `tok2vec` instead of taking it as argument:
 
 </Accordion>
 
-### spacy.TextCatCNN.v2 {#TextCatCNN}
+### spacy.TextCatCNN.v2 {id="TextCatCNN"}
 
 > #### Example Config
 >
@@ -777,7 +777,7 @@ after training.
 
 </Accordion>
 
-### spacy.TextCatBOW.v2 {#TextCatBOW}
+### spacy.TextCatBOW.v2 {id="TextCatBOW"}
 
 > #### Example Config
 >
@@ -809,9 +809,9 @@ after training.
 
 </Accordion>
 
-## Span classification architectures {#spancat source="spacy/ml/models/spancat.py"}
+## Span classification architectures {id="spancat",source="spacy/ml/models/spancat.py"}
 
-### spacy.SpanCategorizer.v1 {#SpanCategorizer}
+### spacy.SpanCategorizer.v1 {id="SpanCategorizer"}
 
 > #### Example Config
 >
@@ -848,7 +848,7 @@ single vector, and a scorer model to map the vectors to probabilities.
 | `scorer`    | The scorer model. ~~Model[Floats2d, Floats2d]~~                                 |
 | **CREATES** | The model using the architecture. ~~Model[Tuple[List[Doc], Ragged], Floats2d]~~ |
 
-### spacy.mean_max_reducer.v1 {#mean_max_reducer}
+### spacy.mean_max_reducer.v1 {id="mean_max_reducer"}
 
 Reduce sequences by concatenating their mean and max pooled vectors, and then
 combine the concatenated vectors with a hidden layer.
@@ -857,7 +857,7 @@ combine the concatenated vectors with a hidden layer.
 | ------------- | ------------------------------------- |
 | `hidden_size` | The size of the hidden layer. ~~int~~ |
 
-## Entity linking architectures {#entitylinker source="spacy/ml/models/entity_linker.py"}
+## Entity linking architectures {id="entitylinker",source="spacy/ml/models/entity_linker.py"}
 
 An [`EntityLinker`](/api/entitylinker) component disambiguates textual mentions
 (tagged as named entities) to unique identifiers, grounding the named entities
@@ -870,7 +870,7 @@ into the "real world". This requires 3 main components:
 - A machine learning [`Model`](https://thinc.ai/docs/api-model) that picks the
   most plausible ID from the set of candidates.
 
-### spacy.EntityLinker.v2 {#EntityLinker}
+### spacy.EntityLinker.v2 {id="EntityLinker"}
 
 > #### Example Config
 >
@@ -899,7 +899,7 @@ The `EntityLinker` model architecture is a Thinc `Model` with a
 | `nO`        | Output dimension, determined by the length of the vectors encoding each entity in the KB. If the `nO` dimension is not set, the entity linking component will set it when `initialize` is called. ~~Optional[int]~~ |
 | **CREATES** | The model using the architecture. ~~Model[List[Doc], Floats2d]~~                                                                                                                                                    |
 
-### spacy.EmptyKB.v1 {#EmptyKB}
+### spacy.EmptyKB.v1 {id="EmptyKB"}
 
 A function that creates an empty `KnowledgeBase` from a [`Vocab`](/api/vocab)
 instance. This is the default when a new entity linker component is created.
@@ -908,7 +908,7 @@ instance. This is the default when a new entity linker component is created.
 | ---------------------- | ----------------------------------------------------------------------------------- |
 | `entity_vector_length` | The length of the vectors encoding each entity in the KB. Defaults to `64`. ~~int~~ |
 
-### spacy.KBFromFile.v1 {#KBFromFile}
+### spacy.KBFromFile.v1 {id="KBFromFile"}
 
 A function that reads an existing `KnowledgeBase` from file.
 
@@ -916,7 +916,7 @@ A function that reads an existing `KnowledgeBase` from file.
 | --------- | -------------------------------------------------------- |
 | `kb_path` | The location of the KB that was stored to file. ~~Path~~ |
 
-### spacy.CandidateGenerator.v1 {#CandidateGenerator}
+### spacy.CandidateGenerator.v1 {id="CandidateGenerator"}
 
 A function that takes as input a [`KnowledgeBase`](/api/kb) and a
 [`Span`](/api/span) object denoting a named entity, and returns a list of
@@ -924,7 +924,7 @@ plausible [`Candidate`](/api/kb/#candidate) objects. The default
 `CandidateGenerator` uses the text of a mention to find its potential aliases in
 the `KnowledgeBase`. Note that this function is case-dependent.
 
-## Coreference {#coref-architectures tag="experimental"}
+## Coreference {id="coref-architectures",tag="experimental"}
 
 A [`CoreferenceResolver`](/api/coref) component identifies tokens that refer to
 the same entity. A [`SpanResolver`](/api/span-resolver) component infers spans
@@ -932,7 +932,7 @@ from single tokens. Together these components can be used to reproduce
 traditional coreference models. You can also omit the `SpanResolver` if working
 with only token-level clusters is acceptable.
 
-### spacy-experimental.Coref.v1 {#Coref tag="experimental"}
+### spacy-experimental.Coref.v1 {id="Coref",tag="experimental"}
 
 > #### Example Config
 >
@@ -967,7 +967,7 @@ The `Coref` model architecture is a Thinc `Model`.
 | `antecedent_batch_size`   | Internal batch size. ~~int~~                                                                                                                                                             |
 | **CREATES**               | The model using the architecture. ~~Model[List[Doc], Floats2d]~~                                                                                                                         |
 
-### spacy-experimental.SpanResolver.v1 {#SpanResolver tag="experimental"}
+### spacy-experimental.SpanResolver.v1 {id="SpanResolver",tag="experimental"}
 
 > #### Example Config
 >

website/docs/api/attributeruler.mdx

@@ -2,7 +2,7 @@
 title: AttributeRuler
 tag: class
 source: spacy/pipeline/attributeruler.py
-new: 3
+version: 3
 teaser: 'Pipeline component for rule-based token attribute assignment'
 api_string_name: attribute_ruler
 api_trainable: false
@@ -15,7 +15,7 @@ between attributes such as mapping fine-grained POS tags to coarse-grained POS
 tags. See the [usage guide](/usage/linguistic-features/#mappings-exceptions) for
 examples.
 
-## Config and implementation {#config}
+## Config and implementation {id="config"}
 
 The default config is defined by the pipeline component factory and describes
 how the component should be configured. You can override its settings via the
@@ -37,7 +37,7 @@ how the component should be configured. You can override its settings via the
 %%GITHUB_SPACY/spacy/pipeline/attributeruler.py
 ```
 
-## AttributeRuler.\_\_init\_\_ {#init tag="method"}
+## AttributeRuler.\_\_init\_\_ {id="init",tag="method"}
 
 Initialize the attribute ruler.
 
@@ -56,7 +56,7 @@ Initialize the attribute ruler.
 | `validate`     | Whether patterns should be validated (passed to the [`Matcher`](/api/matcher#init)). Defaults to `False`. ~~bool~~                                                                                                                                                                         |
 | `scorer`       | The scoring method. Defaults to [`Scorer.score_token_attr`](/api/scorer#score_token_attr) for the attributes `"tag`", `"pos"`, `"morph"` and `"lemma"` and [`Scorer.score_token_attr_per_feat`](/api/scorer#score_token_attr_per_feat) for the attribute `"morph"`. ~~Optional[Callable]~~ |
 
-## AttributeRuler.\_\_call\_\_ {#call tag="method"}
+## AttributeRuler.\_\_call\_\_ {id="call",tag="method"}
 
 Apply the attribute ruler to a `Doc`, setting token attributes for tokens
 matched by the provided patterns.
@@ -66,7 +66,7 @@ matched by the provided patterns.
 | `doc`       | The document to process. ~~Doc~~ |
 | **RETURNS** | The processed document. ~~Doc~~  |
 
-## AttributeRuler.add {#add tag="method"}
+## AttributeRuler.add {id="add",tag="method"}
 
 Add patterns to the attribute ruler. The patterns are a list of `Matcher`
 patterns and the attributes are a dict of attributes to set on the matched
@@ -89,7 +89,7 @@ may be negative to index from the end of the span.
 | `attrs`    | The attributes to assign to the target token in the matched span. ~~Dict[str, Any]~~                                              |
 | `index`    | The index of the token in the matched span to modify. May be negative to index from the end of the span. Defaults to `0`. ~~int~~ |
 
-## AttributeRuler.add_patterns {#add_patterns tag="method"}
+## AttributeRuler.add_patterns {id="add_patterns",tag="method"}
 
 > #### Example
 >
@@ -116,7 +116,7 @@ keys `"patterns"`, `"attrs"` and `"index"`, which match the arguments of
 | ---------- | -------------------------------------------------------------------------- |
 | `patterns` | The patterns to add. ~~Iterable[Dict[str, Union[List[dict], dict, int]]]~~ |
 
-## AttributeRuler.patterns {#patterns tag="property"}
+## AttributeRuler.patterns {id="patterns",tag="property"}
 
 Get all patterns that have been added to the attribute ruler in the
 `patterns_dict` format accepted by
@@ -126,7 +126,7 @@ Get all patterns that have been added to the attribute ruler in the
 | ----------- | -------------------------------------------------------------------------------------------- |
 | **RETURNS** | The patterns added to the attribute ruler. ~~List[Dict[str, Union[List[dict], dict, int]]]~~ |
 
-## AttributeRuler.initialize {#initialize tag="method"}
+## AttributeRuler.initialize {id="initialize",tag="method"}
 
 Initialize the component with data and used before training to load in rules
 from a file. This method is typically called by
@@ -160,7 +160,7 @@ config.
 | `tag_map`      | The tag map that maps fine-grained tags to coarse-grained tags and morphological features. Defaults to `None`. ~~Optional[Dict[str, Dict[Union[int, str], Union[int, str]]]]~~                                                                 |
 | `morph_rules`  | The morph rules that map token text and fine-grained tags to coarse-grained tags, lemmas and morphological features. Defaults to `None`. ~~Optional[Dict[str, Dict[str, Dict[Union[int, str], Union[int, str]]]]]~~                            |
 
-## AttributeRuler.load_from_tag_map {#load_from_tag_map tag="method"}
+## AttributeRuler.load_from_tag_map {id="load_from_tag_map",tag="method"}
 
 Load attribute ruler patterns from a tag map.
 
@@ -168,7 +168,7 @@ Load attribute ruler patterns from a tag map.
 | --------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
 | `tag_map` | The tag map that maps fine-grained tags to coarse-grained tags and morphological features. ~~Dict[str, Dict[Union[int, str], Union[int, str]]]~~ |
 
-## AttributeRuler.load_from_morph_rules {#load_from_morph_rules tag="method"}
+## AttributeRuler.load_from_morph_rules {id="load_from_morph_rules",tag="method"}
 
 Load attribute ruler patterns from morph rules.
 
@@ -176,7 +176,7 @@ Load attribute ruler patterns from morph rules.
 | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `morph_rules` | The morph rules that map token text and fine-grained tags to coarse-grained tags, lemmas and morphological features. ~~Dict[str, Dict[str, Dict[Union[int, str], Union[int, str]]]]~~ |
 
-## AttributeRuler.to_disk {#to_disk tag="method"}
+## AttributeRuler.to_disk {id="to_disk",tag="method"}
 
 Serialize the pipe to disk.
 
@@ -193,7 +193,7 @@ Serialize the pipe to disk.
 | _keyword-only_ |                                                                                                                                            |
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~                                                |
 
-## AttributeRuler.from_disk {#from_disk tag="method"}
+## AttributeRuler.from_disk {id="from_disk",tag="method"}
 
 Load the pipe from disk. Modifies the object in place and returns it.
 
@@ -211,7 +211,7 @@ Load the pipe from disk. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~     |
 | **RETURNS**    | The modified `AttributeRuler` object. ~~AttributeRuler~~                                        |
 
-## AttributeRuler.to_bytes {#to_bytes tag="method"}
+## AttributeRuler.to_bytes {id="to_bytes",tag="method"}
 
 > #### Example
 >
@@ -228,7 +228,7 @@ Serialize the pipe to a bytestring.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The serialized form of the `AttributeRuler` object. ~~bytes~~                               |
 
-## AttributeRuler.from_bytes {#from_bytes tag="method"}
+## AttributeRuler.from_bytes {id="from_bytes",tag="method"}
 
 Load the pipe from a bytestring. Modifies the object in place and returns it.
 
@@ -247,7 +247,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The `AttributeRuler` object. ~~AttributeRuler~~                                             |
 
-## Serialization fields {#serialization-fields}
+## Serialization fields {id="serialization-fields"}
 
 During serialization, spaCy will export several data fields used to restore
 different aspects of the object. If needed, you can exclude them from

website/docs/api/attributes.mdx

@@ -41,10 +41,9 @@ from string attribute names to internal attribute IDs is stored in
 
 The corresponding [`Token` object attributes](/api/token#attributes) can be
 accessed using the same names in lowercase, e.g. `token.orth` or `token.length`.
-For attributes that represent string values, the internal integer ID is
+For attributes that represent string values, the internal integer ID is accessed
-accessed as `Token.attr`, e.g. `token.dep`, while the string value can be
+as `Token.attr`, e.g. `token.dep`, while the string value can be retrieved by
-retrieved by appending `_` as in `token.dep_`.
+appending `_` as in `token.dep_`.
-
 
 | Attribute    | Description                                                                                                                                                   |
 | ------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------- |

website/docs/api/cli.mdx

@@ -12,6 +12,8 @@ menu:
   - ['train', 'train']
   - ['pretrain', 'pretrain']
   - ['evaluate', 'evaluate']
+  - ['benchmark', 'benchmark']
+  - ['apply', 'apply']
   - ['find-threshold', 'find-threshold']
   - ['assemble', 'assemble']
   - ['package', 'package']
@@ -25,7 +27,7 @@ a list of available commands, you can type `python -m spacy --help`. You can
 also add the `--help` flag to any command or subcommand to see the description,
 available arguments and usage.
 
-## download {#download tag="command"}
+## download {id="download",tag="command"}
 
 Download [trained pipelines](/usage/models) for spaCy. The downloader finds the
 best-matching compatible version and uses `pip install` to download the Python
@@ -43,7 +45,7 @@ pipeline name to be specified with its version (e.g. `en_core_web_sm-3.0.0`).
 > will also allow you to add it as a versioned package dependency to your
 > project.
 
-```cli
+```bash
 $ python -m spacy download [model] [--direct] [--sdist] [pip_args]
 ```
 
@@ -56,24 +58,24 @@ $ python -m spacy download [model] [--direct] [--sdist] [pip_args]
 | pip args                                   | Additional installation options to be passed to `pip install` when installing the pipeline package. For example, `--user` to install to the user home directory or `--no-deps` to not install package dependencies. ~~Any (option/flag)~~ |
 | **CREATES**                                | The installed pipeline package in your `site-packages` directory.                                                                                                                                                                         |
 
-## info {#info tag="command"}
+## info {id="info",tag="command"}
 
 Print information about your spaCy installation, trained pipelines and local
 setup, and generate [Markdown](https://en.wikipedia.org/wiki/Markdown)-formatted
 markup to copy-paste into
 [GitHub issues](https://github.com/explosion/spaCy/issues).
 
-```cli
+```bash
 $ python -m spacy info [--markdown] [--silent] [--exclude]
 ```
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy info en_core_web_lg --markdown
 > ```
 
-```cli
+```bash
 $ python -m spacy info [model] [--markdown] [--silent] [--exclude]
 ```
 
@@ -87,7 +89,7 @@ $ python -m spacy info [model] [--markdown] [--silent] [--exclude]
 | `--help`, `-h`                               | Show help message and available arguments. ~~bool (flag)~~                                                              |
 | **PRINTS**                                   | Information about your spaCy installation.                                                                              |
 
-## validate {#validate new="2" tag="command"}
+## validate {id="validate",version="2",tag="command"}
 
 Find all trained pipeline packages installed in the current environment and
 check whether they are compatible with the currently installed version of spaCy.
@@ -102,7 +104,7 @@ compatible versions and command for updating are shown.
 > suite, to ensure all packages are up to date before proceeding. If
 > incompatible packages are found, it will return `1`.
 
-```cli
+```bash
 $ python -m spacy validate
 ```
 
@@ -110,12 +112,12 @@ $ python -m spacy validate
 | ---------- | -------------------------------------------------------------------- |
 | **PRINTS** | Details about the compatibility of your installed pipeline packages. |
 
-## init {#init new="3"}
+## init {id="init",version="3"}
 
 The `spacy init` CLI includes helpful commands for initializing training config
 files and pipeline directories.
 
-### init config {#init-config new="3" tag="command"}
+### init config {id="init-config",version="3",tag="command"}
 
 Initialize and save a [`config.cfg` file](/usage/training#config) using the
 **recommended settings** for your use case. It works just like the
@@ -127,11 +129,11 @@ customize those settings in your config file later.
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy init config config.cfg --lang en --pipeline ner,textcat --optimize accuracy
 > ```
 
-```cli
+```bash
 $ python -m spacy init config [output_file] [--lang] [--pipeline] [--optimize] [--gpu] [--pretraining] [--force]
 ```
 
@@ -147,7 +149,7 @@ $ python -m spacy init config [output_file] [--lang] [--pipeline] [--optimize] [
 | `--help`, `-h`         | Show help message and available arguments. ~~bool (flag)~~                                                                                                                                                                                                                                                                         |
 | **CREATES**            | The config file for training.                                                                                                                                                                                                                                                                                                      |
 
-### init fill-config {#init-fill-config new="3"}
+### init fill-config {id="init-fill-config",version="3"}
 
 Auto-fill a partial [.cfg file](/usage/training#config) with **all default
 values**, e.g. a config generated with the
@@ -161,15 +163,15 @@ validation error with more details.
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy init fill-config base.cfg config.cfg --diff
 > ```
 >
 > #### Example diff
 >
-> ![Screenshot of visual diff in terminal](../images/cli_init_fill-config_diff.jpg)
+> ![Screenshot of visual diff in terminal](/images/cli_init_fill-config_diff.jpg)
 
-```cli
+```bash
 $ python -m spacy init fill-config [base_path] [output_file] [--diff]
 ```
 
@@ -183,7 +185,7 @@ $ python -m spacy init fill-config [base_path] [output_file] [--diff]
 | `--help`, `-h`         | Show help message and available arguments. ~~bool (flag)~~                                                                                                                           |
 | **CREATES**            | Complete and auto-filled config file for training.                                                                                                                                   |
 
-### init vectors {#init-vectors new="3" tag="command"}
+### init vectors {id="init-vectors",version="3",tag="command"}
 
 Convert [word vectors](/usage/linguistic-features#vectors-similarity) for use
 with spaCy. Will export an `nlp` object that you can use in the
@@ -198,7 +200,7 @@ This functionality was previously available as part of the command `init-model`.
 
 </Infobox>
 
-```cli
+```bash
 $ python -m spacy init vectors [lang] [vectors_loc] [output_dir] [--prune] [--truncate] [--name] [--verbose]
 ```
 
@@ -215,7 +217,7 @@ $ python -m spacy init vectors [lang] [vectors_loc] [output_dir] [--prune] [--tr
 | `--help`, `-h`     | Show help message and available arguments. ~~bool (flag)~~                                                                                                                                                                                                          |
 | **CREATES**        | A spaCy pipeline directory containing the vocab and vectors.                                                                                                                                                                                                        |
 
-### init labels {#init-labels new="3" tag="command"}
+### init labels {id="init-labels",version="3",tag="command"}
 
 Generate JSON files for the labels in the data. This helps speed up the training
 process, since spaCy won't have to preprocess the data to extract the labels.
@@ -233,7 +235,7 @@ After generating the labels, you can provide them to components that accept a
 > path = "corpus/labels/ner.json
 > ```
 
-```cli
+```bash
 $ python -m spacy init labels [config_path] [output_path] [--code] [--verbose] [--gpu-id] [overrides]
 ```
 
@@ -248,7 +250,7 @@ $ python -m spacy init labels [config_path] [output_path] [--code] [--verbose] [
 | overrides         | Config parameters to override. Should be options starting with `--` that correspond to the config section and value to override, e.g. `--paths.train ./train.spacy`. ~~Any (option/flag)~~                         |
 | **CREATES**       | The label files.                                                                                                                                                                                                   |
 
-## convert {#convert tag="command"}
+## convert {id="convert",tag="command"}
 
 Convert files into spaCy's
 [binary training data format](/api/data-formats#binary-training), a serialized
@@ -256,7 +258,7 @@ Convert files into spaCy's
 management functions. The converter can be specified on the command line, or
 chosen based on the file extension of the input file.
 
-```cli
+```bash
 $ python -m spacy convert [input_file] [output_dir] [--converter] [--file-type] [--n-sents] [--seg-sents] [--base] [--morphology] [--merge-subtokens] [--ner-map] [--lang]
 ```
 
@@ -277,7 +279,7 @@ $ python -m spacy convert [input_file] [output_dir] [--converter] [--file-type]
 | `--help`, `-h`            | Show help message and available arguments. ~~bool (flag)~~                                                                                |
 | **CREATES**               | Binary [`DocBin`](/api/docbin) training data that can be used with [`spacy train`](/api/cli#train).                                       |
 
-### Converters {#converters}
+### Converters {id="converters"}
 
 | ID              | Description                                                                                                                                                                                                                                                                                                                                                           |
 | --------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
@@ -287,12 +289,12 @@ $ python -m spacy convert [input_file] [output_dir] [--converter] [--file-type]
 | `ner` / `conll` | NER with IOB/IOB2/BILUO tags, one token per line with columns separated by whitespace. The first column is the token and the final column is the NER tag. Sentences are separated by blank lines and documents are separated by the line `-DOCSTART- -X- O O`. Supports CoNLL 2003 NER format. See [sample data](%%GITHUB_SPACY/extra/example_data/ner_example_data). |
 | `iob`           | NER with IOB/IOB2/BILUO tags, one sentence per line with tokens separated by whitespace and annotation separated by `\|`, either `word\|B-ENT`or`word\|POS\|B-ENT`. See [sample data](%%GITHUB_SPACY/extra/example_data/ner_example_data).                                                                                                                            |
 
-## debug {#debug new="3"}
+## debug {id="debug",version="3"}
 
 The `spacy debug` CLI includes helpful commands for debugging and profiling your
 configs, data and implementations.
 
-### debug config {#debug-config new="3" tag="command"}
+### debug config {id="debug-config",version="3",tag="command"}
 
 Debug a [`config.cfg` file](/usage/training#config) and show validation errors.
 The command will create all objects in the tree and validate them. Note that
@@ -302,13 +304,13 @@ errors at once and some issues are only shown once previous errors have been
 fixed. To auto-fill a partial config and save the result, you can use the
 [`init fill-config`](/api/cli#init-fill-config) command.
 
-```cli
+```bash
 $ python -m spacy debug config [config_path] [--code] [--show-functions] [--show-variables] [overrides]
 ```
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy debug config config.cfg
 > ```
 
@@ -332,7 +334,7 @@ python -m spacy init fill-config tmp/starter-config_invalid.cfg tmp/starter-conf
 
 <Accordion title="Example output (valid config and all options)" spaced>
 
-```cli
+```bash
 $ python -m spacy debug config ./config.cfg --show-functions --show-variables
 ```
 
@@ -452,7 +454,7 @@ File       /path/to/thinc/thinc/schedules.py (line 91)
 | overrides                | Config parameters to override. Should be options starting with `--` that correspond to the config section and value to override, e.g. `--paths.train ./train.spacy`. ~~Any (option/flag)~~                                     |
 | **PRINTS**               | Config validation errors, if available.                                                                                                                                                                                        |
 
-### debug data {#debug-data tag="command"}
+### debug data {id="debug-data",tag="command"}
 
 Analyze, debug and validate your training and development data. Get useful
 stats, and find problems like invalid entity annotations, cyclic dependencies,
@@ -474,17 +476,17 @@ report span characteristics such as the average span length and the span (or
 span boundary) distinctiveness. The distinctiveness measure shows how different
 the tokens are with respect to the rest of the corpus using the KL-divergence of
 the token distributions. To learn more, you can check out Papay et al.'s work on
-[*Dissecting Span Identification Tasks with Performance Prediction* (EMNLP 2020)](https://aclanthology.org/2020.emnlp-main.396/).
+[_Dissecting Span Identification Tasks with Performance Prediction_ (EMNLP 2020)](https://aclanthology.org/2020.emnlp-main.396/).
 
 </Infobox>
 
-```cli
+```bash
 $ python -m spacy debug data [config_path] [--code] [--ignore-warnings] [--verbose] [--no-format] [overrides]
 ```
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy debug data ./config.cfg
 > ```
 
@@ -638,7 +640,7 @@ will not be available.
 | overrides                  | Config parameters to override. Should be options starting with `--` that correspond to the config section and value to override, e.g. `--paths.train ./train.spacy`. ~~Any (option/flag)~~                         |
 | **PRINTS**                 | Debugging information.                                                                                                                                                                                             |
 
-### debug diff-config {#debug-diff tag="command"}
+### debug diff-config {id="debug-diff",tag="command"}
 
 Show a diff of a config file with respect to spaCy's defaults or another config
 file. If additional settings were used in the creation of the config file, then
@@ -646,13 +648,13 @@ you must supply these as extra parameters to the command when comparing to the
 default settings. The generated diff can also be used when posting to the
 discussion forum to provide more information for the maintainers.
 
-```cli
+```bash
 $ python -m spacy debug diff-config [config_path] [--compare-to] [--optimize] [--gpu] [--pretraining] [--markdown]
 ```
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy debug diff-config ./config.cfg
 > ```
 
@@ -867,7 +869,7 @@ after_init = null
 | `markdown`, `-md`    | Generate Markdown for Github issues. Defaults to `False`. ~~bool (flag)~~                                                                                                                                                                                                                                 |
 | **PRINTS**           | Diff between the two config files.                                                                                                                                                                                                                                                                        |
 
-### debug profile {#debug-profile tag="command"}
+### debug profile {id="debug-profile",tag="command"}
 
 Profile which functions take the most time in a spaCy pipeline. Input should be
 formatted as one JSON object per line with a key `"text"`. It can either be
@@ -881,7 +883,7 @@ The `profile` command is now available as a subcommand of `spacy debug`.
 
 </Infobox>
 
-```cli
+```bash
 $ python -m spacy debug profile [model] [inputs] [--n-texts]
 ```
 
@@ -893,12 +895,12 @@ $ python -m spacy debug profile [model] [inputs] [--n-texts]
 | `--help`, `-h`    | Show help message and available arguments. ~~bool (flag)~~                         |
 | **PRINTS**        | Profiling information for the pipeline.                                            |
 
-### debug model {#debug-model new="3" tag="command"}
+### debug model {id="debug-model",version="3",tag="command"}
 
 Debug a Thinc [`Model`](https://thinc.ai/docs/api-model) by running it on a
 sample text and checking how it updates its internal weights and parameters.
 
-```cli
+```bash
 $ python -m spacy debug model [config_path] [component] [--layers] [--dimensions] [--parameters] [--gradients] [--attributes] [--print-step0] [--print-step1] [--print-step2] [--print-step3] [--gpu-id]
 ```
 
@@ -909,7 +911,7 @@ model ("Step 0"), which helps us to understand the internal structure of the
 Neural Network, and to focus on specific layers that we want to inspect further
 (see next example).
 
-```cli
+```bash
 $ python -m spacy debug model ./config.cfg tagger -P0
 ```
 
@@ -955,7 +957,7 @@ an all-zero matrix determined by the `nO` and `nI` dimensions. After a first
 training step (Step 2), this matrix has clearly updated its values through the
 training feedback loop.
 
-```cli
+```bash
 $ python -m spacy debug model ./config.cfg tagger -l "5,15" -DIM -PAR -P0 -P1 -P2
 ```
 
@@ -1016,7 +1018,7 @@ $ python -m spacy debug model ./config.cfg tagger -l "5,15" -DIM -PAR -P0 -P1 -P
 | overrides               | Config parameters to override. Should be options starting with `--` that correspond to the config section and value to override, e.g. `--paths.train ./train.spacy`. ~~Any (option/flag)~~                         |
 | **PRINTS**              | Debugging information.                                                                                                                                                                                             |
 
-## train {#train tag="command"}
+## train {id="train",tag="command"}
 
 Train a pipeline. Expects data in spaCy's
 [binary format](/api/data-formats#training) and a
@@ -1042,11 +1044,11 @@ in the section `[paths]`.
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy train config.cfg --output ./output --paths.train ./train --paths.dev ./dev
 > ```
 
-```cli
+```bash
 $ python -m spacy train [config_path] [--output] [--code] [--verbose] [--gpu-id] [overrides]
 ```
 
@@ -1061,7 +1063,7 @@ $ python -m spacy train [config_path] [--output] [--code] [--verbose] [--gpu-id]
 | overrides         | Config parameters to override. Should be options starting with `--` that correspond to the config section and value to override, e.g. `--paths.train ./train.spacy`. ~~Any (option/flag)~~                         |
 | **CREATES**       | The final trained pipeline and the best trained pipeline.                                                                                                                                                          |
 
-### Calling the training function from Python {#train-function new="3.2"}
+### Calling the training function from Python {id="train-function",version="3.2"}
 
 The training CLI exposes a `train` helper function that lets you run the
 training just like `spacy train`. Usually it's easier to use the command line
@@ -1084,7 +1086,7 @@ directly, but if you need to kick off training from code this is how to do it.
 | `use_gpu`      | Which GPU to use. Defaults to -1 for no GPU. ~~int~~                                                                          |
 | `overrides`    | Values to override config settings. ~~Dict[str, Any]~~                                                                        |
 
-## pretrain {#pretrain new="2.1" tag="command,experimental"}
+## pretrain {id="pretrain",version="2.1",tag="command,experimental"}
 
 Pretrain the "token to vector" ([`Tok2vec`](/api/tok2vec)) layer of pipeline
 components on raw text, using an approximate language-modeling objective.
@@ -1112,11 +1114,11 @@ auto-generated by setting `--pretraining` on
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy pretrain config.cfg ./output_pretrain --paths.raw_text ./data.jsonl
 > ```
 
-```cli
+```bash
 $ python -m spacy pretrain [config_path] [output_dir] [--code] [--resume-path] [--epoch-resume] [--gpu-id] [overrides]
 ```
 
@@ -1132,10 +1134,21 @@ $ python -m spacy pretrain [config_path] [output_dir] [--code] [--resume-path] [
 | overrides               | Config parameters to override. Should be options starting with `--` that correspond to the config section and value to override, e.g. `--training.dropout 0.2`. ~~Any (option/flag)~~                              |
 | **CREATES**             | The pretrained weights that can be used to initialize `spacy train`.                                                                                                                                               |
 
-## evaluate {#evaluate new="2" tag="command"}
+## evaluate {id="evaluate",version="2",tag="command"}
 
-Evaluate a trained pipeline. Expects a loadable spaCy pipeline (package name or
+The `evaluate` subcommand is superseded by
-path) and evaluation data in the
+[`spacy benchmark accuracy`](#benchmark-accuracy). `evaluate` is provided as an
+alias to `benchmark accuracy` for compatibility.
+
+## benchmark {id="benchmark", version="3.5"}
+
+The `spacy benchmark` CLI includes commands for benchmarking the accuracy and
+speed of your spaCy pipelines.
+
+### accuracy {id="benchmark-accuracy", version="3.5", tag="command"}
+
+Evaluate the accuracy of a trained pipeline. Expects a loadable spaCy pipeline
+(package name or path) and evaluation data in the
 [binary `.spacy` format](/api/data-formats#binary-training). The
 `--gold-preproc` option sets up the evaluation examples with gold-standard
 sentences and tokens for the predictions. Gold preprocessing helps the
@@ -1145,8 +1158,8 @@ skew. To render a sample of dependency parses in a HTML file using the
 [displaCy visualizations](/usage/visualizers), set as output directory as the
 `--displacy-path` argument.
 
-```cli
+```bash
-$ python -m spacy evaluate [model] [data_path] [--output] [--code] [--gold-preproc] [--gpu-id] [--displacy-path] [--displacy-limit]
+$ python -m spacy benchmark accuracy [model] [data_path] [--output] [--code] [--gold-preproc] [--gpu-id] [--displacy-path] [--displacy-limit]
 ```
 
 | Name                                      | Description                                                                                                                                                                          |
@@ -1162,7 +1175,61 @@ $ python -m spacy evaluate [model] [data_path] [--output] [--code] [--gold-prepr
 | `--help`, `-h`                            | Show help message and available arguments. ~~bool (flag)~~                                                                                                                           |
 | **CREATES**                               | Training results and optional metrics and visualizations.                                                                                                                            |
 
-## find-threshold {#find-threshold new="3.5" tag="command"}
+### speed {id="benchmark-speed", version="3.5", tag="command"}
+
+Benchmark the speed of a trained pipeline with a 95% confidence interval.
+Expects a loadable spaCy pipeline (package name or path) and benchmark data in
+the [binary `.spacy` format](/api/data-formats#binary-training). The pipeline is
+warmed up before any measurements are taken.
+
+```cli
+$ python -m spacy benchmark speed [model] [data_path] [--batch_size] [--no-shuffle] [--gpu-id] [--batches] [--warmup]
+```
+
+| Name                 | Description                                                                                              |
+| -------------------- | -------------------------------------------------------------------------------------------------------- |
+| `model`              | Pipeline to benchmark the speed of. Can be a package or a path to a data directory. ~~str (positional)~~ |
+| `data_path`          | Location of benchmark data in spaCy's [binary format](/api/data-formats#training). ~~Path (positional)~~ |
+| `--batch-size`, `-b` | Set the batch size. If not set, the pipeline's batch size is used. ~~Optional[int] \(option)~~           |
+| `--no-shuffle`       | Do not shuffle documents in the benchmark data. ~~bool (flag)~~                                          |
+| `--gpu-id`, `-g`     | GPU to use, if any. Defaults to `-1` for CPU. ~~int (option)~~                                           |
+| `--batches`          | Number of batches to benchmark on. Defaults to `50`. ~~Optional[int] \(option)~~                         |
+| `--warmup`, `-w`     | Iterations over the benchmark data for warmup. Defaults to `3` ~~Optional[int] \(option)~~               |
+| `--help`, `-h`       | Show help message and available arguments. ~~bool (flag)~~                                               |
+| **PRINTS**           | Pipeline speed in words per second with a 95% confidence interval.                                       |
+
+## apply {id="apply", version="3.5", tag="command"}
+
+Applies a trained pipeline to data and stores the resulting annotated documents
+in a `DocBin`. The input can be a single file or a directory. The recognized
+input formats are:
+
+1. `.spacy`
+2. `.jsonl` containing a user specified `text_key`
+3. Files with any other extension are assumed to be plain text files containing
+   a single document.
+
+When a directory is provided it is traversed recursively to collect all files.
+
+```bash
+$ python -m spacy apply [model] [data-path] [output-file] [--code] [--text-key] [--force-overwrite] [--gpu-id] [--batch-size] [--n-process]
+```
+
+| Name                      | Description                                                                                                                                                                          |
+| ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `model`                   | Pipeline to apply to the data. Can be a package or a path to a data directory. ~~str (positional)~~                                                                                  |
+| `data_path`               | Location of data to be evaluated in spaCy's [binary format](/api/data-formats#training), jsonl, or plain text. ~~Path (positional)~~                                                 |
+| `output-file`, `-o`       | Output `DocBin` path. ~~str (positional)~~                                                                                                                                           |
+| `--code`, `-c`            | Path to Python file with additional code to be imported. Allows [registering custom functions](/usage/training#custom-functions) for new architectures. ~~Optional[Path] \(option)~~ |
+| `--text-key`, `-tk`       | The key for `.jsonl` files to use to grab the texts from. Defaults to `text`. ~~Optional[str] \(option)~~                                                                            |
+| `--force-overwrite`, `-F` | If the provided `output-file` already exists, then force `apply` to overwrite it. If this is `False` (default) then quits with a warning instead. ~~bool (flag)~~                    |
+| `--gpu-id`, `-g`          | GPU to use, if any. Defaults to `-1` for CPU. ~~int (option)~~                                                                                                                       |
+| `--batch-size`, `-b`      | Batch size to use for prediction. Defaults to `1`. ~~int (option)~~                                                                                                                  |
+| `--n-process`, `-n`       | Number of processes to use for prediction. Defaults to `1`. ~~int (option)~~                                                                                                         |
+| `--help`, `-h`            | Show help message and available arguments. ~~bool (flag)~~                                                                                                                           |
+| **CREATES**               | A `DocBin` with the annotations from the `model` for all the files found in `data-path`.                                                                                             |
+
+## find-threshold {id="find-threshold",version="3.5",tag="command"}
 
 Runs prediction trials for a trained model with varying tresholds to maximize
 the specified metric. The search space for the threshold is traversed linearly
@@ -1177,17 +1244,16 @@ be provided.
 
 > #### Examples
 >
-> ```cli
+> ```bash
 > # For textcat_multilabel:
 > $ python -m spacy find-threshold my_nlp data.spacy textcat_multilabel threshold cats_macro_f
 > ```
 >
-> ```cli
+> ```bash
 > # For spancat:
 > $ python -m spacy find-threshold my_nlp data.spacy spancat threshold spans_sc_f
 > ```
 
-
 | Name                    | Description                                                                                                                                                                          |
 | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
 | `model`                 | Pipeline to evaluate. Can be a package or a path to a data directory. ~~str (positional)~~                                                                                           |
@@ -1202,7 +1268,7 @@ be provided.
 | `--silent`, `-V`, `-VV` | GPU to use, if any. Defaults to `-1` for CPU. ~~int (option)~~                                                                                                                       |
 | `--help`, `-h`          | Show help message and available arguments. ~~bool (flag)~~                                                                                                                           |
 
-## assemble {#assemble tag="command"}
+## assemble {id="assemble",tag="command"}
 
 Assemble a pipeline from a config file without additional training. Expects a
 [config file](/api/data-formats#config) with all settings and hyperparameters.
@@ -1212,11 +1278,11 @@ config.
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy assemble config.cfg ./output
 > ```
 
-```cli
+```bash
 $ python -m spacy assemble [config_path] [output_dir] [--code] [--verbose] [overrides]
 ```
 
@@ -1230,7 +1296,7 @@ $ python -m spacy assemble [config_path] [output_dir] [--code] [--verbose] [over
 | overrides         | Config parameters to override. Should be options starting with `--` that correspond to the config section and value to override, e.g. `--paths.data ./data`. ~~Any (option/flag)~~                            |
 | **CREATES**       | The final assembled pipeline.                                                                                                                                                                                 |
 
-## package {#package tag="command"}
+## package {id="package",tag="command"}
 
 Generate an installable [Python package](/usage/training#models-generating) from
 an existing pipeline data directory. All data files are copied over. If
@@ -1256,13 +1322,13 @@ the sdist and wheel by setting `--build sdist,wheel`.
 
 </Infobox>
 
-```cli
+```bash
 $ python -m spacy package [input_dir] [output_dir] [--code] [--meta-path] [--create-meta] [--build] [--name] [--version] [--force]
 ```
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy package /input /output
 > $ cd /output/en_pipeline-0.0.0
 > $ pip install dist/en_pipeline-0.0.0.tar.gz
@@ -1282,13 +1348,13 @@ $ python -m spacy package [input_dir] [output_dir] [--code] [--meta-path] [--cre
 | `--help`, `-h`                               | Show help message and available arguments. ~~bool (flag)~~                                                                                                                                                                                                                       |
 | **CREATES**                                  | A Python package containing the spaCy pipeline.                                                                                                                                                                                                                                  |
 
-## project {#project new="3"}
+## project {id="project",version="3"}
 
 The `spacy project` CLI includes subcommands for working with
 [spaCy projects](/usage/projects), end-to-end workflows for building and
 deploying custom spaCy pipelines.
 
-### project clone {#project-clone tag="command"}
+### project clone {id="project-clone",tag="command"}
 
 Clone a project template from a Git repository. Calls into `git` under the hood
 and can use the sparse checkout feature if available, so you're only downloading
@@ -1297,19 +1363,19 @@ what you need. By default, spaCy's
 can provide any other repo (public or private) that you have access to using the
 `--repo` option.
 
-```cli
+```bash
 $ python -m spacy project clone [name] [dest] [--repo] [--branch] [--sparse]
 ```
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy project clone pipelines/ner_wikiner
 > ```
 >
 > Clone from custom repo:
 >
-> ```cli
+> ```bash
 > $ python -m spacy project clone template --repo https://github.com/your_org/your_repo
 > ```
 
@@ -1323,7 +1389,7 @@ $ python -m spacy project clone [name] [dest] [--repo] [--branch] [--sparse]
 | `--help`, `-h`   | Show help message and available arguments. ~~bool (flag)~~                                                                                                |
 | **CREATES**      | The cloned [project directory](/usage/projects#project-files).                                                                                            |
 
-### project assets {#project-assets tag="command"}
+### project assets {id="project-assets",tag="command"}
 
 Fetch project assets like datasets and pretrained weights. Assets are defined in
 the `assets` section of the [`project.yml`](/usage/projects#project-yml). If a
@@ -1334,13 +1400,13 @@ considered "private" and you have to take care of putting them into the
 destination directory yourself. If a local path is provided, the asset is copied
 into the current project.
 
-```cli
+```bash
 $ python -m spacy project assets [project_dir]
 ```
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy project assets [--sparse]
 > ```
 
@@ -1351,7 +1417,7 @@ $ python -m spacy project assets [project_dir]
 | `--help`, `-h`   | Show help message and available arguments. ~~bool (flag)~~                                                                                                |
 | **CREATES**      | Downloaded or copied assets defined in the `project.yml`.                                                                                                 |
 
-### project run {#project-run tag="command"}
+### project run {id="project-run",tag="command"}
 
 Run a named command or workflow defined in the
 [`project.yml`](/usage/projects#project-yml). If a workflow name is specified,
@@ -1360,13 +1426,13 @@ all commands in the workflow are run, in order. If commands define
 re-run if state has changed. For example, if the input dataset changes, a
 preprocessing command that depends on those files will be re-run.
 
-```cli
+```bash
 $ python -m spacy project run [subcommand] [project_dir] [--force] [--dry]
 ```
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy project run train
 > ```
 
@@ -1379,7 +1445,7 @@ $ python -m spacy project run [subcommand] [project_dir] [--force] [--dry]
 | `--help`, `-h`  | Show help message and available arguments. ~~bool (flag)~~                              |
 | **EXECUTES**    | The command defined in the `project.yml`.                                               |
 
-### project push {#project-push tag="command"}
+### project push {id="project-push",tag="command"}
 
 Upload all available files or directories listed as in the `outputs` section of
 commands to a remote storage. Outputs are archived and compressed prior to
@@ -1399,13 +1465,13 @@ remote storages, so you can use any protocol that `Pathy` supports, including
 filesystem, although you may need to install extra dependencies to use certain
 protocols.
 
-```cli
+```bash
 $ python -m spacy project push [remote] [project_dir]
 ```
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy project push my_bucket
 > ```
 >
@@ -1422,7 +1488,7 @@ $ python -m spacy project push [remote] [project_dir]
 | `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~                              |
 | **UPLOADS**    | All project outputs that exist and are not already stored in the remote.                |
 
-### project pull {#project-pull tag="command"}
+### project pull {id="project-pull",tag="command"}
 
 Download all files or directories listed as `outputs` for commands, unless they
 are not already present locally. When searching for files in the remote, `pull`
@@ -1444,13 +1510,13 @@ remote storages, so you can use any protocol that `Pathy` supports, including
 filesystem, although you may need to install extra dependencies to use certain
 protocols.
 
-```cli
+```bash
 $ python -m spacy project pull [remote] [project_dir]
 ```
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy project pull my_bucket
 > ```
 >
@@ -1467,7 +1533,7 @@ $ python -m spacy project pull [remote] [project_dir]
 | `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~                              |
 | **DOWNLOADS**  | All project outputs that do not exist locally and can be found in the remote.           |
 
-### project document {#project-document tag="command"}
+### project document {id="project-document",tag="command"}
 
 Auto-generate a pretty Markdown-formatted `README` for your project, based on
 its [`project.yml`](/usage/projects#project-yml). Will create sections that
@@ -1476,13 +1542,13 @@ content will be placed between two hidden markers, so you can add your own
 custom content before or after the auto-generated documentation. When you re-run
 the `project document` command, only the auto-generated part is replaced.
 
-```cli
+```bash
 $ python -m spacy project document [project_dir] [--output] [--no-emoji]
 ```
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy project document --output README.md
 > ```
 
@@ -1491,7 +1557,7 @@ $ python -m spacy project document [project_dir] [--output] [--no-emoji]
 For more examples, see the templates in our
 [`projects`](https://github.com/explosion/projects) repo.
 
-![Screenshot of auto-generated Markdown Readme](../images/project_document.jpg)
+![Screenshot of auto-generated Markdown Readme](/images/project_document.jpg)
 
 </Accordion>
 
@@ -1502,7 +1568,7 @@ For more examples, see the templates in our
 | `--no-emoji`, `-NE` | Don't use emoji in the titles. ~~bool (flag)~~                                                                                                                                                          |
 | **CREATES**         | The Markdown-formatted project documentation.                                                                                                                                                           |
 
-### project dvc {#project-dvc tag="command"}
+### project dvc {id="project-dvc",tag="command"}
 
 Auto-generate [Data Version Control](https://dvc.org) (DVC) config file. Calls
 [`dvc run`](https://dvc.org/doc/command-reference/run) with `--no-exec` under
@@ -1522,13 +1588,13 @@ You'll also need to add the assets you want to track with
 
 </Infobox>
 
-```cli
+```bash
 $ python -m spacy project dvc [project_dir] [workflow] [--force] [--verbose] [--quiet]
 ```
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ git init
 > $ dvc init
 > $ python -m spacy project dvc all
@@ -1544,14 +1610,14 @@ $ python -m spacy project dvc [project_dir] [workflow] [--force] [--verbose] [--
 | `--help`, `-h`    | Show help message and available arguments. ~~bool (flag)~~                                                    |
 | **CREATES**       | A `dvc.yaml` file in the project directory, based on the steps defined in the given workflow.                 |
 
-## huggingface-hub {#huggingface-hub new="3.1"}
+## huggingface-hub {id="huggingface-hub",version="3.1"}
 
 The `spacy huggingface-cli` CLI includes commands for uploading your trained
 spaCy pipelines to the [Hugging Face Hub](https://huggingface.co/).
 
 > #### Installation
 >
-> ```cli
+> ```bash
 > $ pip install spacy-huggingface-hub
 > $ huggingface-cli login
 > ```
@@ -1565,19 +1631,19 @@ package installed. Installing the package will automatically add the
 
 </Infobox>
 
-### huggingface-hub push {#huggingface-hub-push tag="command"}
+### huggingface-hub push {id="huggingface-hub-push",tag="command"}
 
 Push a spaCy pipeline to the Hugging Face Hub. Expects a `.whl` file packaged
 with [`spacy package`](/api/cli#package) and `--build wheel`. For more details,
 see the spaCy project [integration](/usage/projects#huggingface_hub).
 
-```cli
+```bash
 $ python -m spacy huggingface-hub push [whl_path] [--org] [--msg] [--local-repo] [--verbose]
 ```
 
 > #### Example
 >
-> ```cli
+> ```bash
 > $ python -m spacy huggingface-hub push en_ner_fashion-0.0.0-py3-none-any.whl
 > ```
 

website/docs/api/coref.mdx

@@ -34,7 +34,7 @@ same thing. Clusters are represented as SpanGroups that start with a prefix
 A `CoreferenceResolver` component can be paired with a
 [`SpanResolver`](/api/span-resolver) to expand single tokens to spans.
 
-## Assigned Attributes {#assigned-attributes}
+## Assigned Attributes {id="assigned-attributes"}
 
 Predictions will be saved to `Doc.spans` as a [`SpanGroup`](/api/spangroup). The
 span key will be a prefix plus a serial number referring to the coreference
@@ -47,7 +47,7 @@ parameter.
 | ------------------------------------------ | ------------------------------------------------------------------------------------------------------- |
 | `Doc.spans[prefix + "_" + cluster_number]` | One coreference cluster, represented as single-token spans. Cluster numbers start from 1. ~~SpanGroup~~ |
 
-## Config and implementation {#config}
+## Config and implementation {id="config"}
 
 The default config is defined by the pipeline component factory and describes
 how the component should be configured. You can override its settings via the
@@ -73,7 +73,7 @@ details on the architectures and their arguments and hyperparameters.
 | `model`               | The [`Model`](https://thinc.ai/docs/api-model) powering the pipeline component. Defaults to [Coref](/api/architectures#Coref). ~~Model~~ |
 | `span_cluster_prefix` | The prefix for the keys for clusters saved to `doc.spans`. Defaults to `coref_clusters`. ~~str~~                                         |
 
-## CoreferenceResolver.\_\_init\_\_ {#init tag="method"}
+## CoreferenceResolver.\_\_init\_\_ {id="init",tag="method"}
 
 > #### Example
 >
@@ -102,7 +102,7 @@ shortcut for this and instantiate the component using its string name and
 | _keyword-only_        |                                                                                                     |
 | `span_cluster_prefix` | The prefix for the key for saving clusters of spans. ~~bool~~                                       |
 
-## CoreferenceResolver.\_\_call\_\_ {#call tag="method"}
+## CoreferenceResolver.\_\_call\_\_ {id="call",tag="method"}
 
 Apply the pipe to one document. The document is modified in place and returned.
 This usually happens under the hood when the `nlp` object is called on a text
@@ -125,7 +125,7 @@ and all pipeline components are applied to the `Doc` in order. Both
 | `doc`       | The document to process. ~~Doc~~ |
 | **RETURNS** | The processed document. ~~Doc~~  |
 
-## CoreferenceResolver.pipe {#pipe tag="method"}
+## CoreferenceResolver.pipe {id="pipe",tag="method"}
 
 Apply the pipe to a stream of documents. This usually happens under the hood
 when the `nlp` object is called on a text and all pipeline components are
@@ -148,7 +148,7 @@ applied to the `Doc` in order. Both [`__call__`](/api/coref#call) and
 | `batch_size`   | The number of documents to buffer. Defaults to `128`. ~~int~~ |
 | **YIELDS**     | The processed documents in order. ~~Doc~~                     |
 
-## CoreferenceResolver.initialize {#initialize tag="method"}
+## CoreferenceResolver.initialize {id="initialize",tag="method"}
 
 Initialize the component for training. `get_examples` should be a function that
 returns an iterable of [`Example`](/api/example) objects. **At least one example
@@ -172,7 +172,7 @@ by [`Language.initialize`](/api/language#initialize).
 | _keyword-only_ |                                                                                                                                                                            |
 | `nlp`          | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~                                                                                                       |
 
-## CoreferenceResolver.predict {#predict tag="method"}
+## CoreferenceResolver.predict {id="predict",tag="method"}
 
 Apply the component's model to a batch of [`Doc`](/api/doc) objects, without
 modifying them. Clusters are returned as a list of `MentionClusters`, one for
@@ -192,7 +192,7 @@ to token indices.
 | `docs`      | The documents to predict. ~~Iterable[Doc]~~                                  |
 | **RETURNS** | The predicted coreference clusters for the `docs`. ~~List[MentionClusters]~~ |
 
-## CoreferenceResolver.set_annotations {#set_annotations tag="method"}
+## CoreferenceResolver.set_annotations {id="set_annotations",tag="method"}
 
 Modify a batch of documents, saving coreference clusters in `Doc.spans`.
 
@@ -209,7 +209,7 @@ Modify a batch of documents, saving coreference clusters in `Doc.spans`.
 | `docs`     | The documents to modify. ~~Iterable[Doc]~~                                   |
 | `clusters` | The predicted coreference clusters for the `docs`. ~~List[MentionClusters]~~ |
 
-## CoreferenceResolver.update {#update tag="method"}
+## CoreferenceResolver.update {id="update",tag="method"}
 
 Learn from a batch of [`Example`](/api/example) objects. Delegates to
 [`predict`](/api/coref#predict).
@@ -231,7 +231,7 @@ Learn from a batch of [`Example`](/api/example) objects. Delegates to
 | `losses`       | Optional record of the loss during training. Updated using the component name as the key. ~~Optional[Dict[str, float]]~~ |
 | **RETURNS**    | The updated `losses` dictionary. ~~Dict[str, float]~~                                                                    |
 
-## CoreferenceResolver.create_optimizer {#create_optimizer tag="method"}
+## CoreferenceResolver.create_optimizer {id="create_optimizer",tag="method"}
 
 Create an optimizer for the pipeline component.
 
@@ -246,7 +246,7 @@ Create an optimizer for the pipeline component.
 | ----------- | ---------------------------- |
 | **RETURNS** | The optimizer. ~~Optimizer~~ |
 
-## CoreferenceResolver.use_params {#use_params tag="method, contextmanager"}
+## CoreferenceResolver.use_params {id="use_params",tag="method, contextmanager"}
 
 Modify the pipe's model, to use the given parameter values. At the end of the
 context, the original parameters are restored.
@@ -263,7 +263,7 @@ context, the original parameters are restored.
 | -------- | -------------------------------------------------- |
 | `params` | The parameter values to use in the model. ~~dict~~ |
 
-## CoreferenceResolver.to_disk {#to_disk tag="method"}
+## CoreferenceResolver.to_disk {id="to_disk",tag="method"}
 
 Serialize the pipe to disk.
 
@@ -280,7 +280,7 @@ Serialize the pipe to disk.
 | _keyword-only_ |                                                                                                                                            |
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~                                                |
 
-## CoreferenceResolver.from_disk {#from_disk tag="method"}
+## CoreferenceResolver.from_disk {id="from_disk",tag="method"}
 
 Load the pipe from disk. Modifies the object in place and returns it.
 
@@ -298,7 +298,7 @@ Load the pipe from disk. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~     |
 | **RETURNS**    | The modified `CoreferenceResolver` object. ~~CoreferenceResolver~~                              |
 
-## CoreferenceResolver.to_bytes {#to_bytes tag="method"}
+## CoreferenceResolver.to_bytes {id="to_bytes",tag="method"}
 
 > #### Example
 >
@@ -315,7 +315,7 @@ Serialize the pipe to a bytestring, including the `KnowledgeBase`.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The serialized form of the `CoreferenceResolver` object. ~~bytes~~                          |
 
-## CoreferenceResolver.from_bytes {#from_bytes tag="method"}
+## CoreferenceResolver.from_bytes {id="from_bytes",tag="method"}
 
 Load the pipe from a bytestring. Modifies the object in place and returns it.
 
@@ -334,7 +334,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The `CoreferenceResolver` object. ~~CoreferenceResolver~~                                   |
 
-## Serialization fields {#serialization-fields}
+## Serialization fields {id="serialization-fields"}
 
 During serialization, spaCy will export several data fields used to restore
 different aspects of the object. If needed, you can exclude them from

website/docs/api/corpus.mdx

@@ -3,7 +3,7 @@ title: Corpus
 teaser: An annotated corpus
 tag: class
 source: spacy/training/corpus.py
-new: 3
+version: 3
 ---
 
 This class manages annotated corpora and can be used for training and
@@ -13,7 +13,7 @@ customize the data loading during training, you can register your own
 see the usage guide on [data utilities](/usage/training#data) for more details
 and examples.
 
-## Config and implementation {#config}
+## Config and implementation {id="config"}
 
 `spacy.Corpus.v1` is a registered function that creates a `Corpus` of training
 or evaluation data. It takes the same arguments as the `Corpus` class and
@@ -49,7 +49,7 @@ streaming.
 %%GITHUB_SPACY/spacy/training/corpus.py
 ```
 
-## Corpus.\_\_init\_\_ {#init tag="method"}
+## Corpus.\_\_init\_\_ {id="init",tag="method"}
 
 Create a `Corpus` for iterating [Example](/api/example) objects from a file or
 directory of [`.spacy` data files](/api/data-formats#binary-training). The
@@ -81,7 +81,7 @@ train/test skew.
 | `augmenter`    | Optional data augmentation callback. ~~Callable[[Language, Example], Iterable[Example]]~~                                                           |
 | `shuffle`      | Whether to shuffle the examples. Defaults to `False`. ~~bool~~                                                                                      |
 
-## Corpus.\_\_call\_\_ {#call tag="method"}
+## Corpus.\_\_call\_\_ {id="call",tag="method"}
 
 Yield examples from the data.
 
@@ -101,7 +101,7 @@ Yield examples from the data.
 | `nlp`      | The current `nlp` object. ~~Language~~ |
 | **YIELDS** | The examples. ~~Example~~              |
 
-## JsonlCorpus {#jsonlcorpus tag="class"}
+## JsonlCorpus {id="jsonlcorpus",tag="class"}
 
 Iterate Doc objects from a file or directory of JSONL (newline-delimited JSON)
 formatted raw text files. Can be used to read the raw text corpus for language
@@ -120,14 +120,13 @@ file.
 > srsly.write_jsonl("/path/to/text.jsonl", data)
 > ```
 
-```json
+```json {title="Example"}
-### Example
 {"text": "Can I ask where you work now and what you do, and if you enjoy it?"}
 {"text": "They may just pull out of the Seattle market completely, at least until they have autonomous vehicles."}
 {"text": "My cynical view on this is that it will never be free to the public. Reason: what would be the draw of joining the military? Right now their selling point is free Healthcare and Education. Ironically both are run horribly and most, that I've talked to, come out wishing they never went in."}
 ```
 
-### JsonlCorpus.\_\init\_\_ {#jsonlcorpus tag="method"}
+### JsonlCorpus.\_\_init\_\_ {id="jsonlcorpus",tag="method"}
 
 Initialize the reader.
 
@@ -157,7 +156,7 @@ Initialize the reader.
 | `max_length`   | Maximum document length (in tokens). Longer documents will be skipped. Defaults to `0`, which indicates no limit. ~~int~~        |
 | `limit`        | Limit corpus to a subset of examples, e.g. for debugging. Defaults to `0` for no limit. ~~int~~                                  |
 
-### JsonlCorpus.\_\_call\_\_ {#jsonlcorpus-call tag="method"}
+### JsonlCorpus.\_\_call\_\_ {id="jsonlcorpus-call",tag="method"}
 
 Yield examples from the data.
 

website/docs/api/cython-classes.mdx

@@ -9,7 +9,7 @@ menu:
   - ['StringStore', 'stringstore']
 ---
 
-## Doc {#doc tag="cdef class" source="spacy/tokens/doc.pxd"}
+## Doc {id="doc",tag="cdef class",source="spacy/tokens/doc.pxd"}
 
 The `Doc` object holds an array of [`TokenC`](/api/cython-structs#tokenc)
 structs.
@@ -21,7 +21,7 @@ accessed from Python. For the Python documentation, see [`Doc`](/api/doc).
 
 </Infobox>
 
-### Attributes {#doc_attributes}
+### Attributes {id="doc_attributes"}
 
 | Name         | Description                                                                                              |
 | ------------ | -------------------------------------------------------------------------------------------------------- |
@@ -31,7 +31,7 @@ accessed from Python. For the Python documentation, see [`Doc`](/api/doc).
 | `length`     | The number of tokens in the document. ~~int~~                                                            |
 | `max_length` | The underlying size of the `Doc.c` array. ~~int~~                                                        |
 
-### Doc.push_back {#doc_push_back tag="method"}
+### Doc.push_back {id="doc_push_back",tag="method"}
 
 Append a token to the `Doc`. The token can be provided as a
 [`LexemeC`](/api/cython-structs#lexemec) or
@@ -55,7 +55,7 @@ Append a token to the `Doc`. The token can be provided as a
 | `lex_or_tok` | The word to append to the `Doc`. ~~LexemeOrToken~~ |
 | `has_space`  | Whether the word has trailing whitespace. ~~bint~~ |
 
-## Token {#token tag="cdef class" source="spacy/tokens/token.pxd"}
+## Token {id="token",tag="cdef class",source="spacy/tokens/token.pxd"}
 
 A Cython class providing access and methods for a
 [`TokenC`](/api/cython-structs#tokenc) struct. Note that the `Token` object does
@@ -68,7 +68,7 @@ accessed from Python. For the Python documentation, see [`Token`](/api/token).
 
 </Infobox>
 
-### Attributes {#token_attributes}
+### Attributes {id="token_attributes"}
 
 | Name    | Description                                                                |
 | ------- | -------------------------------------------------------------------------- |
@@ -77,7 +77,7 @@ accessed from Python. For the Python documentation, see [`Token`](/api/token).
 | `i`     | The offset of the token within the document. ~~int~~                       |
 | `doc`   | The parent document. ~~Doc~~                                               |
 
-### Token.cinit {#token_cinit tag="method"}
+### Token.cinit {id="token_cinit",tag="method"}
 
 Create a `Token` object from a `TokenC*` pointer.
 
@@ -94,7 +94,7 @@ Create a `Token` object from a `TokenC*` pointer.
 | `offset` | The offset of the token within the document. ~~int~~                       |
 | `doc`    | The parent document. ~~int~~                                               |
 
-## Span {#span tag="cdef class" source="spacy/tokens/span.pxd"}
+## Span {id="span",tag="cdef class",source="spacy/tokens/span.pxd"}
 
 A Cython class providing access and methods for a slice of a `Doc` object.
 
@@ -105,7 +105,7 @@ accessed from Python. For the Python documentation, see [`Span`](/api/span).
 
 </Infobox>
 
-### Attributes {#span_attributes}
+### Attributes {id="span_attributes"}
 
 | Name         | Description                                                                   |
 | ------------ | ----------------------------------------------------------------------------- |
@@ -116,7 +116,7 @@ accessed from Python. For the Python documentation, see [`Span`](/api/span).
 | `end_char`   | The index of the last character of the span. ~~int~~                          |
 | `label`      | A label to attach to the span, e.g. for named entities. ~~attr_t (uint64_t)~~ |
 
-## Lexeme {#lexeme tag="cdef class" source="spacy/lexeme.pxd"}
+## Lexeme {id="lexeme",tag="cdef class",source="spacy/lexeme.pxd"}
 
 A Cython class providing access and methods for an entry in the vocabulary.
 
@@ -127,7 +127,7 @@ accessed from Python. For the Python documentation, see [`Lexeme`](/api/lexeme).
 
 </Infobox>
 
-### Attributes {#lexeme_attributes}
+### Attributes {id="lexeme_attributes"}
 
 | Name    | Description                                                                   |
 | ------- | ----------------------------------------------------------------------------- |
@@ -135,7 +135,7 @@ accessed from Python. For the Python documentation, see [`Lexeme`](/api/lexeme).
 | `vocab` | A reference to the shared `Vocab` object. ~~Vocab~~                           |
 | `orth`  | ID of the verbatim text content. ~~attr_t (uint64_t)~~                        |
 
-## Vocab {#vocab tag="cdef class" source="spacy/vocab.pxd"}
+## Vocab {id="vocab",tag="cdef class",source="spacy/vocab.pxd"}
 
 A Cython class providing access and methods for a vocabulary and other data
 shared across a language.
@@ -147,7 +147,7 @@ accessed from Python. For the Python documentation, see [`Vocab`](/api/vocab).
 
 </Infobox>
 
-### Attributes {#vocab_attributes}
+### Attributes {id="vocab_attributes"}
 
 | Name      | Description                                                                                                |
 | --------- | ---------------------------------------------------------------------------------------------------------- |
@@ -155,7 +155,7 @@ accessed from Python. For the Python documentation, see [`Vocab`](/api/vocab).
 | `strings` | A `StringStore` that maps string to hash values and vice versa. ~~StringStore~~                            |
 | `length`  | The number of entries in the vocabulary. ~~int~~                                                           |
 
-### Vocab.get {#vocab_get tag="method"}
+### Vocab.get {id="vocab_get",tag="method"}
 
 Retrieve a [`LexemeC*`](/api/cython-structs#lexemec) pointer from the
 vocabulary.
@@ -172,7 +172,7 @@ vocabulary.
 | `string`    | The string of the word to look up. ~~str~~                                                                 |
 | **RETURNS** | The lexeme in the vocabulary. ~~const LexemeC\*~~                                                          |
 
-### Vocab.get_by_orth {#vocab_get_by_orth tag="method"}
+### Vocab.get_by_orth {id="vocab_get_by_orth",tag="method"}
 
 Retrieve a [`LexemeC*`](/api/cython-structs#lexemec) pointer from the
 vocabulary.
@@ -189,7 +189,7 @@ vocabulary.
 | `orth`      | ID of the verbatim text content. ~~attr_t (uint64_t)~~                                                     |
 | **RETURNS** | The lexeme in the vocabulary. ~~const LexemeC\*~~                                                          |
 
-## StringStore {#stringstore tag="cdef class" source="spacy/strings.pxd"}
+## StringStore {id="stringstore",tag="cdef class",source="spacy/strings.pxd"}
 
 A lookup table to retrieve strings by 64-bit hashes.
 
@@ -201,7 +201,7 @@ accessed from Python. For the Python documentation, see
 
 </Infobox>
 
-### Attributes {#stringstore_attributes}
+### Attributes {id="stringstore_attributes"}
 
 | Name   | Description                                                                                                      |
 | ------ | ---------------------------------------------------------------------------------------------------------------- |

website/docs/api/cython-structs.mdx

@@ -7,7 +7,7 @@ menu:
   - ['LexemeC', 'lexemec']
 ---
 
-## TokenC {#tokenc tag="C struct" source="spacy/structs.pxd"}
+## TokenC {id="tokenc",tag="C struct",source="spacy/structs.pxd"}
 
 Cython data container for the `Token` object.
 
@@ -39,7 +39,7 @@ Cython data container for the `Token` object.
 | `ent_type`   | Named entity type. ~~attr_t (uint64_t)~~                                                                                                                                                                                                                                                                                                    |
 | `ent_id`     | ID of the entity the token is an instance of, if any. Currently not used, but potentially for coreference resolution. ~~attr_t (uint64_t)~~                                                                                                                                                                                                 |
 
-### Token.get_struct_attr {#token_get_struct_attr tag="staticmethod, nogil" source="spacy/tokens/token.pxd"}
+### Token.get_struct_attr {id="token_get_struct_attr",tag="staticmethod, nogil",source="spacy/tokens/token.pxd"}
 
 Get the value of an attribute from the `TokenC` struct by attribute ID.
 
@@ -58,7 +58,7 @@ Get the value of an attribute from the `TokenC` struct by attribute ID.
 | `feat_name` | The ID of the attribute to look up. The attributes are enumerated in `spacy.typedefs`. ~~attr_id_t~~ |
 | **RETURNS** | The value of the attribute. ~~attr_t (uint64_t)~~                                                    |
 
-### Token.set_struct_attr {#token_set_struct_attr tag="staticmethod, nogil" source="spacy/tokens/token.pxd"}
+### Token.set_struct_attr {id="token_set_struct_attr",tag="staticmethod, nogil",source="spacy/tokens/token.pxd"}
 
 Set the value of an attribute of the `TokenC` struct by attribute ID.
 
@@ -78,7 +78,7 @@ Set the value of an attribute of the `TokenC` struct by attribute ID.
 | `feat_name` | The ID of the attribute to look up. The attributes are enumerated in `spacy.typedefs`. ~~attr_id_t~~ |
 | `value`     | The value to set. ~~attr_t (uint64_t)~~                                                              |
 
-### token_by_start {#token_by_start tag="function" source="spacy/tokens/doc.pxd"}
+### token_by_start {id="token_by_start",tag="function",source="spacy/tokens/doc.pxd"}
 
 Find a token in a `TokenC*` array by the offset of its first character.
 
@@ -100,7 +100,7 @@ Find a token in a `TokenC*` array by the offset of its first character.
 | `start_char` | The start index to search for. ~~int~~                            |
 | **RETURNS**  | The index of the token in the array or `-1` if not found. ~~int~~ |
 
-### token_by_end {#token_by_end tag="function" source="spacy/tokens/doc.pxd"}
+### token_by_end {id="token_by_end",tag="function",source="spacy/tokens/doc.pxd"}
 
 Find a token in a `TokenC*` array by the offset of its final character.
 
@@ -122,7 +122,7 @@ Find a token in a `TokenC*` array by the offset of its final character.
 | `end_char`  | The end index to search for. ~~int~~                              |
 | **RETURNS** | The index of the token in the array or `-1` if not found. ~~int~~ |
 
-### set_children_from_heads {#set_children_from_heads tag="function" source="spacy/tokens/doc.pxd"}
+### set_children_from_heads {id="set_children_from_heads",tag="function",source="spacy/tokens/doc.pxd"}
 
 Set attributes that allow lookup of syntactic children on a `TokenC*` array.
 This function must be called after making changes to the `TokenC.head`
@@ -148,7 +148,7 @@ attribute, in order to make the parse tree navigation consistent.
 | `tokens` | A `TokenC*` array. ~~const TokenC\*~~      |
 | `length` | The number of tokens in the array. ~~int~~ |
 
-## LexemeC {#lexemec tag="C struct" source="spacy/structs.pxd"}
+## LexemeC {id="lexemec",tag="C struct",source="spacy/structs.pxd"}
 
 Struct holding information about a lexical type. `LexemeC` structs are usually
 owned by the `Vocab`, and accessed through a read-only pointer on the `TokenC`
@@ -172,7 +172,7 @@ struct.
 | `prefix` | Length-N substring from the start of the lexeme. Defaults to `N=1`. ~~attr_t (uint64_t)~~                                                        |
 | `suffix` | Length-N substring from the end of the lexeme. Defaults to `N=3`. ~~attr_t (uint64_t)~~                                                          |
 
-### Lexeme.get_struct_attr {#lexeme_get_struct_attr tag="staticmethod, nogil" source="spacy/lexeme.pxd"}
+### Lexeme.get_struct_attr {id="lexeme_get_struct_attr",tag="staticmethod, nogil",source="spacy/lexeme.pxd"}
 
 Get the value of an attribute from the `LexemeC` struct by attribute ID.
 
@@ -192,7 +192,7 @@ Get the value of an attribute from the `LexemeC` struct by attribute ID.
 | `feat_name` | The ID of the attribute to look up. The attributes are enumerated in `spacy.typedefs`. ~~attr_id_t~~ |
 | **RETURNS** | The value of the attribute. ~~attr_t (uint64_t)~~                                                    |
 
-### Lexeme.set_struct_attr {#lexeme_set_struct_attr tag="staticmethod, nogil" source="spacy/lexeme.pxd"}
+### Lexeme.set_struct_attr {id="lexeme_set_struct_attr",tag="staticmethod, nogil",source="spacy/lexeme.pxd"}
 
 Set the value of an attribute of the `LexemeC` struct by attribute ID.
 
@@ -212,7 +212,7 @@ Set the value of an attribute of the `LexemeC` struct by attribute ID.
 | `feat_name` | The ID of the attribute to look up. The attributes are enumerated in `spacy.typedefs`. ~~attr_id_t~~ |
 | `value`     | The value to set. ~~attr_t (uint64_t)~~                                                              |
 
-### Lexeme.c_check_flag {#lexeme_c_check_flag tag="staticmethod, nogil" source="spacy/lexeme.pxd"}
+### Lexeme.c_check_flag {id="lexeme_c_check_flag",tag="staticmethod, nogil",source="spacy/lexeme.pxd"}
 
 Check the value of a binary flag attribute.
 
@@ -232,7 +232,7 @@ Check the value of a binary flag attribute.
 | `flag_id`   | The ID of the flag to look up. The flag IDs are enumerated in `spacy.typedefs`. ~~attr_id_t~~ |
 | **RETURNS** | The boolean value of the flag. ~~bint~~                                                       |
 
-### Lexeme.c_set_flag {#lexeme_c_set_flag tag="staticmethod, nogil" source="spacy/lexeme.pxd"}
+### Lexeme.c_set_flag {id="lexeme_c_set_flag",tag="staticmethod, nogil",source="spacy/lexeme.pxd"}
 
 Set the value of a binary flag attribute.
 

website/docs/api/cython.mdx

@@ -6,7 +6,7 @@ menu:
   - ['Conventions', 'conventions']
 ---
 
-## Overview {#overview hidden="true"}
+## Overview {id="overview",hidden="true"}
 
 > #### What's Cython?
 >
@@ -37,7 +37,7 @@ class holds a [`LexemeC`](/api/cython-structs#lexemec) struct, at `Lexeme.c`.
 This lets you shed the Python container, and pass a pointer to the underlying
 data into C-level functions.
 
-## Conventions {#conventions}
+## Conventions {id="conventions"}
 
 spaCy's core data structures are implemented as [Cython](http://cython.org/)
 `cdef` classes. Memory is managed through the

website/docs/api/data-formats.mdx

@@ -14,7 +14,7 @@ vocabulary data. For an overview of label schemes used by the models, see the
 [models directory](/models). Each trained pipeline documents the label schemes
 used in its components, depending on the data it was trained on.
 
-## Training config {#config new="3"}
+## Training config {id="config",version="3"}
 
 Config files define the training process and pipeline and can be passed to
 [`spacy train`](/api/cli#train). They use
@@ -52,7 +52,7 @@ your config and check that it's valid, you can run the
 
 </Infobox>
 
-### nlp {#config-nlp tag="section"}
+### nlp {id="config-nlp",tag="section"}
 
 > #### Example
 >
@@ -83,7 +83,7 @@ Defines the `nlp` object, its tokenizer and
 | `tokenizer`               | The tokenizer to use. Defaults to [`Tokenizer`](/api/tokenizer). ~~Callable[[str], Doc]~~                                                                                                                                                                                                               |
 | `batch_size`              | Default batch size for [`Language.pipe`](/api/language#pipe) and [`Language.evaluate`](/api/language#evaluate). ~~int~~                                                                                                                                                                                 |
 
-### components {#config-components tag="section"}
+### components {id="config-components",tag="section"}
 
 > #### Example
 >
@@ -106,7 +106,7 @@ function to use to create component) or a `source` (name of path of trained
 pipeline to copy components from). See the docs on
 [defining pipeline components](/usage/training#config-components) for details.
 
-### paths, system {#config-variables tag="variables"}
+### paths, system {id="config-variables",tag="variables"}
 
 These sections define variables that can be referenced across the other sections
 as variables. For example `${paths.train}` uses the value of `train` defined in
@@ -116,11 +116,11 @@ need paths, you can define them here. All config values can also be
 [`spacy train`](/api/cli#train), which is especially relevant for data paths
 that you don't want to hard-code in your config file.
 
-```cli
+```bash
 $ python -m spacy train config.cfg --paths.train ./corpus/train.spacy
 ```
 
-### corpora {#config-corpora tag="section"}
+### corpora {id="config-corpora",tag="section"}
 
 > #### Example
 >
@@ -176,7 +176,7 @@ single corpus once and then divide it up into `train` and `dev` partitions.
 | --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
 | `corpora` | A dictionary keyed by string names, mapped to corpus functions that receive the current `nlp` object and return an iterator of [`Example`](/api/example) objects. ~~Dict[str, Callable[[Language], Iterator[Example]]]~~ |
 
-### training {#config-training tag="section"}
+### training {id="config-training",tag="section"}
 
 This section defines settings and controls for the training and evaluation
 process that are used when you run [`spacy train`](/api/cli#train).
@@ -186,7 +186,7 @@ process that are used when you run [`spacy train`](/api/cli#train).
 | `accumulate_gradient`                                | Whether to divide the batch up into substeps. Defaults to `1`. ~~int~~                                                                                                                                                                                                                                                              |
 | `batcher`                                            | Callable that takes an iterator of [`Doc`](/api/doc) objects and yields batches of `Doc`s. Defaults to [`batch_by_words`](/api/top-level#batch_by_words). ~~Callable[[Iterator[Doc], Iterator[List[Doc]]]]~~                                                                                                                        |
 | `before_to_disk`                                     | Optional callback to modify `nlp` object right before it is saved to disk during and after training. Can be used to remove or reset config values or disable components. Defaults to `null`. ~~Optional[Callable[[Language], Language]]~~                                                                                           |
-| `before_update`                                      | Optional callback that is invoked at the start of each training step with the `nlp` object and a `Dict` containing the following entries: `step`, `epoch`. Can be used to make deferred changes to components. Defaults to `null`. ~~Optional[Callable[[Language, Dict[str, Any]], None]]~~                                         |
+| `before_update` <Tag variant="new">3.5</Tag>         | Optional callback that is invoked at the start of each training step with the `nlp` object and a `Dict` containing the following entries: `step`, `epoch`. Can be used to make deferred changes to components. Defaults to `null`. ~~Optional[Callable[[Language, Dict[str, Any]], None]]~~                                         |
 | `dev_corpus`                                         | Dot notation of the config location defining the dev corpus. Defaults to `corpora.dev`. ~~str~~                                                                                                                                                                                                                                     |
 | `dropout`                                            | The dropout rate. Defaults to `0.1`. ~~float~~                                                                                                                                                                                                                                                                                      |
 | `eval_frequency`                                     | How often to evaluate during training (steps). Defaults to `200`. ~~int~~                                                                                                                                                                                                                                                           |
@@ -202,7 +202,7 @@ process that are used when you run [`spacy train`](/api/cli#train).
 | `seed`                                               | The random seed. Defaults to variable `${system.seed}`. ~~int~~                                                                                                                                                                                                                                                                     |
 | `train_corpus`                                       | Dot notation of the config location defining the train corpus. Defaults to `corpora.train`. ~~str~~                                                                                                                                                                                                                                 |
 
-### pretraining {#config-pretraining tag="section,optional"}
+### pretraining {id="config-pretraining",tag="section,optional"}
 
 This section is optional and defines settings and controls for
 [language model pretraining](/usage/embeddings-transformers#pretraining). It's
@@ -220,7 +220,7 @@ used when you run [`spacy pretrain`](/api/cli#pretrain).
 | `component`    | Component name to identify the layer with the model to pretrain. Defaults to `"tok2vec"`. ~~str~~                                                                                                            |
 | `layer`        | The specific layer of the model to pretrain. If empty, the whole model will be used. ~~str~~                                                                                                                 |
 
-### initialize {#config-initialize tag="section"}
+### initialize {id="config-initialize",tag="section"}
 
 This config block lets you define resources for **initializing the pipeline**.
 It's used by [`Language.initialize`](/api/language#initialize) and typically
@@ -255,9 +255,9 @@ Also see the usage guides on the
 | `vectors`      | Name or path of pipeline containing pretrained word vectors to use, e.g. created with [`init vectors`](/api/cli#init-vectors). Defaults to `null`. ~~Optional[str]~~                                                                                                                                                                                                                                           |
 | `vocab_data`   | Path to JSONL-formatted [vocabulary file](/api/data-formats#vocab-jsonl) to initialize vocabulary. ~~Optional[str]~~                                                                                                                                                                                                                                                                                           |
 
-## Training data {#training}
+## Training data {id="training"}
 
-### Binary training format {#binary-training new="3"}
+### Binary training format {id="binary-training",version="3"}
 
 > #### Example
 >
@@ -288,7 +288,7 @@ Note that while this is the format used to save training data, you do not have
 to understand the internal details to use it or create training data. See the
 section on [preparing training data](/usage/training#training-data).
 
-### JSON training format {#json-input tag="deprecated"}
+### JSON training format {id="json-input",tag="deprecated"}
 
 <Infobox variant="warning" title="Changed in v3.0">
 
@@ -300,7 +300,7 @@ objects to JSON, you can now serialize them directly using the
 [`spacy convert`](/api/cli) lets you convert your JSON data to the new `.spacy`
 format:
 
-```cli
+```bash
 $ python -m spacy convert ./data.json .
 ```
 
@@ -317,8 +317,7 @@ $ python -m spacy convert ./data.json .
 > [`offsets_to_biluo_tags`](/api/top-level#offsets_to_biluo_tags) function can
 > help you convert entity offsets to the right format.
 
-```python
+```python {title="Example structure"}
-### Example structure
 [{
     "id": int,                      # ID of the document within the corpus
     "paragraphs": [{                # list of paragraphs in the corpus
@@ -357,7 +356,7 @@ https://github.com/explosion/spaCy/blob/v2.3.x/examples/training/training-data.j
 
 </Accordion>
 
-### Annotation format for creating training examples {#dict-input}
+### Annotation format for creating training examples {id="dict-input"}
 
 An [`Example`](/api/example) object holds the information for one training
 instance. It stores two [`Doc`](/api/doc) objects: one for holding the
@@ -436,8 +435,7 @@ file to keep track of your settings and hyperparameters and your own
 
 </Infobox>
 
-```python
+```python {title="Examples"}
-### Examples
 # Training data for a part-of-speech tagger
 doc = Doc(vocab, words=["I", "like", "stuff"])
 gold_dict = {"tags": ["NOUN", "VERB", "NOUN"]}
@@ -466,7 +464,7 @@ gold_dict = {"entities": [(0, 12, "PERSON")],
 example = Example.from_dict(doc, gold_dict)
 ```
 
-## Lexical data for vocabulary {#vocab-jsonl new="2"}
+## Lexical data for vocabulary {id="vocab-jsonl",version="2"}
 
 This data file can be provided via the `vocab_data` setting in the
 `[initialize]` block of the training config to pre-define the lexical data to
@@ -483,13 +481,11 @@ spaCy's [`Lexeme`](/api/lexeme#attributes) object.
 > vocab_data = "/path/to/vocab-data.jsonl"
 > ```
 
-```python
+```python {title="First line"}
-### First line
 {"lang": "en", "settings": {"oov_prob": -20.502029418945312}}
 ```
 
-```python
+```python {title="Entry structure"}
-### Entry structure
 {
     "orth": string,     # the word text
     "id": int,          # can correspond to row in vectors table
@@ -526,7 +522,7 @@ Here's an example of the 20 most frequent lexemes in the English training data:
 %%GITHUB_SPACY/extra/example_data/vocab-data.jsonl
 ```
 
-## Pipeline meta {#meta}
+## Pipeline meta {id="meta"}
 
 The pipeline meta is available as the file `meta.json` and exported
 automatically when you save an `nlp` object to disk. Its contents are available

website/docs/api/dependencymatcher.mdx

@@ -2,7 +2,7 @@
 title: DependencyMatcher
 teaser: Match subtrees within a dependency parse
 tag: class
-new: 3
+version: 3
 source: spacy/matcher/dependencymatcher.pyx
 ---
 
@@ -14,7 +14,7 @@ It requires a pretrained [`DependencyParser`](/api/parser) or other component
 that sets the `Token.dep` and `Token.head` attributes. See the
 [usage guide](/usage/rule-based-matching#dependencymatcher) for examples.
 
-## Pattern format {#patterns}
+## Pattern format {id="patterns"}
 
 > ```python
 > ### Example
@@ -62,7 +62,7 @@ of relations, see the usage guide on
 
 </Infobox>
 
-### Operators {#operators}
+### Operators {id="operators"}
 
 The following operators are supported by the `DependencyMatcher`, most of which
 come directly from
@@ -87,8 +87,7 @@ come directly from
 | `A <++ B` | `B` is a right parent of `A`, i.e. `A` is a child of `B` and `A.i < B.i` _(not in Semgrex)_.                         |
 | `A <-- B` | `B` is a left parent of `A`, i.e. `A` is a child of `B` and `A.i > B.i` _(not in Semgrex)_.                          |
 
-
+## DependencyMatcher.\_\_init\_\_ {id="init",tag="method"}
-## DependencyMatcher.\_\_init\_\_ {#init tag="method"}
 
 Create a `DependencyMatcher`.
 
@@ -105,7 +104,7 @@ Create a `DependencyMatcher`.
 | _keyword-only_ |                                                                                                       |
 | `validate`     | Validate all patterns added to this matcher. ~~bool~~                                                 |
 
-## DependencyMatcher.\_\call\_\_ {#call tag="method"}
+## DependencyMatcher.\_\_call\_\_ {id="call",tag="method"}
 
 Find all tokens matching the supplied patterns on the `Doc` or `Span`.
 
@@ -127,7 +126,7 @@ Find all tokens matching the supplied patterns on the `Doc` or `Span`.
 | `doclike`   | The `Doc` or `Span` to match over. ~~Union[Doc, Span]~~                                                                                                                                                                                                                                                                               |
 | **RETURNS** | A list of `(match_id, token_ids)` tuples, describing the matches. The `match_id` is the ID of the match pattern and `token_ids` is a list of token indices matched by the pattern, where the position of each token in the list corresponds to the position of the node specification in the pattern. ~~List[Tuple[int, List[int]]]~~ |
 
-## DependencyMatcher.\_\_len\_\_ {#len tag="method"}
+## DependencyMatcher.\_\_len\_\_ {id="len",tag="method"}
 
 Get the number of rules added to the dependency matcher. Note that this only
 returns the number of rules (identical with the number of IDs), not the number
@@ -148,7 +147,7 @@ of individual patterns.
 | ----------- | ---------------------------- |
 | **RETURNS** | The number of rules. ~~int~~ |
 
-## DependencyMatcher.\_\_contains\_\_ {#contains tag="method"}
+## DependencyMatcher.\_\_contains\_\_ {id="contains",tag="method"}
 
 Check whether the matcher contains rules for a match ID.
 
@@ -166,7 +165,7 @@ Check whether the matcher contains rules for a match ID.
 | `key`       | The match ID. ~~str~~                                          |
 | **RETURNS** | Whether the matcher contains rules for this match ID. ~~bool~~ |
 
-## DependencyMatcher.add {#add tag="method"}
+## DependencyMatcher.add {id="add",tag="method"}
 
 Add a rule to the matcher, consisting of an ID key, one or more patterns, and an
 optional callback function to act on the matches. The callback function will
@@ -191,7 +190,7 @@ will be overwritten.
 | _keyword-only_ |                                                                                                                                                                      |
 | `on_match`     | Callback function to act on matches. Takes the arguments `matcher`, `doc`, `i` and `matches`. ~~Optional[Callable[[DependencyMatcher, Doc, int, List[Tuple], Any]]~~ |
 
-## DependencyMatcher.get {#get tag="method"}
+## DependencyMatcher.get {id="get",tag="method"}
 
 Retrieve the pattern stored for a key. Returns the rule as an
 `(on_match, patterns)` tuple containing the callback and available patterns.
@@ -208,7 +207,7 @@ Retrieve the pattern stored for a key. Returns the rule as an
 | `key`       | The ID of the match rule. ~~str~~                                                                           |
 | **RETURNS** | The rule, as an `(on_match, patterns)` tuple. ~~Tuple[Optional[Callable], List[List[Union[Dict, Tuple]]]]~~ |
 
-## DependencyMatcher.remove {#remove tag="method"}
+## DependencyMatcher.remove {id="remove",tag="method"}
 
 Remove a rule from the dependency matcher. A `KeyError` is raised if the match
 ID does not exist.

website/docs/api/dependencyparser.mdx

@@ -25,7 +25,7 @@ current state. The weights are updated such that the scores assigned to the set
 of optimal actions is increased, while scores assigned to other actions are
 decreased. Note that more than one action may be optimal for a given state.
 
-## Assigned Attributes {#assigned-attributes}
+## Assigned Attributes {id="assigned-attributes"}
 
 Dependency predictions are assigned to the `Token.dep` and `Token.head` fields.
 Beside the dependencies themselves, the parser decides sentence boundaries,
@@ -39,7 +39,7 @@ which are saved in `Token.is_sent_start` and accessible via `Doc.sents`.
 | `Token.is_sent_start` | A boolean value indicating whether the token starts a sentence. After the parser runs this will be `True` or `False` for all tokens. ~~bool~~ |
 | `Doc.sents`           | An iterator over sentences in the `Doc`, determined by `Token.is_sent_start` values. ~~Iterator[Span]~~                                       |
 
-## Config and implementation {#config}
+## Config and implementation {id="config"}
 
 The default config is defined by the pipeline component factory and describes
 how the component should be configured. You can override its settings via the
@@ -74,7 +74,7 @@ architectures and their arguments and hyperparameters.
 %%GITHUB_SPACY/spacy/pipeline/dep_parser.pyx
 ```
 
-## DependencyParser.\_\_init\_\_ {#init tag="method"}
+## DependencyParser.\_\_init\_\_ {id="init",tag="method"}
 
 > #### Example
 >
@@ -107,7 +107,7 @@ shortcut for this and instantiate the component using its string name and
 | `min_action_freq`             | The minimum frequency of labelled actions to retain. Rarer labelled actions have their label backed-off to "dep". While this primarily affects the label accuracy, it can also affect the attachment structure, as the labels are used to represent the pseudo-projectivity transformation. ~~int~~ |
 | `scorer`                      | The scoring method. Defaults to [`Scorer.score_deps`](/api/scorer#score_deps) for the attribute `"dep"` ignoring the labels `p` and `punct` and [`Scorer.score_spans`](/api/scorer/#score_spans) for the attribute `"sents"`. ~~Optional[Callable]~~                                                |
 
-## DependencyParser.\_\_call\_\_ {#call tag="method"}
+## DependencyParser.\_\_call\_\_ {id="call",tag="method"}
 
 Apply the pipe to one document. The document is modified in place, and returned.
 This usually happens under the hood when the `nlp` object is called on a text
@@ -131,7 +131,7 @@ and all pipeline components are applied to the `Doc` in order. Both
 | `doc`       | The document to process. ~~Doc~~ |
 | **RETURNS** | The processed document. ~~Doc~~  |
 
-## DependencyParser.pipe {#pipe tag="method"}
+## DependencyParser.pipe {id="pipe",tag="method"}
 
 Apply the pipe to a stream of documents. This usually happens under the hood
 when the `nlp` object is called on a text and all pipeline components are
@@ -155,7 +155,7 @@ applied to the `Doc` in order. Both [`__call__`](/api/dependencyparser#call) and
 | `batch_size`   | The number of documents to buffer. Defaults to `128`. ~~int~~ |
 | **YIELDS**     | The processed documents in order. ~~Doc~~                     |
 
-## DependencyParser.initialize {#initialize tag="method" new="3"}
+## DependencyParser.initialize {id="initialize",tag="method",version="3"}
 
 Initialize the component for training. `get_examples` should be a function that
 returns an iterable of [`Example`](/api/example) objects. **At least one example
@@ -198,7 +198,7 @@ This method was previously called `begin_training`.
 | `nlp`          | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~                                                                                                                                                                                                                                                                                                                                                   |
 | `labels`       | The label information to add to the component, as provided by the [`label_data`](#label_data) property after initialization. To generate a reusable JSON file from your data, you should run the [`init labels`](/api/cli#init-labels) command. If no labels are provided, the `get_examples` callback is used to extract the labels from the data, which may be a lot slower. ~~Optional[Dict[str, Dict[str, int]]]~~ |
 
-## DependencyParser.predict {#predict tag="method"}
+## DependencyParser.predict {id="predict",tag="method"}
 
 Apply the component's model to a batch of [`Doc`](/api/doc) objects, without
 modifying them.
@@ -215,7 +215,7 @@ modifying them.
 | `docs`      | The documents to predict. ~~Iterable[Doc]~~                   |
 | **RETURNS** | A helper class for the parse state (internal). ~~StateClass~~ |
 
-## DependencyParser.set_annotations {#set_annotations tag="method"}
+## DependencyParser.set_annotations {id="set_annotations",tag="method"}
 
 Modify a batch of [`Doc`](/api/doc) objects, using pre-computed scores.
 
@@ -232,7 +232,7 @@ Modify a batch of [`Doc`](/api/doc) objects, using pre-computed scores.
 | `docs`   | The documents to modify. ~~Iterable[Doc]~~                                                                                            |
 | `scores` | The scores to set, produced by `DependencyParser.predict`. Returns an internal helper class for the parse state. ~~List[StateClass]~~ |
 
-## DependencyParser.update {#update tag="method"}
+## DependencyParser.update {id="update",tag="method"}
 
 Learn from a batch of [`Example`](/api/example) objects, updating the pipe's
 model. Delegates to [`predict`](/api/dependencyparser#predict) and
@@ -255,7 +255,7 @@ model. Delegates to [`predict`](/api/dependencyparser#predict) and
 | `losses`       | Optional record of the loss during training. Updated using the component name as the key. ~~Optional[Dict[str, float]]~~ |
 | **RETURNS**    | The updated `losses` dictionary. ~~Dict[str, float]~~                                                                    |
 
-## DependencyParser.get_loss {#get_loss tag="method"}
+## DependencyParser.get_loss {id="get_loss",tag="method"}
 
 Find the loss and gradient of loss for the batch of documents and their
 predicted scores.
@@ -274,7 +274,7 @@ predicted scores.
 | `scores`    | Scores representing the model's predictions. ~~StateClass~~                 |
 | **RETURNS** | The loss and the gradient, i.e. `(loss, gradient)`. ~~Tuple[float, float]~~ |
 
-## DependencyParser.create_optimizer {#create_optimizer tag="method"}
+## DependencyParser.create_optimizer {id="create_optimizer",tag="method"}
 
 Create an [`Optimizer`](https://thinc.ai/docs/api-optimizers) for the pipeline
 component.
@@ -290,7 +290,7 @@ component.
 | ----------- | ---------------------------- |
 | **RETURNS** | The optimizer. ~~Optimizer~~ |
 
-## DependencyParser.use_params {#use_params tag="method, contextmanager"}
+## DependencyParser.use_params {id="use_params",tag="method, contextmanager"}
 
 Modify the pipe's model, to use the given parameter values. At the end of the
 context, the original parameters are restored.
@@ -307,7 +307,7 @@ context, the original parameters are restored.
 | -------- | -------------------------------------------------- |
 | `params` | The parameter values to use in the model. ~~dict~~ |
 
-## DependencyParser.add_label {#add_label tag="method"}
+## DependencyParser.add_label {id="add_label",tag="method"}
 
 Add a new label to the pipe. Note that you don't have to call this method if you
 provide a **representative data sample** to the [`initialize`](#initialize)
@@ -327,7 +327,7 @@ to the model, and the output dimension will be
 | `label`     | The label to add. ~~str~~                                   |
 | **RETURNS** | `0` if the label is already present, otherwise `1`. ~~int~~ |
 
-## DependencyParser.set_output {#set_output tag="method"}
+## DependencyParser.set_output {id="set_output",tag="method"}
 
 Change the output dimension of the component's model by calling the model's
 attribute `resize_output`. This is a function that takes the original model and
@@ -346,7 +346,7 @@ forgetting" problem.
 | ---- | --------------------------------- |
 | `nO` | The new output dimension. ~~int~~ |
 
-## DependencyParser.to_disk {#to_disk tag="method"}
+## DependencyParser.to_disk {id="to_disk",tag="method"}
 
 Serialize the pipe to disk.
 
@@ -363,7 +363,7 @@ Serialize the pipe to disk.
 | _keyword-only_ |                                                                                                                                            |
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~                                                |
 
-## DependencyParser.from_disk {#from_disk tag="method"}
+## DependencyParser.from_disk {id="from_disk",tag="method"}
 
 Load the pipe from disk. Modifies the object in place and returns it.
 
@@ -381,7 +381,7 @@ Load the pipe from disk. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~     |
 | **RETURNS**    | The modified `DependencyParser` object. ~~DependencyParser~~                                    |
 
-## DependencyParser.to_bytes {#to_bytes tag="method"}
+## DependencyParser.to_bytes {id="to_bytes",tag="method"}
 
 > #### Example
 >
@@ -398,7 +398,7 @@ Serialize the pipe to a bytestring.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The serialized form of the `DependencyParser` object. ~~bytes~~                             |
 
-## DependencyParser.from_bytes {#from_bytes tag="method"}
+## DependencyParser.from_bytes {id="from_bytes",tag="method"}
 
 Load the pipe from a bytestring. Modifies the object in place and returns it.
 
@@ -417,7 +417,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The `DependencyParser` object. ~~DependencyParser~~                                         |
 
-## DependencyParser.labels {#labels tag="property"}
+## DependencyParser.labels {id="labels",tag="property"}
 
 The labels currently added to the component.
 
@@ -432,7 +432,7 @@ The labels currently added to the component.
 | ----------- | ------------------------------------------------------ |
 | **RETURNS** | The labels added to the component. ~~Tuple[str, ...]~~ |
 
-## DependencyParser.label_data {#label_data tag="property" new="3"}
+## DependencyParser.label_data {id="label_data",tag="property",version="3"}
 
 The labels currently added to the component and their internal meta information.
 This is the data generated by [`init labels`](/api/cli#init-labels) and used by
@@ -450,7 +450,7 @@ the model with a pre-defined label set.
 | ----------- | ------------------------------------------------------------------------------- |
 | **RETURNS** | The label data added to the component. ~~Dict[str, Dict[str, Dict[str, int]]]~~ |
 
-## Serialization fields {#serialization-fields}
+## Serialization fields {id="serialization-fields"}
 
 During serialization, spaCy will export several data fields used to restore
 different aspects of the object. If needed, you can exclude them from

website/docs/api/doc.mdx

@@ -12,7 +12,7 @@ compressed binary strings. The `Doc` object holds an array of
 [`Span`](/api/span) objects are views of this array, i.e. they don't own the
 data themselves.
 
-## Doc.\_\_init\_\_ {#init tag="method"}
+## Doc.\_\_init\_\_ {id="init",tag="method"}
 
 Construct a `Doc` object. The most common way to get a `Doc` object is via the
 `nlp` object.
@@ -47,7 +47,7 @@ Construct a `Doc` object. The most common way to get a `Doc` object is via the
 | `sent_starts` <Tag variant="new">3</Tag> | A list of values, of the same length as `words`, to assign as `token.is_sent_start`. Will be overridden by heads if `heads` is provided. Defaults to `None`. ~~Optional[List[Union[bool, int, None]]]~~ |
 | `ents` <Tag variant="new">3</Tag>        | A list of strings, of the same length of `words`, to assign the token-based IOB tag. Defaults to `None`. ~~Optional[List[str]]~~                                                                        |
 
-## Doc.\_\_getitem\_\_ {#getitem tag="method"}
+## Doc.\_\_getitem\_\_ {id="getitem",tag="method"}
 
 Get a [`Token`](/api/token) object at position `i`, where `i` is an integer.
 Negative indexing is supported, and follows the usual Python semantics, i.e.
@@ -80,7 +80,7 @@ semantics.
 | `start_end` | The slice of the document to get. ~~Tuple[int, int]~~ |
 | **RETURNS** | The span at `doc[start:end]`. ~~Span~~                |
 
-## Doc.\_\_iter\_\_ {#iter tag="method"}
+## Doc.\_\_iter\_\_ {id="iter",tag="method"}
 
 Iterate over `Token` objects, from which the annotations can be easily accessed.
 
@@ -100,7 +100,7 @@ underlying C data directly from Cython.
 | ---------- | --------------------------- |
 | **YIELDS** | A `Token` object. ~~Token~~ |
 
-## Doc.\_\_len\_\_ {#len tag="method"}
+## Doc.\_\_len\_\_ {id="len",tag="method"}
 
 Get the number of tokens in the document.
 
@@ -115,7 +115,7 @@ Get the number of tokens in the document.
 | ----------- | --------------------------------------------- |
 | **RETURNS** | The number of tokens in the document. ~~int~~ |
 
-## Doc.set_extension {#set_extension tag="classmethod" new="2"}
+## Doc.set_extension {id="set_extension",tag="classmethod",version="2"}
 
 Define a custom attribute on the `Doc` which becomes available via `Doc._`. For
 details, see the documentation on
@@ -140,7 +140,7 @@ details, see the documentation on
 | `setter`  | Setter function that takes the `Doc` and a value, and modifies the object. Is called when the user writes to the `Doc._` attribute. ~~Optional[Callable[[Doc, Any], None]]~~ |
 | `force`   | Force overwriting existing attribute. ~~bool~~                                                                                                                               |
 
-## Doc.get_extension {#get_extension tag="classmethod" new="2"}
+## Doc.get_extension {id="get_extension",tag="classmethod",version="2"}
 
 Look up a previously registered extension by name. Returns a 4-tuple
 `(default, method, getter, setter)` if the extension is registered. Raises a
@@ -160,7 +160,7 @@ Look up a previously registered extension by name. Returns a 4-tuple
 | `name`      | Name of the extension. ~~str~~                                                                                                                     |
 | **RETURNS** | A `(default, method, getter, setter)` tuple of the extension. ~~Tuple[Optional[Any], Optional[Callable], Optional[Callable], Optional[Callable]]~~ |
 
-## Doc.has_extension {#has_extension tag="classmethod" new="2"}
+## Doc.has_extension {id="has_extension",tag="classmethod",version="2"}
 
 Check whether an extension has been registered on the `Doc` class.
 
@@ -177,7 +177,7 @@ Check whether an extension has been registered on the `Doc` class.
 | `name`      | Name of the extension to check. ~~str~~             |
 | **RETURNS** | Whether the extension has been registered. ~~bool~~ |
 
-## Doc.remove_extension {#remove_extension tag="classmethod" new="2.0.12"}
+## Doc.remove_extension {id="remove_extension",tag="classmethod",version="2.0.12"}
 
 Remove a previously registered extension.
 
@@ -195,7 +195,7 @@ Remove a previously registered extension.
 | `name`      | Name of the extension. ~~str~~                                                                                                                             |
 | **RETURNS** | A `(default, method, getter, setter)` tuple of the removed extension. ~~Tuple[Optional[Any], Optional[Callable], Optional[Callable], Optional[Callable]]~~ |
 
-## Doc.char_span {#char_span tag="method" new="2"}
+## Doc.char_span {id="char_span",tag="method",version="2"}
 
 Create a `Span` object from the slice `doc.text[start_idx:end_idx]`. Returns
 `None` if the character indices don't map to a valid span using the default
@@ -219,7 +219,7 @@ alignment mode `"strict".
 | `alignment_mode` | How character indices snap to token boundaries. Options: `"strict"` (no snapping), `"contract"` (span of all tokens completely within the character span), `"expand"` (span of all tokens at least partially covered by the character span). Defaults to `"strict"`. ~~str~~ |
 | **RETURNS**      | The newly constructed object or `None`. ~~Optional[Span]~~                                                                                                                                                                                                                   |
 
-## Doc.set_ents {#set_ents tag="method" new="3"}
+## Doc.set_ents {id="set_ents",tag="method",version="3"}
 
 Set the named entities in the document.
 
@@ -243,7 +243,7 @@ Set the named entities in the document.
 | `outside`      | Spans outside of entities (O in IOB). ~~Optional[List[Span]]~~                                                                                                                                      |
 | `default`      | How to set entity annotation for tokens outside of any provided spans. Options: `"blocked"`, `"missing"`, `"outside"` and `"unmodified"` (preserve current state). Defaults to `"outside"`. ~~str~~ |
 
-## Doc.similarity {#similarity tag="method" model="vectors"}
+## Doc.similarity {id="similarity",tag="method",model="vectors"}
 
 Make a semantic similarity estimate. The default estimate is cosine similarity
 using an average of word vectors.
@@ -263,7 +263,7 @@ using an average of word vectors.
 | `other`     | The object to compare with. By default, accepts `Doc`, `Span`, `Token` and `Lexeme` objects. ~~Union[Doc, Span, Token, Lexeme]~~ |
 | **RETURNS** | A scalar similarity score. Higher is more similar. ~~float~~                                                                     |
 
-## Doc.count_by {#count_by tag="method"}
+## Doc.count_by {id="count_by",tag="method"}
 
 Count the frequencies of a given attribute. Produces a dict of
 `{attr (int): count (ints)}` frequencies, keyed by the values of the given
@@ -284,7 +284,7 @@ attribute ID.
 | `attr_id`   | The attribute ID. ~~int~~                                             |
 | **RETURNS** | A dictionary mapping attributes to integer counts. ~~Dict[int, int]~~ |
 
-## Doc.get_lca_matrix {#get_lca_matrix tag="method"}
+## Doc.get_lca_matrix {id="get_lca_matrix",tag="method"}
 
 Calculates the lowest common ancestor matrix for a given `Doc`. Returns LCA
 matrix containing the integer index of the ancestor, or `-1` if no common
@@ -302,7 +302,7 @@ ancestor is found, e.g. if span excludes a necessary ancestor.
 | ----------- | -------------------------------------------------------------------------------------- |
 | **RETURNS** | The lowest common ancestor matrix of the `Doc`. ~~numpy.ndarray[ndim=2, dtype=int32]~~ |
 
-## Doc.has_annotation {#has_annotation tag="method"}
+## Doc.has_annotation {id="has_annotation",tag="method"}
 
 Check whether the doc contains annotation on a
 [`Token` attribute](/api/token#attributes).
@@ -327,7 +327,7 @@ doc = nlp("This is a text")
 | `require_complete` | Whether to check that the attribute is set on every token in the doc. Defaults to `False`. ~~bool~~ |
 | **RETURNS**        | Whether specified annotation is present in the doc. ~~bool~~                                        |
 
-## Doc.to_array {#to_array tag="method"}
+## Doc.to_array {id="to_array",tag="method"}
 
 Export given token attributes to a numpy `ndarray`. If `attr_ids` is a sequence
 of `M` attributes, the output array will be of shape `(N, M)`, where `N` is the
@@ -355,7 +355,7 @@ Returns a 2D array with one row per token and one column per attribute (when
 | `attr_ids`  | A list of attributes (int IDs or string names) or a single attribute (int ID or string name). ~~Union[int, str, List[Union[int, str]]]~~ |
 | **RETURNS** | The exported attributes as a numpy array. ~~Union[numpy.ndarray[ndim=2, dtype=uint64], numpy.ndarray[ndim=1, dtype=uint64]]~~            |
 
-## Doc.from_array {#from_array tag="method"}
+## Doc.from_array {id="from_array",tag="method"}
 
 Load attributes from a numpy array. Write to a `Doc` object, from an `(M, N)`
 array of attributes.
@@ -379,7 +379,7 @@ array of attributes.
 | `exclude`   | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS** | The `Doc` itself. ~~Doc~~                                                                   |
 
-## Doc.from_docs {#from_docs tag="staticmethod" new="3"}
+## Doc.from_docs {id="from_docs",tag="staticmethod",version="3"}
 
 Concatenate multiple `Doc` objects to form a new one. Raises an error if the
 `Doc` objects do not all share the same `Vocab`.
@@ -408,7 +408,7 @@ Concatenate multiple `Doc` objects to form a new one. Raises an error if the
 | `exclude` <Tag variant="new">3.3</Tag> | String names of Doc attributes to exclude. Supported: `spans`, `tensor`, `user_data`. ~~Iterable[str]~~           |
 | **RETURNS**                            | The new `Doc` object that is containing the other docs or `None`, if `docs` is empty or `None`. ~~Optional[Doc]~~ |
 
-## Doc.to_disk {#to_disk tag="method" new="2"}
+## Doc.to_disk {id="to_disk",tag="method",version="2"}
 
 Save the current state to a directory.
 
@@ -424,7 +424,7 @@ Save the current state to a directory.
 | _keyword-only_ |                                                                                                                                            |
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~                                                |
 
-## Doc.from_disk {#from_disk tag="method" new="2"}
+## Doc.from_disk {id="from_disk",tag="method",version="2"}
 
 Loads state from a directory. Modifies the object in place and returns it.
 
@@ -443,7 +443,7 @@ Loads state from a directory. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~     |
 | **RETURNS**    | The modified `Doc` object. ~~Doc~~                                                              |
 
-## Doc.to_bytes {#to_bytes tag="method"}
+## Doc.to_bytes {id="to_bytes",tag="method"}
 
 Serialize, i.e. export the document contents to a binary string.
 
@@ -460,7 +460,7 @@ Serialize, i.e. export the document contents to a binary string.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | A losslessly serialized copy of the `Doc`, including all annotations. ~~bytes~~             |
 
-## Doc.from_bytes {#from_bytes tag="method"}
+## Doc.from_bytes {id="from_bytes",tag="method"}
 
 Deserialize, i.e. import the document contents from a binary string.
 
@@ -481,7 +481,7 @@ Deserialize, i.e. import the document contents from a binary string.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The `Doc` object. ~~Doc~~                                                                   |
 
-## Doc.to_json {#to_json tag="method"}
+## Doc.to_json {id="to_json",tag="method"}
 
 Serializes a document to JSON. Note that this is format differs from the
 deprecated [`JSON training format`](/api/data-formats#json-input).
@@ -498,7 +498,7 @@ deprecated [`JSON training format`](/api/data-formats#json-input).
 | `underscore` | Optional list of string names of custom `Doc` attributes. Attribute values need to be JSON-serializable. Values will be added to an `"_"` key in the data, e.g. `"_": {"foo": "bar"}`. ~~Optional[List[str]]~~ |
 | **RETURNS**  | The data in JSON format. ~~Dict[str, Any]~~                                                                                                                                                                    |
 
-## Doc.from_json {#from_json tag="method" new="3.3.1"}
+## Doc.from_json {id="from_json",tag="method",version="3.3.1"}
 
 Deserializes a document from JSON, i.e. generates a document from the provided
 JSON data as generated by [`Doc.to_json()`](/api/doc#to_json).
@@ -520,7 +520,7 @@ JSON data as generated by [`Doc.to_json()`](/api/doc#to_json).
 | `validate`     | Whether to validate the JSON input against the expected schema for detailed debugging. Defaults to `False`. ~~bool~~ |
 | **RETURNS**    | A `Doc` corresponding to the provided JSON. ~~Doc~~                                                                  |
 
-## Doc.retokenize {#retokenize tag="contextmanager" new="2.1"}
+## Doc.retokenize {id="retokenize",tag="contextmanager",version="2.1"}
 
 Context manager to handle retokenization of the `Doc`. Modifications to the
 `Doc`'s tokenization are stored, and then made all at once when the context
@@ -540,7 +540,7 @@ invalidated, although they may accidentally continue to work.
 | ----------- | -------------------------------- |
 | **RETURNS** | The retokenizer. ~~Retokenizer~~ |
 
-### Retokenizer.merge {#retokenizer.merge tag="method"}
+### Retokenizer.merge {id="retokenizer.merge",tag="method"}
 
 Mark a span for merging. The `attrs` will be applied to the resulting token (if
 they're context-dependent token attributes like `LEMMA` or `DEP`) or to the
@@ -563,7 +563,7 @@ values.
 | `span`  | The span to merge. ~~Span~~                                           |
 | `attrs` | Attributes to set on the merged token. ~~Dict[Union[str, int], Any]~~ |
 
-### Retokenizer.split {#retokenizer.split tag="method"}
+### Retokenizer.split {id="retokenizer.split",tag="method"}
 
 Mark a token for splitting, into the specified `orths`. The `heads` are required
 to specify how the new subtokens should be integrated into the dependency tree.
@@ -599,7 +599,7 @@ underlying lexeme (if they're context-independent lexical attributes like
 | `heads` | List of `token` or `(token, subtoken)` tuples specifying the tokens to attach the newly split subtokens to. ~~List[Union[Token, Tuple[Token, int]]]~~ |
 | `attrs` | Attributes to set on all split tokens. Attribute names mapped to list of per-token attribute values. ~~Dict[Union[str, int], List[Any]]~~             |
 
-## Doc.ents {#ents tag="property" model="NER"}
+## Doc.ents {id="ents",tag="property",model="NER"}
 
 The named entities in the document. Returns a tuple of named entity `Span`
 objects, if the entity recognizer has been applied.
@@ -617,7 +617,7 @@ objects, if the entity recognizer has been applied.
 | ----------- | ---------------------------------------------------------------- |
 | **RETURNS** | Entities in the document, one `Span` per entity. ~~Tuple[Span]~~ |
 
-## Doc.spans {#spans tag="property"}
+## Doc.spans {id="spans",tag="property"}
 
 A dictionary of named span groups, to store and access additional span
 annotations. You can write to it by assigning a list of [`Span`](/api/span)
@@ -634,7 +634,7 @@ objects or a [`SpanGroup`](/api/spangroup) to a given key.
 | ----------- | ------------------------------------------------------------------ |
 | **RETURNS** | The span groups assigned to the document. ~~Dict[str, SpanGroup]~~ |
 
-## Doc.cats {#cats tag="property" model="text classifier"}
+## Doc.cats {id="cats",tag="property",model="text classifier"}
 
 Maps a label to a score for categories applied to the document. Typically set by
 the [`TextCategorizer`](/api/textcategorizer).
@@ -650,7 +650,7 @@ the [`TextCategorizer`](/api/textcategorizer).
 | ----------- | ---------------------------------------------------------- |
 | **RETURNS** | The text categories mapped to scores. ~~Dict[str, float]~~ |
 
-## Doc.noun_chunks {#noun_chunks tag="property" model="parser"}
+## Doc.noun_chunks {id="noun_chunks",tag="property",model="parser"}
 
 Iterate over the base noun phrases in the document. Yields base noun-phrase
 `Span` objects, if the document has been syntactically parsed. A base noun
@@ -677,7 +677,7 @@ implemented for the given language, a `NotImplementedError` is raised.
 | ---------- | ------------------------------------- |
 | **YIELDS** | Noun chunks in the document. ~~Span~~ |
 
-## Doc.sents {#sents tag="property" model="sentences"}
+## Doc.sents {id="sents",tag="property",model="sentences"}
 
 Iterate over the sentences in the document. Sentence spans have no label.
 
@@ -699,7 +699,7 @@ will raise an error otherwise.
 | ---------- | ----------------------------------- |
 | **YIELDS** | Sentences in the document. ~~Span~~ |
 
-## Doc.has_vector {#has_vector tag="property" model="vectors"}
+## Doc.has_vector {id="has_vector",tag="property",model="vectors"}
 
 A boolean value indicating whether a word vector is associated with the object.
 
@@ -714,7 +714,7 @@ A boolean value indicating whether a word vector is associated with the object.
 | ----------- | --------------------------------------------------------- |
 | **RETURNS** | Whether the document has a vector data attached. ~~bool~~ |
 
-## Doc.vector {#vector tag="property" model="vectors"}
+## Doc.vector {id="vector",tag="property",model="vectors"}
 
 A real-valued meaning representation. Defaults to an average of the token
 vectors.
@@ -731,7 +731,7 @@ vectors.
 | ----------- | -------------------------------------------------------------------------------------------------- |
 | **RETURNS** | A 1-dimensional array representing the document's vector. ~~numpy.ndarray[ndim=1, dtype=float32]~~ |
 
-## Doc.vector_norm {#vector_norm tag="property" model="vectors"}
+## Doc.vector_norm {id="vector_norm",tag="property",model="vectors"}
 
 The L2 norm of the document's vector representation.
 
@@ -749,7 +749,7 @@ The L2 norm of the document's vector representation.
 | ----------- | --------------------------------------------------- |
 | **RETURNS** | The L2 norm of the vector representation. ~~float~~ |
 
-## Attributes {#attributes}
+## Attributes {id="attributes"}
 
 | Name                 | Description                                                                                                                         |
 | -------------------- | ----------------------------------------------------------------------------------------------------------------------------------- |
@@ -768,7 +768,7 @@ The L2 norm of the document's vector representation.
 | `has_unknown_spaces` | Whether the document was constructed without known spacing between tokens (typically when created from gold tokenization). ~~bool~~ |
 | `_`                  | User space for adding custom [attribute extensions](/usage/processing-pipelines#custom-components-attributes). ~~Underscore~~       |
 
-## Serialization fields {#serialization-fields}
+## Serialization fields {id="serialization-fields"}
 
 During serialization, spaCy will export several data fields used to restore
 different aspects of the object. If needed, you can exclude them from

website/docs/api/docbin.mdx

@@ -1,7 +1,7 @@
 ---
 title: DocBin
 tag: class
-new: 2.2
+version: 2.2
 teaser: Pack Doc objects for binary serialization
 source: spacy/tokens/_serialize.py
 ---
@@ -15,8 +15,7 @@ notable downside to this format is that you can't easily extract just one
 document from the `DocBin`. The serialization format is gzipped msgpack, where
 the msgpack object has the following structure:
 
-```python
+```python {title="msgpack object structure"}
-### msgpack object structure
 {
     "version": str,           # DocBin version number
     "attrs": List[uint64],    # e.g. [TAG, HEAD, ENT_IOB, ENT_TYPE]
@@ -33,7 +32,7 @@ object. This means the storage is more efficient if you pack more documents
 together, because you have less duplication in the strings. For usage examples,
 see the docs on [serializing `Doc` objects](/usage/saving-loading#docs).
 
-## DocBin.\_\_init\_\_ {#init tag="method"}
+## DocBin.\_\_init\_\_ {id="init",tag="method"}
 
 Create a `DocBin` object to hold serialized annotations.
 
@@ -50,7 +49,7 @@ Create a `DocBin` object to hold serialized annotations.
 | `store_user_data` | Whether to write the `Doc.user_data` and the values of custom extension attributes to file/bytes. Defaults to `False`. ~~bool~~                                                                                                                                                                     |
 | `docs`            | `Doc` objects to add on initialization. ~~Iterable[Doc]~~                                                                                                                                                                                                                                           |
 
-## DocBin.\_\len\_\_ {#len tag="method"}
+## DocBin.\_\_len\_\_ {id="len",tag="method"}
 
 Get the number of `Doc` objects that were added to the `DocBin`.
 
@@ -67,7 +66,7 @@ Get the number of `Doc` objects that were added to the `DocBin`.
 | ----------- | --------------------------------------------------- |
 | **RETURNS** | The number of `Doc`s added to the `DocBin`. ~~int~~ |
 
-## DocBin.add {#add tag="method"}
+## DocBin.add {id="add",tag="method"}
 
 Add a `Doc`'s annotations to the `DocBin` for serialization.
 
@@ -83,7 +82,7 @@ Add a `Doc`'s annotations to the `DocBin` for serialization.
 | -------- | -------------------------------- |
 | `doc`    | The `Doc` object to add. ~~Doc~~ |
 
-## DocBin.get_docs {#get_docs tag="method"}
+## DocBin.get_docs {id="get_docs",tag="method"}
 
 Recover `Doc` objects from the annotations, using the given vocab.
 
@@ -98,7 +97,7 @@ Recover `Doc` objects from the annotations, using the given vocab.
 | `vocab`    | The shared vocab. ~~Vocab~~ |
 | **YIELDS** | The `Doc` objects. ~~Doc~~  |
 
-## DocBin.merge {#merge tag="method"}
+## DocBin.merge {id="merge",tag="method"}
 
 Extend the annotations of this `DocBin` with the annotations from another. Will
 raise an error if the pre-defined `attrs` of the two `DocBin`s don't match.
@@ -118,7 +117,7 @@ raise an error if the pre-defined `attrs` of the two `DocBin`s don't match.
 | -------- | ------------------------------------------------------ |
 | `other`  | The `DocBin` to merge into the current bin. ~~DocBin~~ |
 
-## DocBin.to_bytes {#to_bytes tag="method"}
+## DocBin.to_bytes {id="to_bytes",tag="method"}
 
 Serialize the `DocBin`'s annotations to a bytestring.
 
@@ -134,7 +133,7 @@ Serialize the `DocBin`'s annotations to a bytestring.
 | ----------- | ---------------------------------- |
 | **RETURNS** | The serialized `DocBin`. ~~bytes~~ |
 
-## DocBin.from_bytes {#from_bytes tag="method"}
+## DocBin.from_bytes {id="from_bytes",tag="method"}
 
 Deserialize the `DocBin`'s annotations from a bytestring.
 
@@ -150,7 +149,7 @@ Deserialize the `DocBin`'s annotations from a bytestring.
 | `bytes_data` | The data to load from. ~~bytes~~ |
 | **RETURNS**  | The loaded `DocBin`. ~~DocBin~~  |
 
-## DocBin.to_disk {#to_disk tag="method" new="3"}
+## DocBin.to_disk {id="to_disk",tag="method",version="3"}
 
 Save the serialized `DocBin` to a file. Typically uses the `.spacy` extension
 and the result can be used as the input data for
@@ -168,7 +167,7 @@ and the result can be used as the input data for
 | -------- | -------------------------------------------------------------------------- |
 | `path`   | The file path, typically with the `.spacy` extension. ~~Union[str, Path]~~ |
 
-## DocBin.from_disk {#from_disk tag="method" new="3"}
+## DocBin.from_disk {id="from_disk",tag="method",version="3"}
 
 Load a serialized `DocBin` from a file. Typically uses the `.spacy` extension.
 

website/docs/api/edittreelemmatizer.mdx

@@ -2,7 +2,7 @@
 title: EditTreeLemmatizer
 tag: class
 source: spacy/pipeline/edit_tree_lemmatizer.py
-new: 3.3
+version: 3.3
 teaser: 'Pipeline component for lemmatization'
 api_base_class: /api/pipe
 api_string_name: trainable_lemmatizer
@@ -18,7 +18,7 @@ and construction method used by this lemmatizer were proposed in
 
 For a lookup and rule-based lemmatizer, see [`Lemmatizer`](/api/lemmatizer).
 
-## Assigned Attributes {#assigned-attributes}
+## Assigned Attributes {id="assigned-attributes"}
 
 Predictions are assigned to `Token.lemma`.
 
@@ -27,7 +27,7 @@ Predictions are assigned to `Token.lemma`.
 | `Token.lemma`  | The lemma (hash). ~~int~~ |
 | `Token.lemma_` | The lemma. ~~str~~        |
 
-## Config and implementation {#config}
+## Config and implementation {id="config"}
 
 The default config is defined by the pipeline component factory and describes
 how the component should be configured. You can override its settings via the
@@ -57,7 +57,7 @@ architectures and their arguments and hyperparameters.
 %%GITHUB_SPACY/spacy/pipeline/edit_tree_lemmatizer.py
 ```
 
-## EditTreeLemmatizer.\_\_init\_\_ {#init tag="method"}
+## EditTreeLemmatizer.\_\_init\_\_ {id="init",tag="method"}
 
 > #### Example
 >
@@ -90,7 +90,7 @@ shortcut for this and instantiate the component using its string name and
 | `top_k`         | The number of most probable edit trees to try before resorting to `backoff`. Defaults to `1`. ~~int~~                                                                                                                                                             |
 | `scorer`        | The scoring method. Defaults to [`Scorer.score_token_attr`](/api/scorer#score_token_attr) for the attribute `"lemma"`. ~~Optional[Callable]~~                                                                                                                     |
 
-## EditTreeLemmatizer.\_\_call\_\_ {#call tag="method"}
+## EditTreeLemmatizer.\_\_call\_\_ {id="call",tag="method"}
 
 Apply the pipe to one document. The document is modified in place, and returned.
 This usually happens under the hood when the `nlp` object is called on a text
@@ -114,7 +114,7 @@ and all pipeline components are applied to the `Doc` in order. Both
 | `doc`       | The document to process. ~~Doc~~ |
 | **RETURNS** | The processed document. ~~Doc~~  |
 
-## EditTreeLemmatizer.pipe {#pipe tag="method"}
+## EditTreeLemmatizer.pipe {id="pipe",tag="method"}
 
 Apply the pipe to a stream of documents. This usually happens under the hood
 when the `nlp` object is called on a text and all pipeline components are
@@ -138,7 +138,7 @@ and [`pipe`](/api/edittreelemmatizer#pipe) delegate to the
 | `batch_size`   | The number of documents to buffer. Defaults to `128`. ~~int~~ |
 | **YIELDS**     | The processed documents in order. ~~Doc~~                     |
 
-## EditTreeLemmatizer.initialize {#initialize tag="method" new="3"}
+## EditTreeLemmatizer.initialize {id="initialize",tag="method",version="3"}
 
 Initialize the component for training. `get_examples` should be a function that
 returns an iterable of [`Example`](/api/example) objects. **At least one example
@@ -175,7 +175,7 @@ config.
 | `nlp`          | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~                                                                                                                                                                                                                                                                                                                                       |
 | `labels`       | The label information to add to the component, as provided by the [`label_data`](#label_data) property after initialization. To generate a reusable JSON file from your data, you should run the [`init labels`](/api/cli#init-labels) command. If no labels are provided, the `get_examples` callback is used to extract the labels from the data, which may be a lot slower. ~~Optional[Iterable[str]]~~ |
 
-## EditTreeLemmatizer.predict {#predict tag="method"}
+## EditTreeLemmatizer.predict {id="predict",tag="method"}
 
 Apply the component's model to a batch of [`Doc`](/api/doc) objects, without
 modifying them.
@@ -192,7 +192,7 @@ modifying them.
 | `docs`      | The documents to predict. ~~Iterable[Doc]~~ |
 | **RETURNS** | The model's prediction for each document.   |
 
-## EditTreeLemmatizer.set_annotations {#set_annotations tag="method"}
+## EditTreeLemmatizer.set_annotations {id="set_annotations",tag="method"}
 
 Modify a batch of [`Doc`](/api/doc) objects, using pre-computed tree
 identifiers.
@@ -210,7 +210,7 @@ identifiers.
 | `docs`     | The documents to modify. ~~Iterable[Doc]~~                                            |
 | `tree_ids` | The identifiers of the edit trees to apply, produced by `EditTreeLemmatizer.predict`. |
 
-## EditTreeLemmatizer.update {#update tag="method"}
+## EditTreeLemmatizer.update {id="update",tag="method"}
 
 Learn from a batch of [`Example`](/api/example) objects containing the
 predictions and gold-standard annotations, and update the component's model.
@@ -234,7 +234,7 @@ Delegates to [`predict`](/api/edittreelemmatizer#predict) and
 | `losses`       | Optional record of the loss during training. Updated using the component name as the key. ~~Optional[Dict[str, float]]~~ |
 | **RETURNS**    | The updated `losses` dictionary. ~~Dict[str, float]~~                                                                    |
 
-## EditTreeLemmatizer.get_loss {#get_loss tag="method"}
+## EditTreeLemmatizer.get_loss {id="get_loss",tag="method"}
 
 Find the loss and gradient of loss for the batch of documents and their
 predicted scores.
@@ -253,7 +253,7 @@ predicted scores.
 | `scores`    | Scores representing the model's predictions.                                |
 | **RETURNS** | The loss and the gradient, i.e. `(loss, gradient)`. ~~Tuple[float, float]~~ |
 
-## EditTreeLemmatizer.create_optimizer {#create_optimizer tag="method"}
+## EditTreeLemmatizer.create_optimizer {id="create_optimizer",tag="method"}
 
 Create an optimizer for the pipeline component.
 
@@ -268,7 +268,7 @@ Create an optimizer for the pipeline component.
 | ----------- | ---------------------------- |
 | **RETURNS** | The optimizer. ~~Optimizer~~ |
 
-## EditTreeLemmatizer.use_params {#use_params tag="method, contextmanager"}
+## EditTreeLemmatizer.use_params {id="use_params",tag="method, contextmanager"}
 
 Modify the pipe's model, to use the given parameter values. At the end of the
 context, the original parameters are restored.
@@ -285,7 +285,7 @@ context, the original parameters are restored.
 | -------- | -------------------------------------------------- |
 | `params` | The parameter values to use in the model. ~~dict~~ |
 
-## EditTreeLemmatizer.to_disk {#to_disk tag="method"}
+## EditTreeLemmatizer.to_disk {id="to_disk",tag="method"}
 
 Serialize the pipe to disk.
 
@@ -302,7 +302,7 @@ Serialize the pipe to disk.
 | _keyword-only_ |                                                                                                                                            |
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~                                                |
 
-## EditTreeLemmatizer.from_disk {#from_disk tag="method"}
+## EditTreeLemmatizer.from_disk {id="from_disk",tag="method"}
 
 Load the pipe from disk. Modifies the object in place and returns it.
 
@@ -320,7 +320,7 @@ Load the pipe from disk. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~     |
 | **RETURNS**    | The modified `EditTreeLemmatizer` object. ~~EditTreeLemmatizer~~                                |
 
-## EditTreeLemmatizer.to_bytes {#to_bytes tag="method"}
+## EditTreeLemmatizer.to_bytes {id="to_bytes",tag="method"}
 
 > #### Example
 >
@@ -337,7 +337,7 @@ Serialize the pipe to a bytestring.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The serialized form of the `EditTreeLemmatizer` object. ~~bytes~~                           |
 
-## EditTreeLemmatizer.from_bytes {#from_bytes tag="method"}
+## EditTreeLemmatizer.from_bytes {id="from_bytes",tag="method"}
 
 Load the pipe from a bytestring. Modifies the object in place and returns it.
 
@@ -356,7 +356,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The `EditTreeLemmatizer` object. ~~EditTreeLemmatizer~~                                     |
 
-## EditTreeLemmatizer.labels {#labels tag="property"}
+## EditTreeLemmatizer.labels {id="labels",tag="property"}
 
 The labels currently added to the component.
 
@@ -371,7 +371,7 @@ identifiers of edit trees.
 | ----------- | ------------------------------------------------------ |
 | **RETURNS** | The labels added to the component. ~~Tuple[str, ...]~~ |
 
-## EditTreeLemmatizer.label_data {#label_data tag="property" new="3"}
+## EditTreeLemmatizer.label_data {id="label_data",tag="property",version="3"}
 
 The labels currently added to the component and their internal meta information.
 This is the data generated by [`init labels`](/api/cli#init-labels) and used by
@@ -389,7 +389,7 @@ initialize the model with a pre-defined label set.
 | ----------- | ---------------------------------------------------------- |
 | **RETURNS** | The label data added to the component. ~~Tuple[str, ...]~~ |
 
-## Serialization fields {#serialization-fields}
+## Serialization fields {id="serialization-fields"}
 
 During serialization, spaCy will export several data fields used to restore
 different aspects of the object. If needed, you can exclude them from

website/docs/api/entitylinker.mdx

@@ -2,7 +2,7 @@
 title: EntityLinker
 tag: class
 source: spacy/pipeline/entity_linker.py
-new: 2.2
+version: 2.2
 teaser: 'Pipeline component for named entity linking and disambiguation'
 api_base_class: /api/pipe
 api_string_name: entity_linker
@@ -15,9 +15,9 @@ world". It requires a `KnowledgeBase`, as well as a function to generate
 plausible candidates from that `KnowledgeBase` given a certain textual mention,
 and a machine learning model to pick the right candidate, given the local
 context of the mention. `EntityLinker` defaults to using the
-[`InMemoryLookupKB`](/api/kb_in_memory) implementation.
+[`InMemoryLookupKB`](/api/inmemorylookupkb) implementation.
 
-## Assigned Attributes {#assigned-attributes}
+## Assigned Attributes {id="assigned-attributes"}
 
 Predictions, in the form of knowledge base IDs, will be assigned to
 `Token.ent_kb_id_`.
@@ -27,7 +27,7 @@ Predictions, in the form of knowledge base IDs, will be assigned to
 | `Token.ent_kb_id`  | Knowledge base ID (hash). ~~int~~ |
 | `Token.ent_kb_id_` | Knowledge base ID. ~~str~~        |
 
-## Config and implementation {#config}
+## Config and implementation {id="config"}
 
 The default config is defined by the pipeline component factory and describes
 how the component should be configured. You can override its settings via the
@@ -71,7 +71,7 @@ architectures and their arguments and hyperparameters.
 %%GITHUB_SPACY/spacy/pipeline/entity_linker.py
 ```
 
-## EntityLinker.\_\_init\_\_ {#init tag="method"}
+## EntityLinker.\_\_init\_\_ {id="init",tag="method"}
 
 > #### Example
 >
@@ -114,7 +114,7 @@ custom knowledge base, you should either call
 | `scorer` <Tag variant="new">3.2</Tag>    | The scoring method. Defaults to [`Scorer.score_links`](/api/scorer#score_links). ~~Optional[Callable]~~                                                                                                                                                                                     |
 | `threshold` <Tag variant="new">3.4</Tag> | Confidence threshold for entity predictions. The default of `None` implies that all predictions are accepted, otherwise those with a score beneath the treshold are discarded. If there are no predictions with scores above the threshold, the linked entity is `NIL`. ~~Optional[float]~~ |
 
-## EntityLinker.\_\_call\_\_ {#call tag="method"}
+## EntityLinker.\_\_call\_\_ {id="call",tag="method"}
 
 Apply the pipe to one document. The document is modified in place and returned.
 This usually happens under the hood when the `nlp` object is called on a text
@@ -137,7 +137,7 @@ delegate to the [`predict`](/api/entitylinker#predict) and
 | `doc`       | The document to process. ~~Doc~~ |
 | **RETURNS** | The processed document. ~~Doc~~  |
 
-## EntityLinker.pipe {#pipe tag="method"}
+## EntityLinker.pipe {id="pipe",tag="method"}
 
 Apply the pipe to a stream of documents. This usually happens under the hood
 when the `nlp` object is called on a text and all pipeline components are
@@ -161,7 +161,7 @@ applied to the `Doc` in order. Both [`__call__`](/api/entitylinker#call) and
 | `batch_size`   | The number of documents to buffer. Defaults to `128`. ~~int~~ |
 | **YIELDS**     | The processed documents in order. ~~Doc~~                     |
 
-## EntityLinker.set_kb {#set_kb tag="method" new="3"}
+## EntityLinker.set_kb {id="set_kb",tag="method",version="3"}
 
 The `kb_loader` should be a function that takes a `Vocab` instance and creates
 the `KnowledgeBase`, ensuring that the strings of the knowledge base are synced
@@ -183,7 +183,7 @@ with the current vocab.
 | ----------- | ---------------------------------------------------------------------------------------------------------------- |
 | `kb_loader` | Function that creates a [`KnowledgeBase`](/api/kb) from a `Vocab` instance. ~~Callable[[Vocab], KnowledgeBase]~~ |
 
-## EntityLinker.initialize {#initialize tag="method" new="3"}
+## EntityLinker.initialize {id="initialize",tag="method",version="3"}
 
 Initialize the component for training. `get_examples` should be a function that
 returns an iterable of [`Example`](/api/example) objects. **At least one example
@@ -219,7 +219,7 @@ This method was previously called `begin_training`.
 | `nlp`          | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~                                                                                                       |
 | `kb_loader`    | Function that creates a [`KnowledgeBase`](/api/kb) from a `Vocab` instance. ~~Callable[[Vocab], KnowledgeBase]~~                                                           |
 
-## EntityLinker.predict {#predict tag="method"}
+## EntityLinker.predict {id="predict",tag="method"}
 
 Apply the component's model to a batch of [`Doc`](/api/doc) objects, without
 modifying them. Returns the KB IDs for each entity in each doc, including `NIL`
@@ -237,7 +237,7 @@ if there is no prediction.
 | `docs`      | The documents to predict. ~~Iterable[Doc]~~                                |
 | **RETURNS** | The predicted KB identifiers for the entities in the `docs`. ~~List[str]~~ |
 
-## EntityLinker.set_annotations {#set_annotations tag="method"}
+## EntityLinker.set_annotations {id="set_annotations",tag="method"}
 
 Modify a batch of documents, using pre-computed entity IDs for a list of named
 entities.
@@ -255,7 +255,7 @@ entities.
 | `docs`   | The documents to modify. ~~Iterable[Doc]~~                                                                      |
 | `kb_ids` | The knowledge base identifiers for the entities in the docs, predicted by `EntityLinker.predict`. ~~List[str]~~ |
 
-## EntityLinker.update {#update tag="method"}
+## EntityLinker.update {id="update",tag="method"}
 
 Learn from a batch of [`Example`](/api/example) objects, updating both the
 pipe's entity linking model and context encoder. Delegates to
@@ -278,7 +278,7 @@ pipe's entity linking model and context encoder. Delegates to
 | `losses`       | Optional record of the loss during training. Updated using the component name as the key. ~~Optional[Dict[str, float]]~~ |
 | **RETURNS**    | The updated `losses` dictionary. ~~Dict[str, float]~~                                                                    |
 
-## EntityLinker.create_optimizer {#create_optimizer tag="method"}
+## EntityLinker.create_optimizer {id="create_optimizer",tag="method"}
 
 Create an optimizer for the pipeline component.
 
@@ -293,7 +293,7 @@ Create an optimizer for the pipeline component.
 | ----------- | ---------------------------- |
 | **RETURNS** | The optimizer. ~~Optimizer~~ |
 
-## EntityLinker.use_params {#use_params tag="method, contextmanager"}
+## EntityLinker.use_params {id="use_params",tag="method, contextmanager"}
 
 Modify the pipe's model, to use the given parameter values. At the end of the
 context, the original parameters are restored.
@@ -310,7 +310,7 @@ context, the original parameters are restored.
 | -------- | -------------------------------------------------- |
 | `params` | The parameter values to use in the model. ~~dict~~ |
 
-## EntityLinker.to_disk {#to_disk tag="method"}
+## EntityLinker.to_disk {id="to_disk",tag="method"}
 
 Serialize the pipe to disk.
 
@@ -327,7 +327,7 @@ Serialize the pipe to disk.
 | _keyword-only_ |                                                                                                                                            |
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~                                                |
 
-## EntityLinker.from_disk {#from_disk tag="method"}
+## EntityLinker.from_disk {id="from_disk",tag="method"}
 
 Load the pipe from disk. Modifies the object in place and returns it.
 
@@ -345,7 +345,7 @@ Load the pipe from disk. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~     |
 | **RETURNS**    | The modified `EntityLinker` object. ~~EntityLinker~~                                            |
 
-## EntityLinker.to_bytes {#to_bytes tag="method"}
+## EntityLinker.to_bytes {id="to_bytes",tag="method"}
 
 > #### Example
 >
@@ -362,7 +362,7 @@ Serialize the pipe to a bytestring, including the `KnowledgeBase`.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The serialized form of the `EntityLinker` object. ~~bytes~~                                 |
 
-## EntityLinker.from_bytes {#from_bytes tag="method"}
+## EntityLinker.from_bytes {id="from_bytes",tag="method"}
 
 Load the pipe from a bytestring. Modifies the object in place and returns it.
 
@@ -381,7 +381,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The `EntityLinker` object. ~~EntityLinker~~                                                 |
 
-## Serialization fields {#serialization-fields}
+## Serialization fields {id="serialization-fields"}
 
 During serialization, spaCy will export several data fields used to restore
 different aspects of the object. If needed, you can exclude them from

website/docs/api/entityrecognizer.mdx

@@ -20,7 +20,7 @@ your entities will be close to their initial tokens. If your entities are long
 and characterized by tokens in their middle, the component will likely not be a
 good fit for your task.
 
-## Assigned Attributes {#assigned-attributes}
+## Assigned Attributes {id="assigned-attributes"}
 
 Predictions will be saved to `Doc.ents` as a tuple. Each label will also be
 reflected to each underlying token, where it is saved in the `Token.ent_type`
@@ -38,7 +38,7 @@ non-overlapping, or an error will be thrown.
 | `Token.ent_type`  | The label part of the named entity tag (hash). ~~int~~            |
 | `Token.ent_type_` | The label part of the named entity tag. ~~str~~                   |
 
-## Config and implementation {#config}
+## Config and implementation {id="config"}
 
 The default config is defined by the pipeline component factory and describes
 how the component should be configured. You can override its settings via the
@@ -72,7 +72,7 @@ architectures and their arguments and hyperparameters.
 %%GITHUB_SPACY/spacy/pipeline/ner.pyx
 ```
 
-## EntityRecognizer.\_\_init\_\_ {#init tag="method"}
+## EntityRecognizer.\_\_init\_\_ {id="init",tag="method"}
 
 > #### Example
 >
@@ -103,7 +103,7 @@ shortcut for this and instantiate the component using its string name and
 | `update_with_oracle_cut_size` | During training, cut long sequences into shorter segments by creating intermediate states based on the gold-standard history. The model is not very sensitive to this parameter, so you usually won't need to change it. Defaults to `100`. ~~int~~ |
 | `incorrect_spans_key`         | Identifies spans that are known to be incorrect entity annotations. The incorrect entity annotations can be stored in the span group in [`Doc.spans`](/api/doc#spans), under this key. Defaults to `None`. ~~Optional[str]~~                        |
 
-## EntityRecognizer.\_\_call\_\_ {#call tag="method"}
+## EntityRecognizer.\_\_call\_\_ {id="call",tag="method"}
 
 Apply the pipe to one document. The document is modified in place and returned.
 This usually happens under the hood when the `nlp` object is called on a text
@@ -127,7 +127,7 @@ and all pipeline components are applied to the `Doc` in order. Both
 | `doc`       | The document to process. ~~Doc~~ |
 | **RETURNS** | The processed document. ~~Doc~~  |
 
-## EntityRecognizer.pipe {#pipe tag="method"}
+## EntityRecognizer.pipe {id="pipe",tag="method"}
 
 Apply the pipe to a stream of documents. This usually happens under the hood
 when the `nlp` object is called on a text and all pipeline components are
@@ -151,7 +151,7 @@ applied to the `Doc` in order. Both [`__call__`](/api/entityrecognizer#call) and
 | `batch_size`   | The number of documents to buffer. Defaults to `128`. ~~int~~ |
 | **YIELDS**     | The processed documents in order. ~~Doc~~                     |
 
-## EntityRecognizer.initialize {#initialize tag="method" new="3"}
+## EntityRecognizer.initialize {id="initialize",tag="method",version="3"}
 
 Initialize the component for training. `get_examples` should be a function that
 returns an iterable of [`Example`](/api/example) objects. **At least one example
@@ -194,7 +194,7 @@ This method was previously called `begin_training`.
 | `nlp`          | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~                                                                                                                                                                                                                                                                                                                                                   |
 | `labels`       | The label information to add to the component, as provided by the [`label_data`](#label_data) property after initialization. To generate a reusable JSON file from your data, you should run the [`init labels`](/api/cli#init-labels) command. If no labels are provided, the `get_examples` callback is used to extract the labels from the data, which may be a lot slower. ~~Optional[Dict[str, Dict[str, int]]]~~ |
 
-## EntityRecognizer.predict {#predict tag="method"}
+## EntityRecognizer.predict {id="predict",tag="method"}
 
 Apply the component's model to a batch of [`Doc`](/api/doc) objects, without
 modifying them.
@@ -211,7 +211,7 @@ modifying them.
 | `docs`      | The documents to predict. ~~Iterable[Doc]~~                   |
 | **RETURNS** | A helper class for the parse state (internal). ~~StateClass~~ |
 
-## EntityRecognizer.set_annotations {#set_annotations tag="method"}
+## EntityRecognizer.set_annotations {id="set_annotations",tag="method"}
 
 Modify a batch of [`Doc`](/api/doc) objects, using pre-computed scores.
 
@@ -228,7 +228,7 @@ Modify a batch of [`Doc`](/api/doc) objects, using pre-computed scores.
 | `docs`   | The documents to modify. ~~Iterable[Doc]~~                                                                                            |
 | `scores` | The scores to set, produced by `EntityRecognizer.predict`. Returns an internal helper class for the parse state. ~~List[StateClass]~~ |
 
-## EntityRecognizer.update {#update tag="method"}
+## EntityRecognizer.update {id="update",tag="method"}
 
 Learn from a batch of [`Example`](/api/example) objects, updating the pipe's
 model. Delegates to [`predict`](/api/entityrecognizer#predict) and
@@ -251,7 +251,7 @@ model. Delegates to [`predict`](/api/entityrecognizer#predict) and
 | `losses`       | Optional record of the loss during training. Updated using the component name as the key. ~~Optional[Dict[str, float]]~~ |
 | **RETURNS**    | The updated `losses` dictionary. ~~Dict[str, float]~~                                                                    |
 
-## EntityRecognizer.get_loss {#get_loss tag="method"}
+## EntityRecognizer.get_loss {id="get_loss",tag="method"}
 
 Find the loss and gradient of loss for the batch of documents and their
 predicted scores.
@@ -270,7 +270,7 @@ predicted scores.
 | `scores`    | Scores representing the model's predictions. ~~StateClass~~                 |
 | **RETURNS** | The loss and the gradient, i.e. `(loss, gradient)`. ~~Tuple[float, float]~~ |
 
-## EntityRecognizer.create_optimizer {#create_optimizer tag="method"}
+## EntityRecognizer.create_optimizer {id="create_optimizer",tag="method"}
 
 Create an optimizer for the pipeline component.
 
@@ -285,7 +285,7 @@ Create an optimizer for the pipeline component.
 | ----------- | ---------------------------- |
 | **RETURNS** | The optimizer. ~~Optimizer~~ |
 
-## EntityRecognizer.use_params {#use_params tag="method, contextmanager"}
+## EntityRecognizer.use_params {id="use_params",tag="method, contextmanager"}
 
 Modify the pipe's model, to use the given parameter values. At the end of the
 context, the original parameters are restored.
@@ -302,7 +302,7 @@ context, the original parameters are restored.
 | -------- | -------------------------------------------------- |
 | `params` | The parameter values to use in the model. ~~dict~~ |
 
-## EntityRecognizer.add_label {#add_label tag="method"}
+## EntityRecognizer.add_label {id="add_label",tag="method"}
 
 Add a new label to the pipe. Note that you don't have to call this method if you
 provide a **representative data sample** to the [`initialize`](#initialize)
@@ -322,7 +322,7 @@ to the model, and the output dimension will be
 | `label`     | The label to add. ~~str~~                                   |
 | **RETURNS** | `0` if the label is already present, otherwise `1`. ~~int~~ |
 
-## EntityRecognizer.set_output {#set_output tag="method"}
+## EntityRecognizer.set_output {id="set_output",tag="method"}
 
 Change the output dimension of the component's model by calling the model's
 attribute `resize_output`. This is a function that takes the original model and
@@ -341,7 +341,7 @@ forgetting" problem.
 | ---- | --------------------------------- |
 | `nO` | The new output dimension. ~~int~~ |
 
-## EntityRecognizer.to_disk {#to_disk tag="method"}
+## EntityRecognizer.to_disk {id="to_disk",tag="method"}
 
 Serialize the pipe to disk.
 
@@ -358,7 +358,7 @@ Serialize the pipe to disk.
 | _keyword-only_ |                                                                                                                                            |
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~                                                |
 
-## EntityRecognizer.from_disk {#from_disk tag="method"}
+## EntityRecognizer.from_disk {id="from_disk",tag="method"}
 
 Load the pipe from disk. Modifies the object in place and returns it.
 
@@ -376,7 +376,7 @@ Load the pipe from disk. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~     |
 | **RETURNS**    | The modified `EntityRecognizer` object. ~~EntityRecognizer~~                                    |
 
-## EntityRecognizer.to_bytes {#to_bytes tag="method"}
+## EntityRecognizer.to_bytes {id="to_bytes",tag="method"}
 
 > #### Example
 >
@@ -393,7 +393,7 @@ Serialize the pipe to a bytestring.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The serialized form of the `EntityRecognizer` object. ~~bytes~~                             |
 
-## EntityRecognizer.from_bytes {#from_bytes tag="method"}
+## EntityRecognizer.from_bytes {id="from_bytes",tag="method"}
 
 Load the pipe from a bytestring. Modifies the object in place and returns it.
 
@@ -412,7 +412,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The `EntityRecognizer` object. ~~EntityRecognizer~~                                         |
 
-## EntityRecognizer.labels {#labels tag="property"}
+## EntityRecognizer.labels {id="labels",tag="property"}
 
 The labels currently added to the component.
 
@@ -427,7 +427,7 @@ The labels currently added to the component.
 | ----------- | ------------------------------------------------------ |
 | **RETURNS** | The labels added to the component. ~~Tuple[str, ...]~~ |
 
-## EntityRecognizer.label_data {#label_data tag="property" new="3"}
+## EntityRecognizer.label_data {id="label_data",tag="property",version="3"}
 
 The labels currently added to the component and their internal meta information.
 This is the data generated by [`init labels`](/api/cli#init-labels) and used by
@@ -445,7 +445,7 @@ the model with a pre-defined label set.
 | ----------- | ------------------------------------------------------------------------------- |
 | **RETURNS** | The label data added to the component. ~~Dict[str, Dict[str, Dict[str, int]]]~~ |
 
-## Serialization fields {#serialization-fields}
+## Serialization fields {id="serialization-fields"}
 
 During serialization, spaCy will export several data fields used to restore
 different aspects of the object. If needed, you can exclude them from

website/docs/api/entityruler.mdx

@@ -2,7 +2,7 @@
 title: EntityRuler
 tag: class
 source: spacy/pipeline/entityruler.py
-new: 2.1
+version: 2.1
 teaser: 'Pipeline component for rule-based named entity recognition'
 api_string_name: entity_ruler
 api_trainable: false
@@ -15,7 +15,7 @@ used on its own to implement a purely rule-based entity recognition system. For
 usage examples, see the docs on
 [rule-based entity recognition](/usage/rule-based-matching#entityruler).
 
-## Assigned Attributes {#assigned-attributes}
+## Assigned Attributes {id="assigned-attributes"}
 
 This component assigns predictions basically the same way as the
 [`EntityRecognizer`](/api/entityrecognizer).
@@ -36,7 +36,7 @@ non-overlapping, or an error will be thrown.
 | `Token.ent_type`  | The label part of the named entity tag (hash). ~~int~~            |
 | `Token.ent_type_` | The label part of the named entity tag. ~~str~~                   |
 
-## Config and implementation {#config}
+## Config and implementation {id="config"}
 
 The default config is defined by the pipeline component factory and describes
 how the component should be configured. You can override its settings via the
@@ -56,8 +56,9 @@ how the component should be configured. You can override its settings via the
 > ```
 
 | Setting                                              | Description                                                                                                                                                                                   |
-| --------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ---------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `phrase_matcher_attr`                                | Optional attribute name match on for the internal [`PhraseMatcher`](/api/phrasematcher), e.g. `LOWER` to match on the lowercase token text. Defaults to `None`. ~~Optional[Union[int, str]]~~ |
+| `matcher_fuzzy_compare` <Tag variant="new">3.5</Tag> | The fuzzy comparison method, passed on to the internal `Matcher`. Defaults to `spacy.matcher.levenshtein.levenshtein_compare`. ~~Callable~~                                                             |
 | `validate`                                           | Whether patterns should be validated (passed to the `Matcher` and `PhraseMatcher`). Defaults to `False`. ~~bool~~                                                                             |
 | `overwrite_ents`                                     | If existing entities are present, e.g. entities added by the model, overwrite them by matches if necessary. Defaults to `False`. ~~bool~~                                                     |
 | `ent_id_sep`                                         | Separator used internally for entity IDs. Defaults to `"\|\|"`. ~~str~~                                                                                                                       |
@@ -67,7 +68,7 @@ how the component should be configured. You can override its settings via the
 %%GITHUB_SPACY/spacy/pipeline/entityruler.py
 ```
 
-## EntityRuler.\_\_init\_\_ {#init tag="method"}
+## EntityRuler.\_\_init\_\_ {id="init",tag="method"}
 
 Initialize the entity ruler. If patterns are supplied here, they need to be a
 list of dictionaries with a `"label"` and `"pattern"` key. A pattern can either
@@ -86,22 +87,24 @@ be a token pattern (list) or a phrase pattern (string). For example:
 > ```
 
 | Name                                                 | Description                                                                                                                                                                                                                           |
-| --------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ---------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `nlp`                                                | The shared nlp object to pass the vocab to the matchers and process phrase patterns. ~~Language~~                                                                                                                                     |
 | `name` <Tag variant="new">3</Tag>                    | Instance name of the current pipeline component. Typically passed in automatically from the factory when the component is added. Used to disable the current entity ruler while creating phrase patterns with the nlp object. ~~str~~ |
 | _keyword-only_                                       |                                                                                                                                                                                                                                       |
 | `phrase_matcher_attr`                                | Optional attribute name match on for the internal [`PhraseMatcher`](/api/phrasematcher), e.g. `LOWER` to match on the lowercase token text. Defaults to `None`. ~~Optional[Union[int, str]]~~                                         |
+| `matcher_fuzzy_compare` <Tag variant="new">3.5</Tag> | The fuzzy comparison method, passed on to the internal `Matcher`. Defaults to `spacy.matcher.levenshtein.levenshtein_compare`. ~~Callable~~                                                                                                     |
 | `validate`                                           | Whether patterns should be validated, passed to Matcher and PhraseMatcher as `validate`. Defaults to `False`. ~~bool~~                                                                                                                |
 | `overwrite_ents`                                     | If existing entities are present, e.g. entities added by the model, overwrite them by matches if necessary. Defaults to `False`. ~~bool~~                                                                                             |
 | `ent_id_sep`                                         | Separator used internally for entity IDs. Defaults to `"\|\|"`. ~~str~~                                                                                                                                                               |
 | `patterns`                                           | Optional patterns to load in on initialization. ~~Optional[List[Dict[str, Union[str, List[dict]]]]]~~                                                                                                                                 |
+| `scorer`                                             | The scoring method. Defaults to [`spacy.scorer.get_ner_prf`](/api/scorer#get_ner_prf). ~~Optional[Callable]~~                                                                                                                         |
 
-## EntityRuler.initialize {#initialize tag="method" new="3"}
+## EntityRuler.initialize {id="initialize",tag="method",version="3"}
 
 Initialize the component with data and used before training to load in rules
-from a [pattern file](/usage/rule-based-matching/#entityruler-files). This method
+from a [pattern file](/usage/rule-based-matching/#entityruler-files). This
-is typically called by [`Language.initialize`](/api/language#initialize) and
+method is typically called by [`Language.initialize`](/api/language#initialize)
-lets you customize arguments it receives via the
+and lets you customize arguments it receives via the
 [`[initialize.components]`](/api/data-formats#config-initialize) block in the
 config.
 
@@ -128,7 +131,7 @@ config.
 | `nlp`          | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~                                                                                                 |
 | `patterns`     | The list of patterns. Defaults to `None`. ~~Optional[Sequence[Dict[str, Union[str, List[Dict[str, Any]]]]]]~~                                                        |
 
-## EntityRuler.\_\len\_\_ {#len tag="method"}
+## EntityRuler.\_\_len\_\_ {id="len",tag="method"}
 
 The number of all patterns added to the entity ruler.
 
@@ -145,7 +148,7 @@ The number of all patterns added to the entity ruler.
 | ----------- | ------------------------------- |
 | **RETURNS** | The number of patterns. ~~int~~ |
 
-## EntityRuler.\_\_contains\_\_ {#contains tag="method"}
+## EntityRuler.\_\_contains\_\_ {id="contains",tag="method"}
 
 Whether a label is present in the patterns.
 
@@ -163,7 +166,7 @@ Whether a label is present in the patterns.
 | `label`     | The label to check. ~~str~~                           |
 | **RETURNS** | Whether the entity ruler contains the label. ~~bool~~ |
 
-## EntityRuler.\_\_call\_\_ {#call tag="method"}
+## EntityRuler.\_\_call\_\_ {id="call",tag="method"}
 
 Find matches in the `Doc` and add them to the `doc.ents`. Typically, this
 happens automatically after the component has been added to the pipeline using
@@ -189,7 +192,7 @@ is chosen.
 | `doc`       | The `Doc` object to process, e.g. the `Doc` in the pipeline. ~~Doc~~ |
 | **RETURNS** | The modified `Doc` with added entities, if available. ~~Doc~~        |
 
-## EntityRuler.add_patterns {#add_patterns tag="method"}
+## EntityRuler.add_patterns {id="add_patterns",tag="method"}
 
 Add patterns to the entity ruler. A pattern can either be a token pattern (list
 of dicts) or a phrase pattern (string). For more details, see the usage guide on
@@ -210,10 +213,10 @@ of dicts) or a phrase pattern (string). For more details, see the usage guide on
 | ---------- | ---------------------------------------------------------------- |
 | `patterns` | The patterns to add. ~~List[Dict[str, Union[str, List[dict]]]]~~ |
 
+## EntityRuler.remove {id="remove",tag="method",version="3.2.1"}
 
-## EntityRuler.remove {#remove tag="method" new="3.2.1"}
+Remove a pattern by its ID from the entity ruler. A `ValueError` is raised if
-
+the ID does not exist.
-Remove a pattern by its ID from the entity ruler. A `ValueError` is raised if the ID does not exist.
 
 > #### Example
 >
@@ -225,10 +228,10 @@ Remove a pattern by its ID from the entity ruler. A `ValueError` is raised if th
 > ```
 
 | Name | Description                         |
-| ---------- | ---------------------------------------------------------------- |
+| ---- | ----------------------------------- |
 | `id` | The ID of the pattern rule. ~~str~~ |
 
-## EntityRuler.to_disk {#to_disk tag="method"}
+## EntityRuler.to_disk {id="to_disk",tag="method"}
 
 Save the entity ruler patterns to a directory. The patterns will be saved as
 newline-delimited JSON (JSONL). If a file with the suffix `.jsonl` is provided,
@@ -247,7 +250,7 @@ only the patterns are saved as JSONL. If a directory name is provided, a
 | ------ | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `path` | A path to a JSONL file or directory, which will be created if it doesn't exist. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ |
 
-## EntityRuler.from_disk {#from_disk tag="method"}
+## EntityRuler.from_disk {id="from_disk",tag="method"}
 
 Load the entity ruler from a path. Expects either a file containing
 newline-delimited JSON (JSONL) with one entry per line, or a directory
@@ -267,7 +270,7 @@ configuration.
 | `path`      | A path to a JSONL file or directory. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ |
 | **RETURNS** | The modified `EntityRuler` object. ~~EntityRuler~~                                                            |
 
-## EntityRuler.to_bytes {#to_bytes tag="method"}
+## EntityRuler.to_bytes {id="to_bytes",tag="method"}
 
 Serialize the entity ruler patterns to a bytestring.
 
@@ -282,7 +285,7 @@ Serialize the entity ruler patterns to a bytestring.
 | ----------- | ---------------------------------- |
 | **RETURNS** | The serialized patterns. ~~bytes~~ |
 
-## EntityRuler.from_bytes {#from_bytes tag="method"}
+## EntityRuler.from_bytes {id="from_bytes",tag="method"}
 
 Load the pipe from a bytestring. Modifies the object in place and returns it.
 
@@ -299,7 +302,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
 | `bytes_data` | The bytestring to load. ~~bytes~~                  |
 | **RETURNS**  | The modified `EntityRuler` object. ~~EntityRuler~~ |
 
-## EntityRuler.labels {#labels tag="property"}
+## EntityRuler.labels {id="labels",tag="property"}
 
 All labels present in the match patterns.
 
@@ -307,7 +310,7 @@ All labels present in the match patterns.
 | ----------- | -------------------------------------- |
 | **RETURNS** | The string labels. ~~Tuple[str, ...]~~ |
 
-## EntityRuler.ent_ids {#ent_ids tag="property" new="2.2.2"}
+## EntityRuler.ent_ids {id="ent_ids",tag="property",version="2.2.2"}
 
 All entity IDs present in the `id` properties of the match patterns.
 
@@ -315,7 +318,7 @@ All entity IDs present in the `id` properties of the match patterns.
 | ----------- | ----------------------------------- |
 | **RETURNS** | The string IDs. ~~Tuple[str, ...]~~ |
 
-## EntityRuler.patterns {#patterns tag="property"}
+## EntityRuler.patterns {id="patterns",tag="property"}
 
 Get all patterns that were added to the entity ruler.
 
@@ -323,7 +326,7 @@ Get all patterns that were added to the entity ruler.
 | ----------- | ---------------------------------------------------------------------------------------- |
 | **RETURNS** | The original patterns, one dictionary per pattern. ~~List[Dict[str, Union[str, dict]]]~~ |
 
-## Attributes {#attributes}
+## Attributes {id="attributes"}
 
 | Name              | Description                                                                                                           |
 | ----------------- | --------------------------------------------------------------------------------------------------------------------- |

website/docs/api/example.mdx

@@ -3,7 +3,7 @@ title: Example
 teaser: A training instance
 tag: class
 source: spacy/training/example.pyx
-new: 3.0
+version: 3.0
 ---
 
 An `Example` holds the information for one training instance. It stores two
@@ -12,7 +12,7 @@ holding the predictions of the pipeline. An
 [`Alignment`](/api/example#alignment-object) object stores the alignment between
 these two documents, as they can differ in tokenization.
 
-## Example.\_\_init\_\_ {#init tag="method"}
+## Example.\_\_init\_\_ {id="init",tag="method"}
 
 Construct an `Example` object from the `predicted` document and the `reference`
 document. If `alignment` is `None`, it will be initialized from the words in
@@ -40,7 +40,7 @@ both documents.
 | _keyword-only_ |                                                                                                                          |
 | `alignment`    | An object holding the alignment between the tokens of the `predicted` and `reference` documents. ~~Optional[Alignment]~~ |
 
-## Example.from_dict {#from_dict tag="classmethod"}
+## Example.from_dict {id="from_dict",tag="classmethod"}
 
 Construct an `Example` object from the `predicted` document and the reference
 annotations provided as a dictionary. For more details on the required format,
@@ -64,7 +64,7 @@ see the [training format documentation](/api/data-formats#dict-input).
 | `example_dict` | The gold-standard annotations as a dictionary. Cannot be `None`. ~~Dict[str, Any]~~ |
 | **RETURNS**    | The newly constructed object. ~~Example~~                                           |
 
-## Example.text {#text tag="property"}
+## Example.text {id="text",tag="property"}
 
 The text of the `predicted` document in this `Example`.
 
@@ -78,7 +78,7 @@ The text of the `predicted` document in this `Example`.
 | ----------- | --------------------------------------------- |
 | **RETURNS** | The text of the `predicted` document. ~~str~~ |
 
-## Example.predicted {#predicted tag="property"}
+## Example.predicted {id="predicted",tag="property"}
 
 The `Doc` holding the predictions. Occasionally also referred to as `example.x`.
 
@@ -94,7 +94,7 @@ The `Doc` holding the predictions. Occasionally also referred to as `example.x`.
 | ----------- | ------------------------------------------------------ |
 | **RETURNS** | The document containing (partial) predictions. ~~Doc~~ |
 
-## Example.reference {#reference tag="property"}
+## Example.reference {id="reference",tag="property"}
 
 The `Doc` holding the gold-standard annotations. Occasionally also referred to
 as `example.y`.
@@ -111,7 +111,7 @@ as `example.y`.
 | ----------- | ---------------------------------------------------------- |
 | **RETURNS** | The document containing gold-standard annotations. ~~Doc~~ |
 
-## Example.alignment {#alignment tag="property"}
+## Example.alignment {id="alignment",tag="property"}
 
 The [`Alignment`](/api/example#alignment-object) object mapping the tokens of
 the `predicted` document to those of the `reference` document.
@@ -131,7 +131,7 @@ the `predicted` document to those of the `reference` document.
 | ----------- | ---------------------------------------------------------------- |
 | **RETURNS** | The document containing gold-standard annotations. ~~Alignment~~ |
 
-## Example.get_aligned {#get_aligned tag="method"}
+## Example.get_aligned {id="get_aligned",tag="method"}
 
 Get the aligned view of a certain token attribute, denoted by its int ID or
 string name.
@@ -152,7 +152,7 @@ string name.
 | `as_string` | Whether or not to return the list of values as strings. Defaults to `False`. ~~bool~~              |
 | **RETURNS** | List of integer values, or string values if `as_string` is `True`. ~~Union[List[int], List[str]]~~ |
 
-## Example.get_aligned_parse {#get_aligned_parse tag="method"}
+## Example.get_aligned_parse {id="get_aligned_parse",tag="method"}
 
 Get the aligned view of the dependency parse. If `projectivize` is set to
 `True`, non-projective dependency trees are made projective through the
@@ -172,7 +172,7 @@ Pseudo-Projective Dependency Parsing algorithm by Nivre and Nilsson (2005).
 | `projectivize` | Whether or not to projectivize the dependency trees. Defaults to `True`. ~~bool~~                  |
 | **RETURNS**    | List of integer values, or string values if `as_string` is `True`. ~~Union[List[int], List[str]]~~ |
 
-## Example.get_aligned_ner {#get_aligned_ner tag="method"}
+## Example.get_aligned_ner {id="get_aligned_ner",tag="method"}
 
 Get the aligned view of the NER
 [BILUO](/usage/linguistic-features#accessing-ner) tags.
@@ -193,7 +193,7 @@ Get the aligned view of the NER
 | ----------- | ------------------------------------------------------------------------------------------------- |
 | **RETURNS** | List of BILUO values, denoting whether tokens are part of an NER annotation or not. ~~List[str]~~ |
 
-## Example.get_aligned_spans_y2x {#get_aligned_spans_y2x tag="method"}
+## Example.get_aligned_spans_y2x {id="get_aligned_spans_y2x",tag="method"}
 
 Get the aligned view of any set of [`Span`](/api/span) objects defined over
 [`Example.reference`](/api/example#reference). The resulting span indices will
@@ -219,7 +219,7 @@ align to the tokenization in [`Example.predicted`](/api/example#predicted).
 | `allow_overlap` | Whether the resulting `Span` objects may overlap or not. Set to `False` by default. ~~bool~~ |
 | **RETURNS**     | `Span` objects aligned to the tokenization of `predicted`. ~~List[Span]~~                    |
 
-## Example.get_aligned_spans_x2y {#get_aligned_spans_x2y tag="method"}
+## Example.get_aligned_spans_x2y {id="get_aligned_spans_x2y",tag="method"}
 
 Get the aligned view of any set of [`Span`](/api/span) objects defined over
 [`Example.predicted`](/api/example#predicted). The resulting span indices will
@@ -247,7 +247,7 @@ against the original gold-standard annotation.
 | `allow_overlap` | Whether the resulting `Span` objects may overlap or not. Set to `False` by default. ~~bool~~ |
 | **RETURNS**     | `Span` objects aligned to the tokenization of `reference`. ~~List[Span]~~                    |
 
-## Example.to_dict {#to_dict tag="method"}
+## Example.to_dict {id="to_dict",tag="method"}
 
 Return a [dictionary representation](/api/data-formats#dict-input) of the
 reference annotation contained in this `Example`.
@@ -262,7 +262,7 @@ reference annotation contained in this `Example`.
 | ----------- | ------------------------------------------------------------------------- |
 | **RETURNS** | Dictionary representation of the reference annotation. ~~Dict[str, Any]~~ |
 
-## Example.split_sents {#split_sents tag="method"}
+## Example.split_sents {id="split_sents",tag="method"}
 
 Split one `Example` into multiple `Example` objects, one for each sentence.
 
@@ -282,15 +282,15 @@ Split one `Example` into multiple `Example` objects, one for each sentence.
 | ----------- | ---------------------------------------------------------------------------- |
 | **RETURNS** | List of `Example` objects, one for each original sentence. ~~List[Example]~~ |
 
-## Alignment {#alignment-object new="3"}
+## Alignment {id="alignment-object",version="3"}
 
 Calculate alignment tables between two tokenizations.
 
-### Alignment attributes {#alignment-attributes"}
+### Alignment attributes {id="alignment-attributes"}
 
-Alignment attributes are managed using `AlignmentArray`, which is a
+Alignment attributes are managed using `AlignmentArray`, which is a simplified
-simplified version of Thinc's [Ragged](https://thinc.ai/docs/api-types#ragged)
+version of Thinc's [Ragged](https://thinc.ai/docs/api-types#ragged) type that
-type that only supports the `data` and `length` attributes.
+only supports the `data` and `length` attributes.
 
 | Name  | Description                                                                           |
 | ----- | ------------------------------------------------------------------------------------- |
@@ -321,7 +321,7 @@ tokenizations add up to the same string. For example, you'll be able to align
 > If `a2b.data[1] == a2b.data[2] == 1`, that means that `A[1]` (`"'"`) and
 > `A[2]` (`"s"`) both align to `B[1]` (`"'s"`).
 
-### Alignment.from_strings {#classmethod tag="function"}
+### Alignment.from_strings {id="classmethod",tag="function"}
 
 | Name        | Description                                                   |
 | ----------- | ------------------------------------------------------------- |

website/docs/api/index.mdx

@@ -3,6 +3,4 @@ title: Library Architecture
 next: /api/architectures
 ---
 
-import Architecture101 from 'usage/101/\_architecture.md'
-
 <Architecture101 />

website/docs/api/inmemorylookupkb.mdx

@@ -5,7 +5,7 @@ teaser:
   information in-memory.
 tag: class
 source: spacy/kb/kb_in_memory.pyx
-new: 3.5
+version: 3.5
 ---
 
 The `InMemoryLookupKB` class inherits from [`KnowledgeBase`](/api/kb) and
@@ -14,7 +14,7 @@ implements all of its methods. It stores all KB data in-memory and generates
 entity names. It's highly optimized for both a low memory footprint and speed of
 retrieval.
 
-## InMemoryLookupKB.\_\_init\_\_ {#init tag="method"}
+## InMemoryLookupKB.\_\_init\_\_ {id="init",tag="method"}
 
 Create the knowledge base.
 
@@ -31,7 +31,7 @@ Create the knowledge base.
 | `vocab`                | The shared vocabulary. ~~Vocab~~                 |
 | `entity_vector_length` | Length of the fixed-size entity vectors. ~~int~~ |
 
-## InMemoryLookupKB.entity_vector_length {#entity_vector_length tag="property"}
+## InMemoryLookupKB.entity_vector_length {id="entity_vector_length",tag="property"}
 
 The length of the fixed-size entity vectors in the knowledge base.
 
@@ -39,11 +39,11 @@ The length of the fixed-size entity vectors in the knowledge base.
 | ----------- | ------------------------------------------------ |
 | **RETURNS** | Length of the fixed-size entity vectors. ~~int~~ |
 
-## InMemoryLookupKB.add_entity {#add_entity tag="method"}
+## InMemoryLookupKB.add_entity {id="add_entity",tag="method"}
 
 Add an entity to the knowledge base, specifying its corpus frequency and entity
 vector, which should be of length
-[`entity_vector_length`](/api/kb_in_memory#entity_vector_length).
+[`entity_vector_length`](/api/inmemorylookupkb#entity_vector_length).
 
 > #### Example
 >
@@ -58,7 +58,7 @@ vector, which should be of length
 | `freq`          | The frequency of the entity in a typical corpus. ~~float~~ |
 | `entity_vector` | The pretrained vector of the entity. ~~numpy.ndarray~~     |
 
-## InMemoryLookupKB.set_entities {#set_entities tag="method"}
+## InMemoryLookupKB.set_entities {id="set_entities",tag="method"}
 
 Define the full list of entities in the knowledge base, specifying the corpus
 frequency and entity vector for each entity.
@@ -75,12 +75,13 @@ frequency and entity vector for each entity.
 | `freq_list`   | List of entity frequencies. ~~Iterable[int]~~                    |
 | `vector_list` | List of entity vectors. ~~Iterable[numpy.ndarray]~~              |
 
-## InMemoryLookupKB.add_alias {#add_alias tag="method"}
+## InMemoryLookupKB.add_alias {id="add_alias",tag="method"}
 
 Add an alias or mention to the knowledge base, specifying its potential KB
 identifiers and their prior probabilities. The entity identifiers should refer
-to entities previously added with [`add_entity`](/api/kb_in_memory#add_entity)
+to entities previously added with
-or [`set_entities`](/api/kb_in_memory#set_entities). The sum of the prior
+[`add_entity`](/api/inmemorylookupkb#add_entity) or
+[`set_entities`](/api/inmemorylookupkb#set_entities). The sum of the prior
 probabilities should not exceed 1. Note that an empty string can not be used as
 alias.
 
@@ -96,7 +97,7 @@ alias.
 | `entities`      | The potential entities that the alias may refer to. ~~Iterable[Union[str, int]]~~ |
 | `probabilities` | The prior probabilities of each entity. ~~Iterable[float]~~                       |
 
-## InMemoryLookupKB.\_\_len\_\_ {#len tag="method"}
+## InMemoryLookupKB.\_\_len\_\_ {id="len",tag="method"}
 
 Get the total number of entities in the knowledge base.
 
@@ -110,7 +111,7 @@ Get the total number of entities in the knowledge base.
 | ----------- | ----------------------------------------------------- |
 | **RETURNS** | The number of entities in the knowledge base. ~~int~~ |
 
-## InMemoryLookupKB.get_entity_strings {#get_entity_strings tag="method"}
+## InMemoryLookupKB.get_entity_strings {id="get_entity_strings",tag="method"}
 
 Get a list of all entity IDs in the knowledge base.
 
@@ -124,7 +125,7 @@ Get a list of all entity IDs in the knowledge base.
 | ----------- | --------------------------------------------------------- |
 | **RETURNS** | The list of entities in the knowledge base. ~~List[str]~~ |
 
-## InMemoryLookupKB.get_size_aliases {#get_size_aliases tag="method"}
+## InMemoryLookupKB.get_size_aliases {id="get_size_aliases",tag="method"}
 
 Get the total number of aliases in the knowledge base.
 
@@ -138,7 +139,7 @@ Get the total number of aliases in the knowledge base.
 | ----------- | ---------------------------------------------------- |
 | **RETURNS** | The number of aliases in the knowledge base. ~~int~~ |
 
-## InMemoryLookupKB.get_alias_strings {#get_alias_strings tag="method"}
+## InMemoryLookupKB.get_alias_strings {id="get_alias_strings",tag="method"}
 
 Get a list of all aliases in the knowledge base.
 
@@ -152,11 +153,11 @@ Get a list of all aliases in the knowledge base.
 | ----------- | -------------------------------------------------------- |
 | **RETURNS** | The list of aliases in the knowledge base. ~~List[str]~~ |
 
-## InMemoryLookupKB.get_candidates {#get_candidates tag="method"}
+## InMemoryLookupKB.get_candidates {id="get_candidates",tag="method"}
 
 Given a certain textual mention as input, retrieve a list of candidate entities
 of type [`Candidate`](/api/kb#candidate). Wraps
-[`get_alias_candidates()`](/api/kb_in_memory#get_alias_candidates).
+[`get_alias_candidates()`](/api/inmemorylookupkb#get_alias_candidates).
 
 > #### Example
 >
@@ -172,9 +173,9 @@ of type [`Candidate`](/api/kb#candidate). Wraps
 | `mention`   | The textual mention or alias. ~~Span~~                               |
 | **RETURNS** | An iterable of relevant `Candidate` objects. ~~Iterable[Candidate]~~ |
 
-## InMemoryLookupKB.get_candidates_batch {#get_candidates_batch tag="method"}
+## InMemoryLookupKB.get_candidates_batch {id="get_candidates_batch",tag="method"}
 
-Same as [`get_candidates()`](/api/kb_in_memory#get_candidates), but for an
+Same as [`get_candidates()`](/api/inmemorylookupkb#get_candidates), but for an
 arbitrary number of mentions. The [`EntityLinker`](/api/entitylinker) component
 will call `get_candidates_batch()` instead of `get_candidates()`, if the config
 parameter `candidates_batch_size` is greater or equal than 1.
@@ -198,7 +199,7 @@ to you.
 | `mentions`  | The textual mention or alias. ~~Iterable[Span]~~                                             |
 | **RETURNS** | An iterable of iterable with relevant `Candidate` objects. ~~Iterable[Iterable[Candidate]]~~ |
 
-## InMemoryLookupKB.get_alias_candidates {#get_alias_candidates tag="method"}
+## InMemoryLookupKB.get_alias_candidates {id="get_alias_candidates",tag="method"}
 
 Given a certain textual mention as input, retrieve a list of candidate entities
 of type [`Candidate`](/api/kb#candidate).
@@ -214,7 +215,7 @@ of type [`Candidate`](/api/kb#candidate).
 | `alias`     | The textual mention or alias. ~~str~~                         |
 | **RETURNS** | The list of relevant `Candidate` objects. ~~List[Candidate]~~ |
 
-## InMemoryLookupKB.get_vector {#get_vector tag="method"}
+## InMemoryLookupKB.get_vector {id="get_vector",tag="method"}
 
 Given a certain entity ID, retrieve its pretrained entity vector.
 
@@ -229,9 +230,9 @@ Given a certain entity ID, retrieve its pretrained entity vector.
 | `entity`    | The entity ID. ~~str~~               |
 | **RETURNS** | The entity vector. ~~numpy.ndarray~~ |
 
-## InMemoryLookupKB.get_vectors {#get_vectors tag="method"}
+## InMemoryLookupKB.get_vectors {id="get_vectors",tag="method"}
 
-Same as [`get_vector()`](/api/kb_in_memory#get_vector), but for an arbitrary
+Same as [`get_vector()`](/api/inmemorylookupkb#get_vector), but for an arbitrary
 number of entity IDs.
 
 The default implementation of `get_vectors()` executes `get_vector()` in a loop.
@@ -249,7 +250,7 @@ entities at once, if performance is of concern to you.
 | `entities`  | The entity IDs. ~~Iterable[str]~~                         |
 | **RETURNS** | The entity vectors. ~~Iterable[Iterable[numpy.ndarray]]~~ |
 
-## InMemoryLookupKB.get_prior_prob {#get_prior_prob tag="method"}
+## InMemoryLookupKB.get_prior_prob {id="get_prior_prob",tag="method"}
 
 Given a certain entity ID and a certain textual mention, retrieve the prior
 probability of the fact that the mention links to the entity ID.
@@ -266,7 +267,7 @@ probability of the fact that the mention links to the entity ID.
 | `alias`     | The textual mention or alias. ~~str~~                                     |
 | **RETURNS** | The prior probability of the `alias` referring to the `entity`. ~~float~~ |
 
-## InMemoryLookupKB.to_disk {#to_disk tag="method"}
+## InMemoryLookupKB.to_disk {id="to_disk",tag="method"}
 
 Save the current state of the knowledge base to a directory.
 
@@ -281,7 +282,7 @@ Save the current state of the knowledge base to a directory.
 | `path`    | A path to a directory, which will be created if it doesn't exist. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ |
 | `exclude` | List of components to exclude. ~~Iterable[str]~~                                                                                           |
 
-## InMemoryLookupKB.from_disk {#from_disk tag="method"}
+## InMemoryLookupKB.from_disk {id="from_disk",tag="method"}
 
 Restore the state of the knowledge base from a given directory. Note that the
 [`Vocab`](/api/vocab) should also be the same as the one used to create the KB.

website/docs/api/kb.mdx

@@ -5,7 +5,7 @@ teaser:
   (ontology)
 tag: class
 source: spacy/kb/kb.pyx
-new: 2.2
+version: 2.2
 ---
 
 The `KnowledgeBase` object is an abstract class providing a method to generate
@@ -21,12 +21,12 @@ functions called by the [`EntityLinker`](/api/entitylinker) component.
 <Infobox variant="warning">
 
 This class was not abstract up to spaCy version 3.5. The `KnowledgeBase`
-implementation up to that point is available as `InMemoryLookupKB` from 3.5
+implementation up to that point is available as
-onwards.
+[`InMemoryLookupKB`](/api/inmemorylookupkb) from 3.5 onwards.
 
 </Infobox>
 
-## KnowledgeBase.\_\_init\_\_ {#init tag="method"}
+## KnowledgeBase.\_\_init\_\_ {id="init",tag="method"}
 
 `KnowledgeBase` is an abstract class and cannot be instantiated. Its child
 classes should call `__init__()` to set up some necessary attributes.
@@ -50,7 +50,7 @@ classes should call `__init__()` to set up some necessary attributes.
 | `vocab`                | The shared vocabulary. ~~Vocab~~                 |
 | `entity_vector_length` | Length of the fixed-size entity vectors. ~~int~~ |
 
-## KnowledgeBase.entity_vector_length {#entity_vector_length tag="property"}
+## KnowledgeBase.entity_vector_length {id="entity_vector_length",tag="property"}
 
 The length of the fixed-size entity vectors in the knowledge base.
 
@@ -58,7 +58,7 @@ The length of the fixed-size entity vectors in the knowledge base.
 | ----------- | ------------------------------------------------ |
 | **RETURNS** | Length of the fixed-size entity vectors. ~~int~~ |
 
-## KnowledgeBase.get_candidates {#get_candidates tag="method"}
+## KnowledgeBase.get_candidates {id="get_candidates",tag="method"}
 
 Given a certain textual mention as input, retrieve a list of candidate entities
 of type [`Candidate`](/api/kb#candidate).
@@ -77,7 +77,7 @@ of type [`Candidate`](/api/kb#candidate).
 | `mention`   | The textual mention or alias. ~~Span~~                               |
 | **RETURNS** | An iterable of relevant `Candidate` objects. ~~Iterable[Candidate]~~ |
 
-## KnowledgeBase.get_candidates_batch {#get_candidates_batch tag="method"}
+## KnowledgeBase.get_candidates_batch {id="get_candidates_batch",tag="method"}
 
 Same as [`get_candidates()`](/api/kb#get_candidates), but for an arbitrary
 number of mentions. The [`EntityLinker`](/api/entitylinker) component will call
@@ -103,23 +103,24 @@ to you.
 | `mentions`  | The textual mention or alias. ~~Iterable[Span]~~                                             |
 | **RETURNS** | An iterable of iterable with relevant `Candidate` objects. ~~Iterable[Iterable[Candidate]]~~ |
 
-## KnowledgeBase.get_alias_candidates {#get_alias_candidates tag="method"}
+## KnowledgeBase.get_alias_candidates {id="get_alias_candidates",tag="method"}
 
 <Infobox variant="warning">
   This method is _not_ available from spaCy 3.5 onwards.
 </Infobox>
 
 From spaCy 3.5 on `KnowledgeBase` is an abstract class (with
-[`InMemoryLookupKB`](/api/kb_in_memory) being a drop-in replacement) to allow
+[`InMemoryLookupKB`](/api/inmemorylookupkb) being a drop-in replacement) to
-more flexibility in customizing knowledge bases. Some of its methods were moved
+allow more flexibility in customizing knowledge bases. Some of its methods were
-to [`InMemoryLookupKB`](/api/kb_in_memory) during this refactoring, one of those
+moved to [`InMemoryLookupKB`](/api/inmemorylookupkb) during this refactoring,
-being `get_alias_candidates()`. This method is now available as
+one of those being `get_alias_candidates()`. This method is now available as
-[`InMemoryLookupKB.get_alias_candidates()`](/api/kb_in_memory#get_alias_candidates).
+[`InMemoryLookupKB.get_alias_candidates()`](/api/inmemorylookupkb#get_alias_candidates).
-Note: [`InMemoryLookupKB.get_candidates()`](/api/kb_in_memory#get_candidates)
+Note:
+[`InMemoryLookupKB.get_candidates()`](/api/inmemorylookupkb#get_candidates)
 defaults to
-[`InMemoryLookupKB.get_alias_candidates()`](/api/kb_in_memory#get_alias_candidates).
+[`InMemoryLookupKB.get_alias_candidates()`](/api/inmemorylookupkb#get_alias_candidates).
 
-## KnowledgeBase.get_vector {#get_vector tag="method"}
+## KnowledgeBase.get_vector {id="get_vector",tag="method"}
 
 Given a certain entity ID, retrieve its pretrained entity vector.
 
@@ -134,7 +135,7 @@ Given a certain entity ID, retrieve its pretrained entity vector.
 | `entity`    | The entity ID. ~~str~~                 |
 | **RETURNS** | The entity vector. ~~Iterable[float]~~ |
 
-## KnowledgeBase.get_vectors {#get_vectors tag="method"}
+## KnowledgeBase.get_vectors {id="get_vectors",tag="method"}
 
 Same as [`get_vector()`](/api/kb#get_vector), but for an arbitrary number of
 entity IDs.
@@ -154,7 +155,7 @@ entities at once, if performance is of concern to you.
 | `entities`  | The entity IDs. ~~Iterable[str]~~                         |
 | **RETURNS** | The entity vectors. ~~Iterable[Iterable[numpy.ndarray]]~~ |
 
-## KnowledgeBase.to_disk {#to_disk tag="method"}
+## KnowledgeBase.to_disk {id="to_disk",tag="method"}
 
 Save the current state of the knowledge base to a directory.
 
@@ -169,7 +170,7 @@ Save the current state of the knowledge base to a directory.
 | `path`    | A path to a directory, which will be created if it doesn't exist. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ |
 | `exclude` | List of components to exclude. ~~Iterable[str]~~                                                                                           |
 
-## KnowledgeBase.from_disk {#from_disk tag="method"}
+## KnowledgeBase.from_disk {id="from_disk",tag="method"}
 
 Restore the state of the knowledge base from a given directory. Note that the
 [`Vocab`](/api/vocab) should also be the same as the one used to create the KB.
@@ -189,7 +190,7 @@ Restore the state of the knowledge base from a given directory. Note that the
 | `exclude`   | List of components to exclude. ~~Iterable[str]~~                                                |
 | **RETURNS** | The modified `KnowledgeBase` object. ~~KnowledgeBase~~                                          |
 
-## Candidate {#candidate tag="class"}
+## Candidate {id="candidate",tag="class"}
 
 A `Candidate` object refers to a textual mention (alias) that may or may not be
 resolved to a specific entity from a `KnowledgeBase`. This will be used as input
@@ -197,7 +198,7 @@ for the entity linking algorithm which will disambiguate the various candidates
 to the correct one. Each candidate `(alias, entity)` pair is assigned to a
 certain prior probability.
 
-### Candidate.\_\_init\_\_ {#candidate-init tag="method"}
+### Candidate.\_\_init\_\_ {id="candidate-init",tag="method"}
 
 Construct a `Candidate` object. Usually this constructor is not called directly,
 but instead these objects are returned by the `get_candidates` method of the
@@ -218,7 +219,7 @@ but instead these objects are returned by the `get_candidates` method of the
 | `alias_hash`  | The hash of the textual mention or alias. ~~int~~                         |
 | `prior_prob`  | The prior probability of the `alias` referring to the `entity`. ~~float~~ |
 
-## Candidate attributes {#candidate-attributes}
+## Candidate attributes {id="candidate-attributes"}
 
 | Name            | Description                                                              |
 | --------------- | ------------------------------------------------------------------------ |

website/docs/api/language.mdx

@@ -15,7 +15,7 @@ the tagger or parser that are called on a document in order. You can also add
 your own processing pipeline components that take a `Doc` object, modify it and
 return it.
 
-## Language.\_\_init\_\_ {#init tag="method"}
+## Language.\_\_init\_\_ {id="init",tag="method"}
 
 Initialize a `Language` object. Note that the `meta` is only used for meta
 information in [`Language.meta`](/api/language#meta) and not to configure the
@@ -44,7 +44,7 @@ information in [`Language.meta`](/api/language#meta) and not to configure the
 | `create_tokenizer` | Optional function that receives the `nlp` object and returns a tokenizer. ~~Callable[[Language], Callable[[str], Doc]]~~ |
 | `batch_size`       | Default batch size for [`pipe`](#pipe) and [`evaluate`](#evaluate). Defaults to `1000`. ~~int~~                          |
 
-## Language.from_config {#from_config tag="classmethod" new="3"}
+## Language.from_config {id="from_config",tag="classmethod",version="3"}
 
 Create a `Language` object from a loaded config. Will set up the tokenizer and
 language data, add pipeline components based on the pipeline and add pipeline
@@ -76,7 +76,7 @@ spaCy loads a model under the hood based on its
 | `validate`                            | Whether to validate the component config and arguments against the types expected by the factory. Defaults to `True`. ~~bool~~                                                                                                                                                                                     |
 | **RETURNS**                           | The initialized object. ~~Language~~                                                                                                                                                                                                                                                                               |
 
-## Language.component {#component tag="classmethod" new="3"}
+## Language.component {id="component",tag="classmethod",version="3"}
 
 Register a custom pipeline component under a given name. This allows
 initializing the component by name using
@@ -112,7 +112,7 @@ decorator. For more details and examples, see the
 | `retokenizes`  | Whether the component changes tokenization. Used for [pipe analysis](/usage/processing-pipelines#analysis). ~~bool~~                                               |
 | `func`         | Optional function if not used as a decorator. ~~Optional[Callable[[Doc], Doc]]~~                                                                                   |
 
-## Language.factory {#factory tag="classmethod"}
+## Language.factory {id="factory",tag="classmethod"}
 
 Register a custom pipeline component factory under a given name. This allows
 initializing the component by name using
@@ -159,7 +159,7 @@ examples, see the
 | `default_score_weights` | The scores to report during training, and their default weight towards the final score used to select the best model. Weights should sum to `1.0` per component and will be combined and normalized for the whole pipeline. If a weight is set to `None`, the score will not be logged or weighted. ~~Dict[str, Optional[float]]~~ |
 | `func`                  | Optional function if not used as a decorator. ~~Optional[Callable[[...], Callable[[Doc], Doc]]]~~                                                                                                                                                                                                                                  |
 
-## Language.\_\_call\_\_ {#call tag="method"}
+## Language.\_\_call\_\_ {id="call",tag="method"}
 
 Apply the pipeline to some text. The text can span multiple sentences, and can
 contain arbitrary whitespace. Alignment into the original string is preserved.
@@ -182,7 +182,7 @@ skipped, but the rest of the pipeline is run.
 | `component_cfg` | Optional dictionary of keyword arguments for components, keyed by component names. Defaults to `None`. ~~Optional[Dict[str, Dict[str, Any]]]~~ |
 | **RETURNS**     | A container for accessing the annotations. ~~Doc~~                                                                                             |
 
-## Language.pipe {#pipe tag="method"}
+## Language.pipe {id="pipe",tag="method"}
 
 Process texts as a stream, and yield `Doc` objects in order. This is usually
 more efficient than processing texts one-by-one.
@@ -209,7 +209,7 @@ tokenization is skipped but the rest of the pipeline is run.
 | `n_process`     | Number of processors to use. Defaults to `1`. ~~int~~                                                                                                               |
 | **YIELDS**      | Documents in the order of the original text. ~~Doc~~                                                                                                                |
 
-## Language.set_error_handler {#set_error_handler tag="method" new="3"}
+## Language.set_error_handler {id="set_error_handler",tag="method",version="3"}
 
 Define a callback that will be invoked when an error is thrown during processing
 of one or more documents. Specifically, this function will call
@@ -231,7 +231,7 @@ being processed, and the original error.
 | --------------- | -------------------------------------------------------------------------------------------------------------- |
 | `error_handler` | A function that performs custom error handling. ~~Callable[[str, Callable[[Doc], Doc], List[Doc], Exception]~~ |
 
-## Language.initialize {#initialize tag="method" new="3"}
+## Language.initialize {id="initialize",tag="method",version="3"}
 
 Initialize the pipeline for training and return an
 [`Optimizer`](https://thinc.ai/docs/api-optimizers). Under the hood, it uses the
@@ -282,7 +282,7 @@ objects.
 | `sgd`          | An optimizer. Will be created via [`create_optimizer`](#create_optimizer) if not set. ~~Optional[Optimizer]~~                                            |
 | **RETURNS**    | The optimizer. ~~Optimizer~~                                                                                                                             |
 
-## Language.resume_training {#resume_training tag="method,experimental" new="3"}
+## Language.resume_training {id="resume_training",tag="method,experimental",version="3"}
 
 Continue training a trained pipeline. Create and return an optimizer, and
 initialize "rehearsal" for any pipeline component that has a `rehearse` method.
@@ -304,7 +304,7 @@ a batch of [Example](/api/example) objects.
 | `sgd`          | An optimizer. Will be created via [`create_optimizer`](#create_optimizer) if not set. ~~Optional[Optimizer]~~ |
 | **RETURNS**    | The optimizer. ~~Optimizer~~                                                                                  |
 
-## Language.update {#update tag="method"}
+## Language.update {id="update",tag="method"}
 
 Update the models in the pipeline.
 
@@ -342,7 +342,7 @@ and custom registered functions if needed. See the
 | `component_cfg` | Optional dictionary of keyword arguments for components, keyed by component names. Defaults to `None`. ~~Optional[Dict[str, Dict[str, Any]]]~~ |
 | **RETURNS**     | The updated `losses` dictionary. ~~Dict[str, float]~~                                                                                          |
 
-## Language.rehearse {#rehearse tag="method,experimental" new="3"}
+## Language.rehearse {id="rehearse",tag="method,experimental",version="3"}
 
 Perform a "rehearsal" update from a batch of data. Rehearsal updates teach the
 current model to make predictions similar to an initial model, to try to address
@@ -364,7 +364,7 @@ the "catastrophic forgetting" problem. This feature is experimental.
 | `losses`       | Dictionary to update with the loss, keyed by pipeline component. ~~Optional[Dict[str, float]]~~               |
 | **RETURNS**    | The updated `losses` dictionary. ~~Dict[str, float]~~                                                         |
 
-## Language.evaluate {#evaluate tag="method"}
+## Language.evaluate {id="evaluate",tag="method"}
 
 Evaluate a pipeline's components.
 
@@ -392,7 +392,7 @@ objects instead of tuples of `Doc` and `GoldParse` objects.
 | `scorer_cfg`    | Optional dictionary of keyword arguments for the `Scorer`. Defaults to `None`. ~~Optional[Dict[str, Any]]~~                                    |
 | **RETURNS**     | A dictionary of evaluation scores. ~~Dict[str, Union[float, Dict[str, float]]]~~                                                               |
 
-## Language.use_params {#use_params tag="contextmanager, method"}
+## Language.use_params {id="use_params",tag="contextmanager, method"}
 
 Replace weights of models in the pipeline with those provided in the params
 dictionary. Can be used as a context manager, in which case, models go back to
@@ -409,7 +409,7 @@ their original weights after the block.
 | -------- | ------------------------------------------------------ |
 | `params` | A dictionary of parameters keyed by model ID. ~~dict~~ |
 
-## Language.add_pipe {#add_pipe tag="method" new="2"}
+## Language.add_pipe {id="add_pipe",tag="method",version="2"}
 
 Add a component to the processing pipeline. Expects a name that maps to a
 component factory registered using
@@ -458,7 +458,7 @@ component, adds it to the pipeline and returns it.
 | `validate` <Tag variant="new">3</Tag> | Whether to validate the component config and arguments against the types expected by the factory. Defaults to `True`. ~~bool~~                                                                                                                                                           |
 | **RETURNS**                           | The pipeline component. ~~Callable[[Doc], Doc]~~                                                                                                                                                                                                                                         |
 
-## Language.create_pipe {#create_pipe tag="method" new="2"}
+## Language.create_pipe {id="create_pipe",tag="method",version="2"}
 
 Create a pipeline component from a factory.
 
@@ -487,7 +487,7 @@ To create a component and add it to the pipeline, you should always use
 | `validate` <Tag variant="new">3</Tag> | Whether to validate the component config and arguments against the types expected by the factory. Defaults to `True`. ~~bool~~                                              |
 | **RETURNS**                           | The pipeline component. ~~Callable[[Doc], Doc]~~                                                                                                                            |
 
-## Language.has_factory {#has_factory tag="classmethod" new="3"}
+## Language.has_factory {id="has_factory",tag="classmethod",version="3"}
 
 Check whether a factory name is registered on the `Language` class or subclass.
 Will check for
@@ -514,7 +514,7 @@ the `Language` base class, available to all subclasses.
 | `name`      | Name of the pipeline factory to check. ~~str~~                      |
 | **RETURNS** | Whether a factory of that name is registered on the class. ~~bool~~ |
 
-## Language.has_pipe {#has_pipe tag="method" new="2"}
+## Language.has_pipe {id="has_pipe",tag="method",version="2"}
 
 Check whether a component is present in the pipeline. Equivalent to
 `name in nlp.pipe_names`.
@@ -536,7 +536,7 @@ Check whether a component is present in the pipeline. Equivalent to
 | `name`      | Name of the pipeline component to check. ~~str~~                  |
 | **RETURNS** | Whether a component of that name exists in the pipeline. ~~bool~~ |
 
-## Language.get_pipe {#get_pipe tag="method" new="2"}
+## Language.get_pipe {id="get_pipe",tag="method",version="2"}
 
 Get a pipeline component for a given component name.
 
@@ -552,7 +552,7 @@ Get a pipeline component for a given component name.
 | `name`      | Name of the pipeline component to get. ~~str~~   |
 | **RETURNS** | The pipeline component. ~~Callable[[Doc], Doc]~~ |
 
-## Language.replace_pipe {#replace_pipe tag="method" new="2"}
+## Language.replace_pipe {id="replace_pipe",tag="method",version="2"}
 
 Replace a component in the pipeline and return the new component.
 
@@ -580,7 +580,7 @@ and instead expects the **name of a component factory** registered using
 | `validate` <Tag variant="new">3</Tag> | Whether to validate the component config and arguments against the types expected by the factory. Defaults to `True`. ~~bool~~                                     |
 | **RETURNS**                           | The new pipeline component. ~~Callable[[Doc], Doc]~~                                                                                                               |
 
-## Language.rename_pipe {#rename_pipe tag="method" new="2"}
+## Language.rename_pipe {id="rename_pipe",tag="method",version="2"}
 
 Rename a component in the pipeline. Useful to create custom names for
 pre-defined and pre-loaded components. To change the default name of a component
@@ -598,7 +598,7 @@ added to the pipeline, you can also use the `name` argument on
 | `old_name` | Name of the component to rename. ~~str~~ |
 | `new_name` | New name of the component. ~~str~~       |
 
-## Language.remove_pipe {#remove_pipe tag="method" new="2"}
+## Language.remove_pipe {id="remove_pipe",tag="method",version="2"}
 
 Remove a component from the pipeline. Returns the removed component name and
 component function.
@@ -615,7 +615,7 @@ component function.
 | `name`      | Name of the component to remove. ~~str~~                                                   |
 | **RETURNS** | A `(name, component)` tuple of the removed component. ~~Tuple[str, Callable[[Doc], Doc]]~~ |
 
-## Language.disable_pipe {#disable_pipe tag="method" new="3"}
+## Language.disable_pipe {id="disable_pipe",tag="method",version="3"}
 
 Temporarily disable a pipeline component so it's not run as part of the
 pipeline. Disabled components are listed in
@@ -641,7 +641,7 @@ does nothing.
 | ------ | ----------------------------------------- |
 | `name` | Name of the component to disable. ~~str~~ |
 
-## Language.enable_pipe {#enable_pipe tag="method" new="3"}
+## Language.enable_pipe {id="enable_pipe",tag="method",version="3"}
 
 Enable a previously disabled component (e.g. via
 [`Language.disable_pipes`](/api/language#disable_pipes)) so it's run as part of
@@ -663,7 +663,7 @@ already enabled, this method does nothing.
 | ------ | ---------------------------------------- |
 | `name` | Name of the component to enable. ~~str~~ |
 
-## Language.select_pipes {#select_pipes tag="contextmanager, method" new="3"}
+## Language.select_pipes {id="select_pipes",tag="contextmanager, method",version="3"}
 
 Disable one or more pipeline components. If used as a context manager, the
 pipeline will be restored to the initial state at the end of the block.
@@ -706,7 +706,7 @@ As of spaCy v3.0, the `disable_pipes` method has been renamed to `select_pipes`:
 | `enable`       | Name(s) of pipeline component(s) that will not be disabled. ~~Optional[Union[str, Iterable[str]]]~~    |
 | **RETURNS**    | The disabled pipes that can be restored by calling the object's `.restore()` method. ~~DisabledPipes~~ |
 
-## Language.get_factory_meta {#get_factory_meta tag="classmethod" new="3"}
+## Language.get_factory_meta {id="get_factory_meta",tag="classmethod",version="3"}
 
 Get the factory meta information for a given pipeline component name. Expects
 the name of the component **factory**. The factory meta is an instance of the
@@ -728,7 +728,7 @@ information about the component and its default provided by the
 | `name`      | The factory name. ~~str~~         |
 | **RETURNS** | The factory meta. ~~FactoryMeta~~ |
 
-## Language.get_pipe_meta {#get_pipe_meta tag="method" new="3"}
+## Language.get_pipe_meta {id="get_pipe_meta",tag="method",version="3"}
 
 Get the factory meta information for a given pipeline component name. Expects
 the name of the component **instance** in the pipeline. The factory meta is an
@@ -751,7 +751,7 @@ contains the information about the component and its default provided by the
 | `name`      | The pipeline component name. ~~str~~ |
 | **RETURNS** | The factory meta. ~~FactoryMeta~~    |
 
-## Language.analyze_pipes {#analyze_pipes tag="method" new="3"}
+## Language.analyze_pipes {id="analyze_pipes",tag="method",version="3"}
 
 Analyze the current pipeline components and show a summary of the attributes
 they assign and require, and the scores they set. The data is based on the
@@ -780,8 +780,7 @@ doesn't, the pipeline analysis won't catch that.
 
 <Accordion title="Example output" spaced>
 
-```json
+```json {title="Structured"}
-### Structured
 {
   "summary": {
     "tagger": {
@@ -799,7 +798,12 @@ doesn't, the pipeline analysis won't catch that.
   },
   "problems": {
     "tagger": [],
-    "entity_linker": ["doc.ents", "doc.sents", "token.ent_iob", "token.ent_type"]
+    "entity_linker": [
+      "doc.ents",
+      "doc.sents",
+      "token.ent_iob",
+      "token.ent_type"
+    ]
   },
   "attrs": {
     "token.ent_iob": { "assigns": [], "requires": ["entity_linker"] },
@@ -840,7 +844,7 @@ token.ent_iob, token.ent_type
 | `pretty`       | Pretty-print the results as a table. Defaults to `False`. ~~bool~~                                                                                                                                                                          |
 | **RETURNS**    | Dictionary containing the pipe analysis, keyed by `"summary"` (component meta by pipe), `"problems"` (attribute names by pipe) and `"attrs"` (pipes that assign and require an attribute, keyed by attribute). ~~Optional[Dict[str, Any]]~~ |
 
-## Language.replace_listeners {#replace_listeners tag="method" new="3"}
+## Language.replace_listeners {id="replace_listeners",tag="method",version="3"}
 
 Find [listener layers](/usage/embeddings-transformers#embedding-layers)
 (connecting to a shared token-to-vector embedding component) of a given pipeline
@@ -885,7 +889,7 @@ when loading a config with
 | `pipe_name`    | Name of pipeline component to replace listeners for. ~~str~~                                                                                                                                                                                                                                                                                                                                                                           |
 | `listeners`    | The paths to the listeners, relative to the component config, e.g. `["model.tok2vec"]`. Typically, implementations will only connect to one tok2vec component, `model.tok2vec`, but in theory, custom models can use multiple listeners. The value here can either be an empty list to not replace any listeners, or a _complete_ list of the paths to all listener layers used by the model that should be replaced.~~Iterable[str]~~ |
 
-## Language.meta {#meta tag="property"}
+## Language.meta {id="meta",tag="property"}
 
 Meta data for the `Language` class, including name, version, data sources,
 license, author information and more. If a trained pipeline is loaded, this
@@ -911,7 +915,7 @@ information is expressed in the [`config.cfg`](/api/data-formats#config).
 | ----------- | --------------------------------- |
 | **RETURNS** | The meta data. ~~Dict[str, Any]~~ |
 
-## Language.config {#config tag="property" new="3"}
+## Language.config {id="config",tag="property",version="3"}
 
 Export a trainable [`config.cfg`](/api/data-formats#config) for the current
 `nlp` object. Includes the current pipeline, all configs used to create the
@@ -932,7 +936,7 @@ subclass of the built-in `dict`. It supports the additional methods `to_disk`
 | ----------- | ---------------------- |
 | **RETURNS** | The config. ~~Config~~ |
 
-## Language.to_disk {#to_disk tag="method" new="2"}
+## Language.to_disk {id="to_disk",tag="method",version="2"}
 
 Save the current state to a directory. Under the hood, this method delegates to
 the `to_disk` methods of the individual pipeline components, if available. This
@@ -951,7 +955,7 @@ will be saved to disk.
 | _keyword-only_ |                                                                                                                                            |
 | `exclude`      | Names of pipeline components or [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~                                |
 
-## Language.from_disk {#from_disk tag="method" new="2"}
+## Language.from_disk {id="from_disk",tag="method",version="2"}
 
 Loads state from a directory, including all data that was saved with the
 `Language` object. Modifies the object in place and returns it.
@@ -984,7 +988,7 @@ you want to load a serialized pipeline from a directory, you should use
 | `exclude`      | Names of pipeline components or [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The modified `Language` object. ~~Language~~                                                                |
 
-## Language.to_bytes {#to_bytes tag="method"}
+## Language.to_bytes {id="to_bytes",tag="method"}
 
 Serialize the current state to a binary string.
 
@@ -1000,7 +1004,7 @@ Serialize the current state to a binary string.
 | `exclude`      | Names of pipeline components or [serialization fields](#serialization-fields) to exclude. ~~iterable~~ |
 | **RETURNS**    | The serialized form of the `Language` object. ~~bytes~~                                                |
 
-## Language.from_bytes {#from_bytes tag="method"}
+## Language.from_bytes {id="from_bytes",tag="method"}
 
 Load state from a binary string. Note that this method is commonly used via the
 subclasses like `English` or `German` to make language-specific functionality
@@ -1028,7 +1032,7 @@ details.
 | `exclude`      | Names of pipeline components or [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The `Language` object. ~~Language~~                                                                         |
 
-## Attributes {#attributes}
+## Attributes {id="attributes"}
 
 | Name                                         | Description                                                                                                                                    |
 | -------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- |
@@ -1046,7 +1050,7 @@ details.
 | `disabled` <Tag variant="new">3</Tag>        | Names of components that are currently disabled and don't run as part of the pipeline. ~~List[str]~~                                           |
 | `path`                                       | Path to the pipeline data directory, if a pipeline is loaded from a path or package. Otherwise `None`. ~~Optional[Path]~~                      |
 
-## Class attributes {#class-attributes}
+## Class attributes {id="class-attributes"}
 
 | Name             | Description                                                                                                                                                                       |
 | ---------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
@@ -1054,7 +1058,7 @@ details.
 | `lang`           | [IETF language tag](https://www.w3.org/International/articles/language-tags/), such as 'en' for English. ~~str~~                                                                  |
 | `default_config` | Base [config](/usage/training#config) to use for [Language.config](/api/language#config). Defaults to [`default_config.cfg`](%%GITHUB_SPACY/spacy/default_config.cfg). ~~Config~~ |
 
-## Defaults {#defaults}
+## Defaults {id="defaults"}
 
 The following attributes can be set on the `Language.Defaults` class to
 customize the default language data:
@@ -1097,7 +1101,7 @@ customize the default language data:
 | `writing_system`                  | Information about the language's writing system, available via `Vocab.writing_system`. Defaults to: `{"direction": "ltr", "has_case": True, "has_letters": True}.`.<br />**Example:** [`zh/__init__.py`](%%GITHUB_SPACY/spacy/lang/zh/__init__.py) ~~Dict[str, Any]~~                                            |
 | `config`                          | Default [config](/usage/training#config) added to `nlp.config`. This can include references to custom tokenizers or lemmatizers.<br />**Example:** [`zh/__init__.py`](%%GITHUB_SPACY/spacy/lang/zh/__init__.py) ~~Config~~                                                                                       |
 
-## Serialization fields {#serialization-fields}
+## Serialization fields {id="serialization-fields"}
 
 During serialization, spaCy will export several data fields used to restore
 different aspects of the object. If needed, you can exclude them from
@@ -1117,7 +1121,7 @@ serialization by passing in the string names via the `exclude` argument.
 | `meta`      | The meta data, available as [`Language.meta`](/api/language#meta). |
 | ...         | String names of pipeline components, e.g. `"ner"`.                 |
 
-## FactoryMeta {#factorymeta new="3" tag="dataclass"}
+## FactoryMeta {id="factorymeta",version="3",tag="dataclass"}
 
 The `FactoryMeta` contains the information about the component and its default
 provided by the [`@Language.component`](/api/language#component) or

website/docs/api/legacy.mdx

@@ -12,11 +12,11 @@ functions that may still be used in projects.
 You can find the detailed documentation of each such legacy function on this
 page.
 
-## Architectures {#architectures}
+## Architectures {id="architectures"}
 
 These functions are available from `@spacy.registry.architectures`.
 
-### spacy.Tok2Vec.v1 {#Tok2Vec_v1}
+### spacy.Tok2Vec.v1 {id="Tok2Vec_v1"}
 
 The `spacy.Tok2Vec.v1` architecture was expecting an `encode` model of type
 `Model[Floats2D, Floats2D]` such as `spacy.MaxoutWindowEncoder.v1` or
@@ -48,7 +48,7 @@ blog post for background.
 | `encode`    | Encode context into the embeddings, using an architecture such as a CNN, BiLSTM or transformer. For example, [MaxoutWindowEncoder.v1](/api/legacy#MaxoutWindowEncoder_v1). ~~Model[Floats2d, Floats2d]~~                         |
 | **CREATES** | The model using the architecture. ~~Model[List[Doc], List[Floats2d]]~~                                                                                                                                                           |
 
-### spacy.MaxoutWindowEncoder.v1 {#MaxoutWindowEncoder_v1}
+### spacy.MaxoutWindowEncoder.v1 {id="MaxoutWindowEncoder_v1"}
 
 The `spacy.MaxoutWindowEncoder.v1` architecture was producing a model of type
 `Model[Floats2D, Floats2D]`. Since `spacy.MaxoutWindowEncoder.v2`, this has been
@@ -76,7 +76,7 @@ and residual connections.
 | `depth`         | The number of convolutional layers. Recommended value is `4`. ~~int~~                                                                                                                                          |
 | **CREATES**     | The model using the architecture. ~~Model[Floats2d, Floats2d]~~                                                                                                                                                |
 
-### spacy.MishWindowEncoder.v1 {#MishWindowEncoder_v1}
+### spacy.MishWindowEncoder.v1 {id="MishWindowEncoder_v1"}
 
 The `spacy.MishWindowEncoder.v1` architecture was producing a model of type
 `Model[Floats2D, Floats2D]`. Since `spacy.MishWindowEncoder.v2`, this has been
@@ -103,24 +103,24 @@ and residual connections.
 | `depth`       | The number of convolutional layers. Recommended value is `4`. ~~int~~                                                                                                                                          |
 | **CREATES**   | The model using the architecture. ~~Model[Floats2d, Floats2d]~~                                                                                                                                                |
 
-### spacy.HashEmbedCNN.v1 {#HashEmbedCNN_v1}
+### spacy.HashEmbedCNN.v1 {id="HashEmbedCNN_v1"}
 
 Identical to [`spacy.HashEmbedCNN.v2`](/api/architectures#HashEmbedCNN) except
 using [`spacy.StaticVectors.v1`](#StaticVectors_v1) if vectors are included.
 
-### spacy.MultiHashEmbed.v1 {#MultiHashEmbed_v1}
+### spacy.MultiHashEmbed.v1 {id="MultiHashEmbed_v1"}
 
 Identical to [`spacy.MultiHashEmbed.v2`](/api/architectures#MultiHashEmbed)
 except with [`spacy.StaticVectors.v1`](#StaticVectors_v1) if vectors are
 included.
 
-### spacy.CharacterEmbed.v1 {#CharacterEmbed_v1}
+### spacy.CharacterEmbed.v1 {id="CharacterEmbed_v1"}
 
 Identical to [`spacy.CharacterEmbed.v2`](/api/architectures#CharacterEmbed)
 except using [`spacy.StaticVectors.v1`](#StaticVectors_v1) if vectors are
 included.
 
-### spacy.TextCatEnsemble.v1 {#TextCatEnsemble_v1}
+### spacy.TextCatEnsemble.v1 {id="TextCatEnsemble_v1"}
 
 The `spacy.TextCatEnsemble.v1` architecture built an internal `tok2vec` and
 `linear_model`. Since `spacy.TextCatEnsemble.v2`, this has been refactored so
@@ -158,7 +158,7 @@ network has an internal CNN Tok2Vec layer and uses attention.
 | `nO`                 | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `initialize` is called. ~~Optional[int]~~ |
 | **CREATES**          | The model using the architecture. ~~Model[List[Doc], Floats2d]~~                                                                                                                               |
 
-### spacy.TextCatCNN.v1 {#TextCatCNN_v1}
+### spacy.TextCatCNN.v1 {id="TextCatCNN_v1"}
 
 Since `spacy.TextCatCNN.v2`, this architecture has become resizable, which means
 that you can add labels to a previously trained textcat. `TextCatCNN` v1 did not
@@ -194,7 +194,7 @@ architecture is usually less accurate than the ensemble, but runs faster.
 | `nO`                | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `initialize` is called. ~~Optional[int]~~ |
 | **CREATES**         | The model using the architecture. ~~Model[List[Doc], Floats2d]~~                                                                                                                               |
 
-### spacy.TextCatBOW.v1 {#TextCatBOW_v1}
+### spacy.TextCatBOW.v1 {id="TextCatBOW_v1"}
 
 Since `spacy.TextCatBOW.v2`, this architecture has become resizable, which means
 that you can add labels to a previously trained textcat. `TextCatBOW` v1 did not
@@ -222,17 +222,17 @@ the others, but may not be as accurate, especially if texts are short.
 | `nO`                | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `initialize` is called. ~~Optional[int]~~ |
 | **CREATES**         | The model using the architecture. ~~Model[List[Doc], Floats2d]~~                                                                                                                               |
 
-### spacy.TransitionBasedParser.v1 {#TransitionBasedParser_v1}
+### spacy.TransitionBasedParser.v1 {id="TransitionBasedParser_v1"}
 
 Identical to
 [`spacy.TransitionBasedParser.v2`](/api/architectures#TransitionBasedParser)
 except the `use_upper` was set to `True` by default.
 
-## Layers {#layers}
+## Layers {id="layers"}
 
 These functions are available from `@spacy.registry.layers`.
 
-### spacy.StaticVectors.v1 {#StaticVectors_v1}
+### spacy.StaticVectors.v1 {id="StaticVectors_v1"}
 
 Identical to [`spacy.StaticVectors.v2`](/api/architectures#StaticVectors) except
 for the handling of tokens without vectors.
@@ -246,11 +246,11 @@ added to an existing vectors table. See more details in
 
 </Infobox>
 
-## Loggers {#loggers}
+## Loggers {id="loggers"}
 
 These functions are available from `@spacy.registry.loggers`.
 
-### spacy.ConsoleLogger.v1 {#ConsoleLogger_v1}
+### spacy.ConsoleLogger.v1 {id="ConsoleLogger_v1"}
 
 > #### Example config
 >
@@ -264,7 +264,7 @@ Writes the results of a training step to the console in a tabular format.
 
 <Accordion title="Example console output" spaced>
 
-```cli
+```bash
 $ python -m spacy train config.cfg
 ```
 

website/docs/api/lemmatizer.mdx

@@ -2,7 +2,7 @@
 title: Lemmatizer
 tag: class
 source: spacy/pipeline/lemmatizer.py
-new: 3
+version: 3
 teaser: 'Pipeline component for lemmatization'
 api_string_name: lemmatizer
 api_trainable: false
@@ -32,7 +32,7 @@ available in the pipeline and runs _before_ the lemmatizer.
 
 </Infobox>
 
-## Assigned Attributes {#assigned-attributes}
+## Assigned Attributes {id="assigned-attributes"}
 
 Lemmas generated by rules or predicted will be saved to `Token.lemma`.
 
@@ -94,7 +94,7 @@ libraries (`pymorphy3`).
 %%GITHUB_SPACY/spacy/pipeline/lemmatizer.py
 ```
 
-## Lemmatizer.\_\_init\_\_ {#init tag="method"}
+## Lemmatizer.\_\_init\_\_ {id="init",tag="method"}
 
 > #### Example
 >
@@ -120,7 +120,7 @@ shortcut for this and instantiate the component using its string name and
 | mode           | The lemmatizer mode, e.g. `"lookup"` or `"rule"`. Defaults to `"lookup"`. ~~str~~                   |
 | overwrite      | Whether to overwrite existing lemmas. ~~bool~~                                                      |
 
-## Lemmatizer.\_\_call\_\_ {#call tag="method"}
+## Lemmatizer.\_\_call\_\_ {id="call",tag="method"}
 
 Apply the pipe to one document. The document is modified in place, and returned.
 This usually happens under the hood when the `nlp` object is called on a text
@@ -140,7 +140,7 @@ and all pipeline components are applied to the `Doc` in order.
 | `doc`       | The document to process. ~~Doc~~ |
 | **RETURNS** | The processed document. ~~Doc~~  |
 
-## Lemmatizer.pipe {#pipe tag="method"}
+## Lemmatizer.pipe {id="pipe",tag="method"}
 
 Apply the pipe to a stream of documents. This usually happens under the hood
 when the `nlp` object is called on a text and all pipeline components are
@@ -161,7 +161,7 @@ applied to the `Doc` in order.
 | `batch_size`   | The number of documents to buffer. Defaults to `128`. ~~int~~ |
 | **YIELDS**     | The processed documents in order. ~~Doc~~                     |
 
-## Lemmatizer.initialize {#initialize tag="method"}
+## Lemmatizer.initialize {id="initialize",tag="method"}
 
 Initialize the lemmatizer and load any data resources. This method is typically
 called by [`Language.initialize`](/api/language#initialize) and lets you
@@ -192,7 +192,7 @@ training. At runtime, all data is loaded from disk.
 | `nlp`          | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~                                                                                                                                                                                                                |
 | `lookups`      | The lookups object containing the tables such as `"lemma_rules"`, `"lemma_index"`, `"lemma_exc"` and `"lemma_lookup"`. If `None`, default tables are loaded from [`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data). Defaults to `None`. ~~Optional[Lookups]~~ |
 
-## Lemmatizer.lookup_lemmatize {#lookup_lemmatize tag="method"}
+## Lemmatizer.lookup_lemmatize {id="lookup_lemmatize",tag="method"}
 
 Lemmatize a token using a lookup-based approach. If no lemma is found, the
 original string is returned.
@@ -202,7 +202,7 @@ original string is returned.
 | `token`     | The token to lemmatize. ~~Token~~                   |
 | **RETURNS** | A list containing one or more lemmas. ~~List[str]~~ |
 
-## Lemmatizer.rule_lemmatize {#rule_lemmatize tag="method"}
+## Lemmatizer.rule_lemmatize {id="rule_lemmatize",tag="method"}
 
 Lemmatize a token using a rule-based approach. Typically relies on POS tags.
 
@@ -211,7 +211,7 @@ Lemmatize a token using a rule-based approach. Typically relies on POS tags.
 | `token`     | The token to lemmatize. ~~Token~~                   |
 | **RETURNS** | A list containing one or more lemmas. ~~List[str]~~ |
 
-## Lemmatizer.is_base_form {#is_base_form tag="method"}
+## Lemmatizer.is_base_form {id="is_base_form",tag="method"}
 
 Check whether we're dealing with an uninflected paradigm, so we can avoid
 lemmatization entirely.
@@ -221,7 +221,7 @@ lemmatization entirely.
 | `token`     | The token to analyze. ~~Token~~                                                                                  |
 | **RETURNS** | Whether the token's attributes (e.g., part-of-speech tag, morphological features) describe a base form. ~~bool~~ |
 
-## Lemmatizer.get_lookups_config {#get_lookups_config tag="classmethod"}
+## Lemmatizer.get_lookups_config {id="get_lookups_config",tag="classmethod"}
 
 Returns the lookups configuration settings for a given mode for use in
 [`Lemmatizer.load_lookups`](/api/lemmatizer#load_lookups).
@@ -231,7 +231,7 @@ Returns the lookups configuration settings for a given mode for use in
 | `mode`      | The lemmatizer mode. ~~str~~                                                           |
 | **RETURNS** | The required table names and the optional table names. ~~Tuple[List[str], List[str]]~~ |
 
-## Lemmatizer.to_disk {#to_disk tag="method"}
+## Lemmatizer.to_disk {id="to_disk",tag="method"}
 
 Serialize the pipe to disk.
 
@@ -248,7 +248,7 @@ Serialize the pipe to disk.
 | _keyword-only_ |                                                                                                                                            |
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~                                                |
 
-## Lemmatizer.from_disk {#from_disk tag="method"}
+## Lemmatizer.from_disk {id="from_disk",tag="method"}
 
 Load the pipe from disk. Modifies the object in place and returns it.
 
@@ -266,7 +266,7 @@ Load the pipe from disk. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~     |
 | **RETURNS**    | The modified `Lemmatizer` object. ~~Lemmatizer~~                                                |
 
-## Lemmatizer.to_bytes {#to_bytes tag="method"}
+## Lemmatizer.to_bytes {id="to_bytes",tag="method"}
 
 > #### Example
 >
@@ -283,7 +283,7 @@ Serialize the pipe to a bytestring.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The serialized form of the `Lemmatizer` object. ~~bytes~~                                   |
 
-## Lemmatizer.from_bytes {#from_bytes tag="method"}
+## Lemmatizer.from_bytes {id="from_bytes",tag="method"}
 
 Load the pipe from a bytestring. Modifies the object in place and returns it.
 
@@ -302,7 +302,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The `Lemmatizer` object. ~~Lemmatizer~~                                                     |
 
-## Attributes {#attributes}
+## Attributes {id="attributes"}
 
 | Name      | Description                                 |
 | --------- | ------------------------------------------- |
@@ -310,7 +310,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
 | `lookups` | The lookups object. ~~Lookups~~             |
 | `mode`    | The lemmatizer mode. ~~str~~                |
 
-## Serialization fields {#serialization-fields}
+## Serialization fields {id="serialization-fields"}
 
 During serialization, spaCy will export several data fields used to restore
 different aspects of the object. If needed, you can exclude them from

website/docs/api/lexeme.mdx

@@ -9,7 +9,7 @@ A `Lexeme` has no string context – it's a word type, as opposed to a word toke
 It therefore has no part-of-speech tag, dependency parse, or lemma (if
 lemmatization depends on the part-of-speech tag).
 
-## Lexeme.\_\_init\_\_ {#init tag="method"}
+## Lexeme.\_\_init\_\_ {id="init",tag="method"}
 
 Create a `Lexeme` object.
 
@@ -18,7 +18,7 @@ Create a `Lexeme` object.
 | `vocab` | The parent vocabulary. ~~Vocab~~   |
 | `orth`  | The orth id of the lexeme. ~~int~~ |
 
-## Lexeme.set_flag {#set_flag tag="method"}
+## Lexeme.set_flag {id="set_flag",tag="method"}
 
 Change the value of a boolean flag.
 
@@ -34,7 +34,7 @@ Change the value of a boolean flag.
 | `flag_id` | The attribute ID of the flag to set. ~~int~~ |
 | `value`   | The new value of the flag. ~~bool~~          |
 
-## Lexeme.check_flag {#check_flag tag="method"}
+## Lexeme.check_flag {id="check_flag",tag="method"}
 
 Check the value of a boolean flag.
 
@@ -51,7 +51,7 @@ Check the value of a boolean flag.
 | `flag_id`   | The attribute ID of the flag to query. ~~int~~ |
 | **RETURNS** | The value of the flag. ~~bool~~                |
 
-## Lexeme.similarity {#similarity tag="method" model="vectors"}
+## Lexeme.similarity {id="similarity",tag="method",model="vectors"}
 
 Compute a semantic similarity estimate. Defaults to cosine over vectors.
 
@@ -70,7 +70,7 @@ Compute a semantic similarity estimate. Defaults to cosine over vectors.
 | other       | The object to compare with. By default, accepts `Doc`, `Span`, `Token` and `Lexeme` objects. ~~Union[Doc, Span, Token, Lexeme]~~ |
 | **RETURNS** | A scalar similarity score. Higher is more similar. ~~float~~                                                                     |
 
-## Lexeme.has_vector {#has_vector tag="property" model="vectors"}
+## Lexeme.has_vector {id="has_vector",tag="property",model="vectors"}
 
 A boolean value indicating whether a word vector is associated with the lexeme.
 
@@ -85,7 +85,7 @@ A boolean value indicating whether a word vector is associated with the lexeme.
 | ----------- | ------------------------------------------------------- |
 | **RETURNS** | Whether the lexeme has a vector data attached. ~~bool~~ |
 
-## Lexeme.vector {#vector tag="property" model="vectors"}
+## Lexeme.vector {id="vector",tag="property",model="vectors"}
 
 A real-valued meaning representation.
 
@@ -101,7 +101,7 @@ A real-valued meaning representation.
 | ----------- | ------------------------------------------------------------------------------------------------ |
 | **RETURNS** | A 1-dimensional array representing the lexeme's vector. ~~numpy.ndarray[ndim=1, dtype=float32]~~ |
 
-## Lexeme.vector_norm {#vector_norm tag="property" model="vectors"}
+## Lexeme.vector_norm {id="vector_norm",tag="property",model="vectors"}
 
 The L2 norm of the lexeme's vector representation.
 
@@ -119,7 +119,7 @@ The L2 norm of the lexeme's vector representation.
 | ----------- | --------------------------------------------------- |
 | **RETURNS** | The L2 norm of the vector representation. ~~float~~ |
 
-## Attributes {#attributes}
+## Attributes {id="attributes"}
 
 | Name             | Description                                                                                                                                                                                                                                                          |
 | ---------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
@@ -138,7 +138,7 @@ The L2 norm of the lexeme's vector representation.
 | `prefix`         | Length-N substring from the start of the word. Defaults to `N=1`. ~~int~~                                                                                                                                                                                            |
 | `prefix_`        | Length-N substring from the start of the word. Defaults to `N=1`. ~~str~~                                                                                                                                                                                            |
 | `suffix`         | Length-N substring from the end of the word. Defaults to `N=3`. ~~int~~                                                                                                                                                                                              |
-| `suffix_`        | Length-N substring from the start of the word. Defaults to `N=3`. ~~str~~                                                                                                                                                                                            |
+| `suffix_`        | Length-N substring from the end of the word. Defaults to `N=3`. ~~str~~                                                                                                                                                                                            |
 | `is_alpha`       | Does the lexeme consist of alphabetic characters? Equivalent to `lexeme.text.isalpha()`. ~~bool~~                                                                                                                                                                    |
 | `is_ascii`       | Does the lexeme consist of ASCII characters? Equivalent to `[any(ord(c) >= 128 for c in lexeme.text)]`. ~~bool~~                                                                                                                                                     |
 | `is_digit`       | Does the lexeme consist of digits? Equivalent to `lexeme.text.isdigit()`. ~~bool~~                                                                                                                                                                                   |

website/docs/api/lookups.mdx

@@ -3,7 +3,7 @@ title: Lookups
 teaser: A container for large lookup tables and dictionaries
 tag: class
 source: spacy/lookups.py
-new: 2.2
+version: 2.2
 ---
 
 This class allows convenient access to large lookup tables and dictionaries,
@@ -13,7 +13,7 @@ can be accessed before the pipeline components are applied (e.g. in the
 tokenizer and lemmatizer), as well as within the pipeline components via
 `doc.vocab.lookups`.
 
-## Lookups.\_\_init\_\_ {#init tag="method"}
+## Lookups.\_\_init\_\_ {id="init",tag="method"}
 
 Create a `Lookups` object.
 
@@ -24,7 +24,7 @@ Create a `Lookups` object.
 > lookups = Lookups()
 > ```
 
-## Lookups.\_\_len\_\_ {#len tag="method"}
+## Lookups.\_\_len\_\_ {id="len",tag="method"}
 
 Get the current number of tables in the lookups.
 
@@ -39,7 +39,7 @@ Get the current number of tables in the lookups.
 | ----------- | -------------------------------------------- |
 | **RETURNS** | The number of tables in the lookups. ~~int~~ |
 
-## Lookups.\_\contains\_\_ {#contains tag="method"}
+## Lookups.\_\_contains\_\_ {id="contains",tag="method"}
 
 Check if the lookups contain a table of a given name. Delegates to
 [`Lookups.has_table`](/api/lookups#has_table).
@@ -57,7 +57,7 @@ Check if the lookups contain a table of a given name. Delegates to
 | `name`      | Name of the table. ~~str~~                               |
 | **RETURNS** | Whether a table of that name is in the lookups. ~~bool~~ |
 
-## Lookups.tables {#tables tag="property"}
+## Lookups.tables {id="tables",tag="property"}
 
 Get the names of all tables in the lookups.
 
@@ -73,7 +73,7 @@ Get the names of all tables in the lookups.
 | ----------- | ------------------------------------------------- |
 | **RETURNS** | Names of the tables in the lookups. ~~List[str]~~ |
 
-## Lookups.add_table {#add_table tag="method"}
+## Lookups.add_table {id="add_table",tag="method"}
 
 Add a new table with optional data to the lookups. Raises an error if the table
 exists.
@@ -91,7 +91,7 @@ exists.
 | `data`      | Optional data to add to the table. ~~dict~~ |
 | **RETURNS** | The newly added table. ~~Table~~            |
 
-## Lookups.get_table {#get_table tag="method"}
+## Lookups.get_table {id="get_table",tag="method"}
 
 Get a table from the lookups. Raises an error if the table doesn't exist.
 
@@ -109,7 +109,7 @@ Get a table from the lookups. Raises an error if the table doesn't exist.
 | `name`      | Name of the table. ~~str~~ |
 | **RETURNS** | The table. ~~Table~~       |
 
-## Lookups.remove_table {#remove_table tag="method"}
+## Lookups.remove_table {id="remove_table",tag="method"}
 
 Remove a table from the lookups. Raises an error if the table doesn't exist.
 
@@ -127,7 +127,7 @@ Remove a table from the lookups. Raises an error if the table doesn't exist.
 | `name`      | Name of the table to remove. ~~str~~ |
 | **RETURNS** | The removed table. ~~Table~~         |
 
-## Lookups.has_table {#has_table tag="method"}
+## Lookups.has_table {id="has_table",tag="method"}
 
 Check if the lookups contain a table of a given name. Equivalent to
 [`Lookups.__contains__`](/api/lookups#contains).
@@ -145,7 +145,7 @@ Check if the lookups contain a table of a given name. Equivalent to
 | `name`      | Name of the table. ~~str~~                               |
 | **RETURNS** | Whether a table of that name is in the lookups. ~~bool~~ |
 
-## Lookups.to_bytes {#to_bytes tag="method"}
+## Lookups.to_bytes {id="to_bytes",tag="method"}
 
 Serialize the lookups to a bytestring.
 
@@ -159,7 +159,7 @@ Serialize the lookups to a bytestring.
 | ----------- | --------------------------------- |
 | **RETURNS** | The serialized lookups. ~~bytes~~ |
 
-## Lookups.from_bytes {#from_bytes tag="method"}
+## Lookups.from_bytes {id="from_bytes",tag="method"}
 
 Load the lookups from a bytestring.
 
@@ -176,7 +176,7 @@ Load the lookups from a bytestring.
 | `bytes_data` | The data to load from. ~~bytes~~ |
 | **RETURNS**  | The loaded lookups. ~~Lookups~~  |
 
-## Lookups.to_disk {#to_disk tag="method"}
+## Lookups.to_disk {id="to_disk",tag="method"}
 
 Save the lookups to a directory as `lookups.bin`. Expects a path to a directory,
 which will be created if it doesn't exist.
@@ -191,7 +191,7 @@ which will be created if it doesn't exist.
 | ------ | ------------------------------------------------------------------------------------------------------------------------------------------ |
 | `path` | A path to a directory, which will be created if it doesn't exist. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ |
 
-## Lookups.from_disk {#from_disk tag="method"}
+## Lookups.from_disk {id="from_disk",tag="method"}
 
 Load lookups from a directory containing a `lookups.bin`. Will skip loading if
 the file doesn't exist.
@@ -209,7 +209,7 @@ the file doesn't exist.
 | `path`      | A path to a directory. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ |
 | **RETURNS** | The loaded lookups. ~~Lookups~~                                                                 |
 
-## Table {#table tag="class, ordererddict"}
+## Table {id="table",tag="class, ordererddict"}
 
 A table in the lookups. Subclass of `OrderedDict` that implements a slightly
 more consistent and unified API and includes a Bloom filter to speed up missed
@@ -218,7 +218,7 @@ lookups. Supports **all other methods and attributes** of `OrderedDict` /
 accept both integers and strings (which will be hashed before being added to the
 table).
 
-### Table.\_\_init\_\_ {#table.init tag="method"}
+### Table.\_\_init\_\_ {id="table.init",tag="method"}
 
 Initialize a new table.
 
@@ -236,7 +236,7 @@ Initialize a new table.
 | ------ | ------------------------------------------ |
 | `name` | Optional table name for reference. ~~str~~ |
 
-### Table.from_dict {#table.from_dict tag="classmethod"}
+### Table.from_dict {id="table.from_dict",tag="classmethod"}
 
 Initialize a new table from a dict.
 
@@ -254,7 +254,7 @@ Initialize a new table from a dict.
 | `name`      | Optional table name for reference. ~~str~~ |
 | **RETURNS** | The newly constructed object. ~~Table~~    |
 
-### Table.set {#table.set tag="method"}
+### Table.set {id="table.set",tag="method"}
 
 Set a new key / value pair. String keys will be hashed. Same as
 `table[key] = value`.
@@ -273,7 +273,7 @@ Set a new key / value pair. String keys will be hashed. Same as
 | `key`   | The key. ~~Union[str, int]~~ |
 | `value` | The value.                   |
 
-### Table.to_bytes {#table.to_bytes tag="method"}
+### Table.to_bytes {id="table.to_bytes",tag="method"}
 
 Serialize the table to a bytestring.
 
@@ -287,7 +287,7 @@ Serialize the table to a bytestring.
 | ----------- | ------------------------------- |
 | **RETURNS** | The serialized table. ~~bytes~~ |
 
-### Table.from_bytes {#table.from_bytes tag="method"}
+### Table.from_bytes {id="table.from_bytes",tag="method"}
 
 Load a table from a bytestring.
 
@@ -304,7 +304,7 @@ Load a table from a bytestring.
 | `bytes_data` | The data to load. ~~bytes~~ |
 | **RETURNS**  | The loaded table. ~~Table~~ |
 
-### Attributes {#table-attributes}
+### Attributes {id="table-attributes"}
 
 | Name           | Description                                                   |
 | -------------- | ------------------------------------------------------------- |

website/docs/api/matcher.mdx

@@ -13,7 +13,7 @@ tokens in context. For in-depth examples and workflows for combining rules and
 statistical models, see the [usage guide](/usage/rule-based-matching) on
 rule-based matching.
 
-## Pattern format {#patterns}
+## Pattern format {id="patterns"}
 
 > ```json
 > ### Example
@@ -87,7 +87,10 @@ it compares to another value.
 > ```
 
 | Attribute                        | Description                                                                                                                                                                                                       |
-| -------------------------- | -------------------------------------------------------------------------------------------------------- |
+| -------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `REGEX`                          | Attribute value matches the regular expression at any position in the string. ~~Any~~                                                                                                                             |
+| `FUZZY`                          | Attribute value matches if the `fuzzy_compare` method matches for `(value, pattern, -1)`. The default method allows a Levenshtein edit distance of at least 2 and up to 30% of the pattern string length. ~~Any~~ |
+| `FUZZY1`, `FUZZY2`, ... `FUZZY9` | Attribute value matches if the `fuzzy_compare` method matches for `(value, pattern, N)`. The default method allows a Levenshtein edit distance of at most N (1-9). ~~Any~~                                        |
 | `IN`                             | Attribute value is member of a list. ~~Any~~                                                                                                                                                                      |
 | `NOT_IN`                         | Attribute value is _not_ member of a list. ~~Any~~                                                                                                                                                                |
 | `IS_SUBSET`                      | Attribute value (for `MORPH` or custom list attributes) is a subset of a list. ~~Any~~                                                                                                                            |
@@ -95,7 +98,10 @@ it compares to another value.
 | `INTERSECTS`                     | Attribute value (for `MORPH` or custom list attribute) has a non-empty intersection with a list. ~~Any~~                                                                                                          |
 | `==`, `>=`, `<=`, `>`, `<`       | Attribute value is equal, greater or equal, smaller or equal, greater or smaller. ~~Union[int, float]~~                                                                                                           |
 
-## Matcher.\_\_init\_\_ {#init tag="method"}
+As of spaCy v3.5, `REGEX` and `FUZZY` can be used in combination with `IN` and
+`NOT_IN`.
+
+## Matcher.\_\_init\_\_ {id="init",tag="method"}
 
 Create the rule-based `Matcher`. If `validate=True` is set, all patterns added
 to the matcher will be validated against a JSON schema and a `MatchPatternError`
@@ -110,11 +116,12 @@ string where an integer is expected) or unexpected property names.
 > ```
 
 | Name            | Description                                                                                           |
-| ---------- | ----------------------------------------------------------------------------------------------------- |
+| --------------- | ----------------------------------------------------------------------------------------------------- |
 | `vocab`         | The vocabulary object, which must be shared with the documents the matcher will operate on. ~~Vocab~~ |
 | `validate`      | Validate all patterns added to this matcher. ~~bool~~                                                 |
+| `fuzzy_compare` | The comparison method used for the `FUZZY` operators. ~~Callable[[str, str, int], bool]~~             |
 
-## Matcher.\_\_call\_\_ {#call tag="method"}
+## Matcher.\_\_call\_\_ {id="call",tag="method"}
 
 Find all token sequences matching the supplied patterns on the `Doc` or `Span`.
 
@@ -143,7 +150,7 @@ the match.
 | `with_alignments` <Tag variant="new">3.0.6</Tag> | Return match alignment information as part of the match tuple as `List[int]` with the same length as the matched span. Each entry denotes the corresponding index of the token in the pattern. If `as_spans` is set to `True`, this setting is ignored. Defaults to `False`. ~~bool~~                    |
 | **RETURNS**                                      | A list of `(match_id, start, end)` tuples, describing the matches. A match tuple describes a span `doc[start:end`]. The `match_id` is the ID of the added match pattern. If `as_spans` is set to `True`, a list of `Span` objects is returned instead. ~~Union[List[Tuple[int, int, int]], List[Span]]~~ |
 
-## Matcher.\_\_len\_\_ {#len tag="method" new="2"}
+## Matcher.\_\_len\_\_ {id="len",tag="method",version="2"}
 
 Get the number of rules added to the matcher. Note that this only returns the
 number of rules (identical with the number of IDs), not the number of individual
@@ -162,7 +169,7 @@ patterns.
 | ----------- | ---------------------------- |
 | **RETURNS** | The number of rules. ~~int~~ |
 
-## Matcher.\_\_contains\_\_ {#contains tag="method" new="2"}
+## Matcher.\_\_contains\_\_ {id="contains",tag="method",version="2"}
 
 Check whether the matcher contains rules for a match ID.
 
@@ -180,7 +187,7 @@ Check whether the matcher contains rules for a match ID.
 | `key`       | The match ID. ~~str~~                                          |
 | **RETURNS** | Whether the matcher contains rules for this match ID. ~~bool~~ |
 
-## Matcher.add {#add tag="method" new="2"}
+## Matcher.add {id="add",tag="method",version="2"}
 
 Add a rule to the matcher, consisting of an ID key, one or more patterns, and an
 optional callback function to act on the matches. The callback function will
@@ -226,7 +233,7 @@ patterns = [[{"TEXT": "Google"}, {"TEXT": "Now"}], [{"TEXT": "GoogleNow"}]]
 | `on_match`                          | Callback function to act on matches. Takes the arguments `matcher`, `doc`, `i` and `matches`. ~~Optional[Callable[[Matcher, Doc, int, List[tuple], Any]]~~ |
 | `greedy` <Tag variant="new">3</Tag> | Optional filter for greedy matches. Can either be `"FIRST"` or `"LONGEST"`. ~~Optional[str]~~                                                              |
 
-## Matcher.remove {#remove tag="method" new="2"}
+## Matcher.remove {id="remove",tag="method",version="2"}
 
 Remove a rule from the matcher. A `KeyError` is raised if the match ID does not
 exist.
@@ -244,7 +251,7 @@ exist.
 | ----- | --------------------------------- |
 | `key` | The ID of the match rule. ~~str~~ |
 
-## Matcher.get {#get tag="method" new="2"}
+## Matcher.get {id="get",tag="method",version="2"}
 
 Retrieve the pattern stored for a key. Returns the rule as an
 `(on_match, patterns)` tuple containing the callback and available patterns.

website/docs/api/morphologizer.mdx

@@ -2,7 +2,7 @@
 title: Morphologizer
 tag: class
 source: spacy/pipeline/morphologizer.pyx
-new: 3
+version: 3
 teaser: 'Pipeline component for predicting morphological features'
 api_base_class: /api/tagger
 api_string_name: morphologizer
@@ -15,7 +15,7 @@ coarse-grained POS tags following the Universal Dependencies
 [FEATS](https://universaldependencies.org/format.html#morphological-annotation)
 annotation guidelines.
 
-## Assigned Attributes {#assigned-attributes}
+## Assigned Attributes {id="assigned-attributes"}
 
 Predictions are saved to `Token.morph` and `Token.pos`.
 
@@ -25,7 +25,7 @@ Predictions are saved to `Token.morph` and `Token.pos`.
 | `Token.pos_`  | The UPOS part of speech. ~~str~~          |
 | `Token.morph` | Morphological features. ~~MorphAnalysis~~ |
 
-## Config and implementation {#config}
+## Config and implementation {id="config"}
 
 The default config is defined by the pipeline component factory and describes
 how the component should be configured. You can override its settings via the
@@ -53,7 +53,7 @@ architectures and their arguments and hyperparameters.
 %%GITHUB_SPACY/spacy/pipeline/morphologizer.pyx
 ```
 
-## Morphologizer.\_\_init\_\_ {#init tag="method"}
+## Morphologizer.\_\_init\_\_ {id="init",tag="method"}
 
 Create a new pipeline instance. In your application, you would normally use a
 shortcut for this and instantiate the component using its string name and
@@ -97,7 +97,7 @@ annotation `C=E|X=Y`):
 | `extend` <Tag variant="new">3.2</Tag>    | Whether existing feature types (whose values may or may not be overwritten depending on `overwrite`) are preserved. Defaults to `False`. ~~bool~~                                                                                                                      |
 | `scorer` <Tag variant="new">3.2</Tag>    | The scoring method. Defaults to [`Scorer.score_token_attr`](/api/scorer#score_token_attr) for the attributes `"pos"` and `"morph"` and [`Scorer.score_token_attr_per_feat`](/api/scorer#score_token_attr_per_feat) for the attribute `"morph"`. ~~Optional[Callable]~~ |
 
-## Morphologizer.\_\_call\_\_ {#call tag="method"}
+## Morphologizer.\_\_call\_\_ {id="call",tag="method"}
 
 Apply the pipe to one document. The document is modified in place, and returned.
 This usually happens under the hood when the `nlp` object is called on a text
@@ -120,7 +120,7 @@ delegate to the [`predict`](/api/morphologizer#predict) and
 | `doc`       | The document to process. ~~Doc~~ |
 | **RETURNS** | The processed document. ~~Doc~~  |
 
-## Morphologizer.pipe {#pipe tag="method"}
+## Morphologizer.pipe {id="pipe",tag="method"}
 
 Apply the pipe to a stream of documents. This usually happens under the hood
 when the `nlp` object is called on a text and all pipeline components are
@@ -144,7 +144,7 @@ applied to the `Doc` in order. Both [`__call__`](/api/morphologizer#call) and
 | `batch_size`   | The number of documents to buffer. Defaults to `128`. ~~int~~ |
 | **YIELDS**     | The processed documents in order. ~~Doc~~                     |
 
-## Morphologizer.initialize {#initialize tag="method"}
+## Morphologizer.initialize {id="initialize",tag="method"}
 
 Initialize the component for training. `get_examples` should be a function that
 returns an iterable of [`Example`](/api/example) objects. **At least one example
@@ -181,7 +181,7 @@ config.
 | `nlp`          | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~                                                                                                                                                                                                                                                                                                                              |
 | `labels`       | The label information to add to the component, as provided by the [`label_data`](#label_data) property after initialization. To generate a reusable JSON file from your data, you should run the [`init labels`](/api/cli#init-labels) command. If no labels are provided, the `get_examples` callback is used to extract the labels from the data, which may be a lot slower. ~~Optional[dict]~~ |
 
-## Morphologizer.predict {#predict tag="method"}
+## Morphologizer.predict {id="predict",tag="method"}
 
 Apply the component's model to a batch of [`Doc`](/api/doc) objects, without
 modifying them.
@@ -198,7 +198,7 @@ modifying them.
 | `docs`      | The documents to predict. ~~Iterable[Doc]~~ |
 | **RETURNS** | The model's prediction for each document.   |
 
-## Morphologizer.set_annotations {#set_annotations tag="method"}
+## Morphologizer.set_annotations {id="set_annotations",tag="method"}
 
 Modify a batch of [`Doc`](/api/doc) objects, using pre-computed scores.
 
@@ -215,7 +215,7 @@ Modify a batch of [`Doc`](/api/doc) objects, using pre-computed scores.
 | `docs`   | The documents to modify. ~~Iterable[Doc]~~              |
 | `scores` | The scores to set, produced by `Morphologizer.predict`. |
 
-## Morphologizer.update {#update tag="method"}
+## Morphologizer.update {id="update",tag="method"}
 
 Learn from a batch of [`Example`](/api/example) objects containing the
 predictions and gold-standard annotations, and update the component's model.
@@ -239,7 +239,7 @@ Delegates to [`predict`](/api/morphologizer#predict) and
 | `losses`       | Optional record of the loss during training. Updated using the component name as the key. ~~Optional[Dict[str, float]]~~ |
 | **RETURNS**    | The updated `losses` dictionary. ~~Dict[str, float]~~                                                                    |
 
-## Morphologizer.get_loss {#get_loss tag="method"}
+## Morphologizer.get_loss {id="get_loss",tag="method"}
 
 Find the loss and gradient of loss for the batch of documents and their
 predicted scores.
@@ -258,7 +258,7 @@ predicted scores.
 | `scores`    | Scores representing the model's predictions.                                |
 | **RETURNS** | The loss and the gradient, i.e. `(loss, gradient)`. ~~Tuple[float, float]~~ |
 
-## Morphologizer.create_optimizer {#create_optimizer tag="method"}
+## Morphologizer.create_optimizer {id="create_optimizer",tag="method"}
 
 Create an optimizer for the pipeline component.
 
@@ -273,7 +273,7 @@ Create an optimizer for the pipeline component.
 | ----------- | ---------------------------- |
 | **RETURNS** | The optimizer. ~~Optimizer~~ |
 
-## Morphologizer.use_params {#use_params tag="method, contextmanager"}
+## Morphologizer.use_params {id="use_params",tag="method, contextmanager"}
 
 Modify the pipe's model, to use the given parameter values. At the end of the
 context, the original parameters are restored.
@@ -290,7 +290,7 @@ context, the original parameters are restored.
 | -------- | -------------------------------------------------- |
 | `params` | The parameter values to use in the model. ~~dict~~ |
 
-## Morphologizer.add_label {#add_label tag="method"}
+## Morphologizer.add_label {id="add_label",tag="method"}
 
 Add a new label to the pipe. If the `Morphologizer` should set annotations for
 both `pos` and `morph`, the label should include the UPOS as the feature `POS`.
@@ -313,7 +313,7 @@ will be automatically added to the model, and the output dimension will be
 | `label`     | The label to add. ~~str~~                                   |
 | **RETURNS** | `0` if the label is already present, otherwise `1`. ~~int~~ |
 
-## Morphologizer.to_disk {#to_disk tag="method"}
+## Morphologizer.to_disk {id="to_disk",tag="method"}
 
 Serialize the pipe to disk.
 
@@ -330,7 +330,7 @@ Serialize the pipe to disk.
 | _keyword-only_ |                                                                                                                                            |
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~                                                |
 
-## Morphologizer.from_disk {#from_disk tag="method"}
+## Morphologizer.from_disk {id="from_disk",tag="method"}
 
 Load the pipe from disk. Modifies the object in place and returns it.
 
@@ -348,7 +348,7 @@ Load the pipe from disk. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~     |
 | **RETURNS**    | The modified `Morphologizer` object. ~~Morphologizer~~                                          |
 
-## Morphologizer.to_bytes {#to_bytes tag="method"}
+## Morphologizer.to_bytes {id="to_bytes",tag="method"}
 
 > #### Example
 >
@@ -365,7 +365,7 @@ Serialize the pipe to a bytestring.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The serialized form of the `Morphologizer` object. ~~bytes~~                                |
 
-## Morphologizer.from_bytes {#from_bytes tag="method"}
+## Morphologizer.from_bytes {id="from_bytes",tag="method"}
 
 Load the pipe from a bytestring. Modifies the object in place and returns it.
 
@@ -384,7 +384,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The `Morphologizer` object. ~~Morphologizer~~                                               |
 
-## Morphologizer.labels {#labels tag="property"}
+## Morphologizer.labels {id="labels",tag="property"}
 
 The labels currently added to the component in the Universal Dependencies
 [FEATS](https://universaldependencies.org/format.html#morphological-annotation)
@@ -403,7 +403,7 @@ coarse-grained POS as the feature `POS`.
 | ----------- | ------------------------------------------------------ |
 | **RETURNS** | The labels added to the component. ~~Tuple[str, ...]~~ |
 
-## Morphologizer.label_data {#label_data tag="property" new="3"}
+## Morphologizer.label_data {id="label_data",tag="property",version="3"}
 
 The labels currently added to the component and their internal meta information.
 This is the data generated by [`init labels`](/api/cli#init-labels) and used by
@@ -421,7 +421,7 @@ model with a pre-defined label set.
 | ----------- | ----------------------------------------------- |
 | **RETURNS** | The label data added to the component. ~~dict~~ |
 
-## Serialization fields {#serialization-fields}
+## Serialization fields {id="serialization-fields"}
 
 During serialization, spaCy will export several data fields used to restore
 different aspects of the object. If needed, you can exclude them from

website/docs/api/morphology.mdx

@@ -10,7 +10,7 @@ morphological analysis, so queries of morphological attributes are delegated to
 this class. See [`MorphAnalysis`](/api/morphology#morphanalysis) for the
 container storing a single morphological analysis.
 
-## Morphology.\_\_init\_\_ {#init tag="method"}
+## Morphology.\_\_init\_\_ {id="init",tag="method"}
 
 Create a `Morphology` object.
 
@@ -26,7 +26,7 @@ Create a `Morphology` object.
 | --------- | --------------------------------- |
 | `strings` | The string store. ~~StringStore~~ |
 
-## Morphology.add {#add tag="method"}
+## Morphology.add {id="add",tag="method"}
 
 Insert a morphological analysis in the morphology table, if not already present.
 The morphological analysis may be provided in the Universal Dependencies
@@ -46,7 +46,7 @@ new analysis.
 | ---------- | ------------------------------------------------ |
 | `features` | The morphological features. ~~Union[Dict, str]~~ |
 
-## Morphology.get {#get tag="method"}
+## Morphology.get {id="get",tag="method"}
 
 > #### Example
 >
@@ -64,7 +64,7 @@ string for the hash of the morphological analysis.
 | ------- | ----------------------------------------------- |
 | `morph` | The hash of the morphological analysis. ~~int~~ |
 
-## Morphology.feats_to_dict {#feats_to_dict tag="staticmethod"}
+## Morphology.feats_to_dict {id="feats_to_dict",tag="staticmethod"}
 
 Convert a string
 [FEATS](https://universaldependencies.org/format.html#morphological-annotation)
@@ -84,7 +84,7 @@ tag map.
 | `feats`     | The morphological features in Universal Dependencies [FEATS](https://universaldependencies.org/format.html#morphological-annotation) format. ~~str~~ |
 | **RETURNS** | The morphological features as a dictionary. ~~Dict[str, str]~~                                                                                       |
 
-## Morphology.dict_to_feats {#dict_to_feats tag="staticmethod"}
+## Morphology.dict_to_feats {id="dict_to_feats",tag="staticmethod"}
 
 Convert a dictionary of features and values to a string
 [FEATS](https://universaldependencies.org/format.html#morphological-annotation)
@@ -103,19 +103,19 @@ representation.
 | `feats_dict` | The morphological features as a dictionary. ~~Dict[str, str]~~                                                                                       |
 | **RETURNS**  | The morphological features in Universal Dependencies [FEATS](https://universaldependencies.org/format.html#morphological-annotation) format. ~~str~~ |
 
-## Attributes {#attributes}
+## Attributes {id="attributes"}
 
 | Name          | Description                                                                                                                     |
-| ------------- | ------------------------------------------------------------------------------------------------------------------------------ |
+| ------------- | ------------------------------------------------------------------------------------------------------------------------------- |
-| `FEATURE_SEP` | The [FEATS](https://universaldependencies.org/format.html#morphological-annotation) feature separator. Default is `|`. ~~str~~ |
+| `FEATURE_SEP` | The [FEATS](https://universaldependencies.org/format.html#morphological-annotation) feature separator. Default is `\|`. ~~str~~ |
 | `FIELD_SEP`   | The [FEATS](https://universaldependencies.org/format.html#morphological-annotation) field separator. Default is `=`. ~~str~~    |
 | `VALUE_SEP`   | The [FEATS](https://universaldependencies.org/format.html#morphological-annotation) value separator. Default is `,`. ~~str~~    |
 
-## MorphAnalysis {#morphanalysis tag="class" source="spacy/tokens/morphanalysis.pyx"}
+## MorphAnalysis {id="morphanalysis",tag="class",source="spacy/tokens/morphanalysis.pyx"}
 
 Stores a single morphological analysis.
 
-### MorphAnalysis.\_\_init\_\_ {#morphanalysis-init tag="method"}
+### MorphAnalysis.\_\_init\_\_ {id="morphanalysis-init",tag="method"}
 
 Initialize a MorphAnalysis object from a Universal Dependencies
 [FEATS](https://universaldependencies.org/format.html#morphological-annotation)
@@ -135,7 +135,7 @@ string or a dictionary of morphological features.
 | `vocab`    | The vocab. ~~Vocab~~                                       |
 | `features` | The morphological features. ~~Union[Dict[str, str], str]~~ |
 
-### MorphAnalysis.\_\_contains\_\_ {#morphanalysis-contains tag="method"}
+### MorphAnalysis.\_\_contains\_\_ {id="morphanalysis-contains",tag="method"}
 
 Whether a feature/value pair is in the analysis.
 
@@ -151,7 +151,7 @@ Whether a feature/value pair is in the analysis.
 | ----------- | --------------------------------------------- |
 | **RETURNS** | A feature/value pair in the analysis. ~~str~~ |
 
-### MorphAnalysis.\_\_iter\_\_ {#morphanalysis-iter tag="method"}
+### MorphAnalysis.\_\_iter\_\_ {id="morphanalysis-iter",tag="method"}
 
 Iterate over the feature/value pairs in the analysis.
 
@@ -167,7 +167,7 @@ Iterate over the feature/value pairs in the analysis.
 | ---------- | --------------------------------------------- |
 | **YIELDS** | A feature/value pair in the analysis. ~~str~~ |
 
-### MorphAnalysis.\_\_len\_\_ {#morphanalysis-len tag="method"}
+### MorphAnalysis.\_\_len\_\_ {id="morphanalysis-len",tag="method"}
 
 Returns the number of features in the analysis.
 
@@ -183,7 +183,7 @@ Returns the number of features in the analysis.
 | ----------- | ----------------------------------------------- |
 | **RETURNS** | The number of features in the analysis. ~~int~~ |
 
-### MorphAnalysis.\_\_str\_\_ {#morphanalysis-str tag="method"}
+### MorphAnalysis.\_\_str\_\_ {id="morphanalysis-str",tag="method"}
 
 Returns the morphological analysis in the Universal Dependencies
 [FEATS](https://universaldependencies.org/format.html#morphological-annotation)
@@ -201,7 +201,7 @@ string format.
 | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
 | **RETURNS** | The analysis in the Universal Dependencies [FEATS](https://universaldependencies.org/format.html#morphological-annotation) format. ~~str~~ |
 
-### MorphAnalysis.get {#morphanalysis-get tag="method"}
+### MorphAnalysis.get {id="morphanalysis-get",tag="method"}
 
 Retrieve values for a feature by field.
 
@@ -218,7 +218,7 @@ Retrieve values for a feature by field.
 | `field`     | The field to retrieve. ~~str~~                   |
 | **RETURNS** | A list of the individual features. ~~List[str]~~ |
 
-### MorphAnalysis.to_dict {#morphanalysis-to_dict tag="method"}
+### MorphAnalysis.to_dict {id="morphanalysis-to_dict",tag="method"}
 
 Produce a dict representation of the analysis, in the same format as the tag
 map.
@@ -235,7 +235,7 @@ map.
 | ----------- | ----------------------------------------------------------- |
 | **RETURNS** | The dict representation of the analysis. ~~Dict[str, str]~~ |
 
-### MorphAnalysis.from_id {#morphanalysis-from_id tag="classmethod"}
+### MorphAnalysis.from_id {id="morphanalysis-from_id",tag="classmethod"}
 
 Create a morphological analysis from a given hash ID.
 

website/docs/api/phrasematcher.mdx

@@ -3,7 +3,7 @@ title: PhraseMatcher
 teaser: Match sequences of tokens, based on documents
 tag: class
 source: spacy/matcher/phrasematcher.pyx
-new: 2
+version: 2
 ---
 
 The `PhraseMatcher` lets you efficiently match large terminology lists. While
@@ -12,7 +12,7 @@ descriptions, the `PhraseMatcher` accepts match patterns in the form of `Doc`
 objects. See the [usage guide](/usage/rule-based-matching#phrasematcher) for
 examples.
 
-## PhraseMatcher.\_\_init\_\_ {#init tag="method"}
+## PhraseMatcher.\_\_init\_\_ {id="init",tag="method"}
 
 Create the rule-based `PhraseMatcher`. Setting a different `attr` to match on
 will change the token attributes that will be compared to determine a match. By
@@ -42,7 +42,7 @@ be shown.
 | `attr`     | The token attribute to match on. Defaults to `ORTH`, i.e. the verbatim token text. ~~Union[int, str]~~ |
 | `validate` | Validate patterns added to the matcher. ~~bool~~                                                       |
 
-## PhraseMatcher.\_\_call\_\_ {#call tag="method"}
+## PhraseMatcher.\_\_call\_\_ {id="call",tag="method"}
 
 Find all token sequences matching the supplied patterns on the `Doc` or `Span`.
 
@@ -76,7 +76,7 @@ match_id_string = nlp.vocab.strings[match_id]
 
 </Infobox>
 
-## PhraseMatcher.\_\_len\_\_ {#len tag="method"}
+## PhraseMatcher.\_\_len\_\_ {id="len",tag="method"}
 
 Get the number of rules added to the matcher. Note that this only returns the
 number of rules (identical with the number of IDs), not the number of individual
@@ -95,7 +95,7 @@ patterns.
 | ----------- | ---------------------------- |
 | **RETURNS** | The number of rules. ~~int~~ |
 
-## PhraseMatcher.\_\_contains\_\_ {#contains tag="method"}
+## PhraseMatcher.\_\_contains\_\_ {id="contains",tag="method"}
 
 Check whether the matcher contains rules for a match ID.
 
@@ -113,7 +113,7 @@ Check whether the matcher contains rules for a match ID.
 | `key`       | The match ID. ~~str~~                                          |
 | **RETURNS** | Whether the matcher contains rules for this match ID. ~~bool~~ |
 
-## PhraseMatcher.add {#add tag="method"}
+## PhraseMatcher.add {id="add",tag="method"}
 
 Add a rule to the matcher, consisting of an ID key, one or more patterns, and a
 callback function to act on the matches. The callback function will receive the
@@ -155,7 +155,7 @@ patterns = [nlp("health care reform"), nlp("healthcare reform")]
 | _keyword-only_ |                                                                                                                                                            |
 | `on_match`     | Callback function to act on matches. Takes the arguments `matcher`, `doc`, `i` and `matches`. ~~Optional[Callable[[Matcher, Doc, int, List[tuple], Any]]~~ |
 
-## PhraseMatcher.remove {#remove tag="method" new="2.2"}
+## PhraseMatcher.remove {id="remove",tag="method",version="2.2"}
 
 Remove a rule from the matcher by match ID. A `KeyError` is raised if the key
 does not exist.

website/docs/api/pipe.mdx

@@ -12,7 +12,7 @@ spaCy pipeline. See the docs on
 [writing trainable components](/usage/processing-pipelines#trainable-components)
 for how to use the `TrainablePipe` base class to implement custom components.
 
-<!-- TODO: Pipe vs TrainablePipe, check methods below (all renamed to TrainablePipe for now) -->
+{/* TODO: Pipe vs TrainablePipe, check methods below (all renamed to TrainablePipe for now) */}
 
 > #### Why is it implemented in Cython?
 >
@@ -27,7 +27,7 @@ for how to use the `TrainablePipe` base class to implement custom components.
 %%GITHUB_SPACY/spacy/pipeline/trainable_pipe.pyx
 ```
 
-## TrainablePipe.\_\_init\_\_ {#init tag="method"}
+## TrainablePipe.\_\_init\_\_ {id="init",tag="method"}
 
 > #### Example
 >
@@ -54,7 +54,7 @@ shortcut for this and instantiate the component using its string name and
 | `name`  | String name of the component instance. Used to add entries to the `losses` during training. ~~str~~                        |
 | `**cfg` | Additional config parameters and settings. Will be available as the dictionary `cfg` and is serialized with the component. |
 
-## TrainablePipe.\_\_call\_\_ {#call tag="method"}
+## TrainablePipe.\_\_call\_\_ {id="call",tag="method"}
 
 Apply the pipe to one document. The document is modified in place, and returned.
 This usually happens under the hood when the `nlp` object is called on a text
@@ -77,7 +77,7 @@ and all pipeline components are applied to the `Doc` in order. Both
 | `doc`       | The document to process. ~~Doc~~ |
 | **RETURNS** | The processed document. ~~Doc~~  |
 
-## TrainablePipe.pipe {#pipe tag="method"}
+## TrainablePipe.pipe {id="pipe",tag="method"}
 
 Apply the pipe to a stream of documents. This usually happens under the hood
 when the `nlp` object is called on a text and all pipeline components are
@@ -100,7 +100,7 @@ applied to the `Doc` in order. Both [`__call__`](/api/pipe#call) and
 | `batch_size`   | The number of documents to buffer. Defaults to `128`. ~~int~~ |
 | **YIELDS**     | The processed documents in order. ~~Doc~~                     |
 
-## TrainablePipe.set_error_handler {#set_error_handler tag="method" new="3"}
+## TrainablePipe.set_error_handler {id="set_error_handler",tag="method",version="3"}
 
 Define a callback that will be invoked when an error is thrown during processing
 of one or more documents with either [`__call__`](/api/pipe#call) or
@@ -122,7 +122,7 @@ processed, and the original error.
 | --------------- | -------------------------------------------------------------------------------------------------------------- |
 | `error_handler` | A function that performs custom error handling. ~~Callable[[str, Callable[[Doc], Doc], List[Doc], Exception]~~ |
 
-## TrainablePipe.get_error_handler {#get_error_handler tag="method" new="3"}
+## TrainablePipe.get_error_handler {id="get_error_handler",tag="method",version="3"}
 
 Retrieve the callback that performs error handling for this component's
 [`__call__`](/api/pipe#call) and [`pipe`](/api/pipe#pipe) methods. If no custom
@@ -141,7 +141,7 @@ returned that simply reraises the exception.
 | ----------- | ---------------------------------------------------------------------------------------------------------------- |
 | **RETURNS** | The function that performs custom error handling. ~~Callable[[str, Callable[[Doc], Doc], List[Doc], Exception]~~ |
 
-## TrainablePipe.initialize {#initialize tag="method" new="3"}
+## TrainablePipe.initialize {id="initialize",tag="method",version="3"}
 
 Initialize the component for training. `get_examples` should be a function that
 returns an iterable of [`Example`](/api/example) objects. The data examples are
@@ -171,7 +171,7 @@ This method was previously called `begin_training`.
 | _keyword-only_ |                                                                                                                                       |
 | `nlp`          | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~                                                                  |
 
-## TrainablePipe.predict {#predict tag="method"}
+## TrainablePipe.predict {id="predict",tag="method"}
 
 Apply the component's model to a batch of [`Doc`](/api/doc) objects, without
 modifying them.
@@ -194,7 +194,7 @@ This method needs to be overwritten with your own custom `predict` method.
 | `docs`      | The documents to predict. ~~Iterable[Doc]~~ |
 | **RETURNS** | The model's prediction for each document.   |
 
-## TrainablePipe.set_annotations {#set_annotations tag="method"}
+## TrainablePipe.set_annotations {id="set_annotations",tag="method"}
 
 Modify a batch of [`Doc`](/api/doc) objects, using pre-computed scores.
 
@@ -218,7 +218,7 @@ method.
 | `docs`   | The documents to modify. ~~Iterable[Doc]~~       |
 | `scores` | The scores to set, produced by `Tagger.predict`. |
 
-## TrainablePipe.update {#update tag="method"}
+## TrainablePipe.update {id="update",tag="method"}
 
 Learn from a batch of [`Example`](/api/example) objects containing the
 predictions and gold-standard annotations, and update the component's model.
@@ -240,7 +240,7 @@ predictions and gold-standard annotations, and update the component's model.
 | `losses`       | Optional record of the loss during training. Updated using the component name as the key. ~~Optional[Dict[str, float]]~~ |
 | **RETURNS**    | The updated `losses` dictionary. ~~Dict[str, float]~~                                                                    |
 
-## TrainablePipe.rehearse {#rehearse tag="method,experimental" new="3"}
+## TrainablePipe.rehearse {id="rehearse",tag="method,experimental",version="3"}
 
 Perform a "rehearsal" update from a batch of data. Rehearsal updates teach the
 current model to make predictions similar to an initial model, to try to address
@@ -262,7 +262,7 @@ the "catastrophic forgetting" problem. This feature is experimental.
 | `losses`       | Optional record of the loss during training. Updated using the component name as the key. ~~Optional[Dict[str, float]]~~ |
 | **RETURNS**    | The updated `losses` dictionary. ~~Dict[str, float]~~                                                                    |
 
-## TrainablePipe.get_loss {#get_loss tag="method"}
+## TrainablePipe.get_loss {id="get_loss",tag="method"}
 
 Find the loss and gradient of loss for the batch of documents and their
 predicted scores.
@@ -287,7 +287,7 @@ This method needs to be overwritten with your own custom `get_loss` method.
 | `scores`    | Scores representing the model's predictions.                                |
 | **RETURNS** | The loss and the gradient, i.e. `(loss, gradient)`. ~~Tuple[float, float]~~ |
 
-## TrainablePipe.score {#score tag="method" new="3"}
+## TrainablePipe.score {id="score",tag="method",version="3"}
 
 Score a batch of examples.
 
@@ -304,7 +304,7 @@ Score a batch of examples.
 | `\*\*kwargs`   | Any additional settings to pass on to the scorer. ~~Any~~                                               |
 | **RETURNS**    | The scores, e.g. produced by the [`Scorer`](/api/scorer). ~~Dict[str, Union[float, Dict[str, float]]]~~ |
 
-## TrainablePipe.create_optimizer {#create_optimizer tag="method"}
+## TrainablePipe.create_optimizer {id="create_optimizer",tag="method"}
 
 Create an optimizer for the pipeline component. Defaults to
 [`Adam`](https://thinc.ai/docs/api-optimizers#adam) with default settings.
@@ -320,7 +320,7 @@ Create an optimizer for the pipeline component. Defaults to
 | ----------- | ---------------------------- |
 | **RETURNS** | The optimizer. ~~Optimizer~~ |
 
-## TrainablePipe.use_params {#use_params tag="method, contextmanager"}
+## TrainablePipe.use_params {id="use_params",tag="method, contextmanager"}
 
 Modify the pipe's model, to use the given parameter values. At the end of the
 context, the original parameters are restored.
@@ -337,7 +337,7 @@ context, the original parameters are restored.
 | -------- | -------------------------------------------------- |
 | `params` | The parameter values to use in the model. ~~dict~~ |
 
-## TrainablePipe.finish_update {#finish_update tag="method"}
+## TrainablePipe.finish_update {id="finish_update",tag="method"}
 
 Update parameters using the current parameter gradients. Defaults to calling
 [`self.model.finish_update`](https://thinc.ai/docs/api-model#finish_update).
@@ -355,7 +355,7 @@ Update parameters using the current parameter gradients. Defaults to calling
 | ----- | ------------------------------------- |
 | `sgd` | An optimizer. ~~Optional[Optimizer]~~ |
 
-## TrainablePipe.add_label {#add_label tag="method"}
+## TrainablePipe.add_label {id="add_label",tag="method"}
 
 > #### Example
 >
@@ -390,7 +390,7 @@ case, all labels found in the sample will be automatically added to the model,
 and the output dimension will be
 [inferred](/usage/layers-architectures#thinc-shape-inference) automatically.
 
-## TrainablePipe.is_resizable {#is_resizable tag="property"}
+## TrainablePipe.is_resizable {id="is_resizable",tag="property"}
 
 > #### Example
 >
@@ -421,7 +421,7 @@ as an attribute to the component's model.
 | ----------- | ---------------------------------------------------------------------------------------------- |
 | **RETURNS** | Whether or not the output dimension of the model can be changed after initialization. ~~bool~~ |
 
-## TrainablePipe.set_output {#set_output tag="method"}
+## TrainablePipe.set_output {id="set_output",tag="method"}
 
 Change the output dimension of the component's model. If the component is not
 [resizable](#is_resizable), this method will raise a `NotImplementedError`. If a
@@ -441,7 +441,7 @@ care should be taken to avoid the "catastrophic forgetting" problem.
 | ---- | --------------------------------- |
 | `nO` | The new output dimension. ~~int~~ |
 
-## TrainablePipe.to_disk {#to_disk tag="method"}
+## TrainablePipe.to_disk {id="to_disk",tag="method"}
 
 Serialize the pipe to disk.
 
@@ -458,7 +458,7 @@ Serialize the pipe to disk.
 | _keyword-only_ |                                                                                                                                            |
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~                                                |
 
-## TrainablePipe.from_disk {#from_disk tag="method"}
+## TrainablePipe.from_disk {id="from_disk",tag="method"}
 
 Load the pipe from disk. Modifies the object in place and returns it.
 
@@ -476,7 +476,7 @@ Load the pipe from disk. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~     |
 | **RETURNS**    | The modified pipe. ~~TrainablePipe~~                                                            |
 
-## TrainablePipe.to_bytes {#to_bytes tag="method"}
+## TrainablePipe.to_bytes {id="to_bytes",tag="method"}
 
 > #### Example
 >
@@ -493,7 +493,7 @@ Serialize the pipe to a bytestring.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The serialized form of the pipe. ~~bytes~~                                                  |
 
-## TrainablePipe.from_bytes {#from_bytes tag="method"}
+## TrainablePipe.from_bytes {id="from_bytes",tag="method"}
 
 Load the pipe from a bytestring. Modifies the object in place and returns it.
 
@@ -512,7 +512,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The pipe. ~~TrainablePipe~~                                                                 |
 
-## Attributes {#attributes}
+## Attributes {id="attributes"}
 
 | Name    | Description                                                                                                                       |
 | ------- | --------------------------------------------------------------------------------------------------------------------------------- |
@@ -521,7 +521,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
 | `name`  | The name of the component instance in the pipeline. Can be used in the losses. ~~str~~                                            |
 | `cfg`   | Keyword arguments passed to [`TrainablePipe.__init__`](/api/pipe#init). Will be serialized with the component. ~~Dict[str, Any]~~ |
 
-## Serialization fields {#serialization-fields}
+## Serialization fields {id="serialization-fields"}
 
 During serialization, spaCy will export several data fields used to restore
 different aspects of the object. If needed, you can exclude them from

website/docs/api/pipeline-functions.mdx

@@ -10,7 +10,7 @@ menu:
   - ['doc_cleaner', 'doc_cleaner']
 ---
 
-## merge_noun_chunks {#merge_noun_chunks tag="function"}
+## merge_noun_chunks {id="merge_noun_chunks",tag="function"}
 
 Merge noun chunks into a single token. Also available via the string name
 `"merge_noun_chunks"`.
@@ -40,7 +40,7 @@ all other components.
 | `doc`       | The `Doc` object to process, e.g. the `Doc` in the pipeline. ~~Doc~~ |
 | **RETURNS** | The modified `Doc` with merged noun chunks. ~~Doc~~                  |
 
-## merge_entities {#merge_entities tag="function"}
+## merge_entities {id="merge_entities",tag="function"}
 
 Merge named entities into a single token. Also available via the string name
 `"merge_entities"`.
@@ -70,7 +70,7 @@ components to the end of the pipeline and after all other components.
 | `doc`       | The `Doc` object to process, e.g. the `Doc` in the pipeline. ~~Doc~~ |
 | **RETURNS** | The modified `Doc` with merged entities. ~~Doc~~                     |
 
-## merge_subtokens {#merge_subtokens tag="function" new="2.1"}
+## merge_subtokens {id="merge_subtokens",tag="function",version="2.1"}
 
 Merge subtokens into a single token. Also available via the string name
 `"merge_subtokens"`. As of v2.1, the parser is able to predict "subtokens" that
@@ -110,7 +110,7 @@ end of the pipeline and after all other components.
 | `label`     | The subtoken dependency label. Defaults to `"subtok"`. ~~str~~       |
 | **RETURNS** | The modified `Doc` with merged subtokens. ~~Doc~~                    |
 
-## token_splitter {#token_splitter tag="function" new="3.0"}
+## token_splitter {id="token_splitter",tag="function",version="3.0"}
 
 Split tokens longer than a minimum length into shorter tokens. Intended for use
 with transformer pipelines where long spaCy tokens lead to input text that
@@ -132,7 +132,7 @@ exceed the transformer model max length.
 | `split_length` | The length of the split tokens. Defaults to `5`. ~~int~~              |
 | **RETURNS**    | The modified `Doc` with the split tokens. ~~Doc~~                     |
 
-## doc_cleaner {#doc_cleaner tag="function" new="3.2.1"}
+## doc_cleaner {id="doc_cleaner",tag="function",version="3.2.1"}
 
 Clean up `Doc` attributes. Intended for use at the end of pipelines with
 `tok2vec` or `transformer` pipeline components that store tensors and other
@@ -154,7 +154,7 @@ whole pipeline has run.
 | `silent`    | If `False`, show warnings if attributes aren't found or can't be set. Defaults to `True`. ~~bool~~                                                                                  |
 | **RETURNS** | The modified `Doc` with the modified attributes. ~~Doc~~                                                                                                                            |
 
-## span_cleaner {#span_cleaner tag="function,experimental"}
+## span_cleaner {id="span_cleaner",tag="function,experimental"}
 
 Remove `SpanGroup`s from `doc.spans` based on a key prefix. This is used to
 clean up after the [`CoreferenceResolver`](/api/coref) when it's paired with a

website/docs/api/scorer.mdx

@@ -10,7 +10,7 @@ The `Scorer` computes evaluation scores. It's typically created by
 provides a number of evaluation methods for evaluating [`Token`](/api/token) and
 [`Doc`](/api/doc) attributes.
 
-## Scorer.\_\_init\_\_ {#init tag="method"}
+## Scorer.\_\_init\_\_ {id="init",tag="method"}
 
 Create a new `Scorer`.
 
@@ -35,7 +35,7 @@ Create a new `Scorer`.
 | _keyword-only_     |                                                                                                                                                                                                                                           |
 | `\*\*kwargs`       | Any additional settings to pass on to the individual scoring methods. ~~Any~~                                                                                                                                                             |
 
-## Scorer.score {#score tag="method"}
+## Scorer.score {id="score",tag="method"}
 
 Calculate the scores for a list of [`Example`](/api/example) objects using the
 scoring methods provided by the components in the pipeline.
@@ -72,11 +72,11 @@ core pipeline components, the individual score names start with the `Token` or
 | `examples`  | The `Example` objects holding both the predictions and the correct gold-standard annotations. ~~Iterable[Example]~~ |
 | **RETURNS** | A dictionary of scores. ~~Dict[str, Union[float, Dict[str, float]]]~~                                               |
 
-## Scorer.score_tokenization {#score_tokenization tag="staticmethod" new="3"}
+## Scorer.score_tokenization {id="score_tokenization",tag="staticmethod",version="3"}
 
 Scores the tokenization:
 
-- `token_acc`: number of correct tokens / number of gold tokens
+- `token_acc`: number of correct tokens / number of predicted tokens
 - `token_p`, `token_r`, `token_f`: precision, recall and F-score for token
   character spans
 
@@ -93,7 +93,7 @@ Docs with `has_unknown_spaces` are skipped during scoring.
 | `examples`  | The `Example` objects holding both the predictions and the correct gold-standard annotations. ~~Iterable[Example]~~ |
 | **RETURNS** | `Dict`                                                                                                              | A dictionary containing the scores `token_acc`, `token_p`, `token_r`, `token_f`. ~~Dict[str, float]]~~ |
 
-## Scorer.score_token_attr {#score_token_attr tag="staticmethod" new="3"}
+## Scorer.score_token_attr {id="score_token_attr",tag="staticmethod",version="3"}
 
 Scores a single token attribute. Tokens with missing values in the reference doc
 are skipped during scoring.
@@ -114,7 +114,7 @@ are skipped during scoring.
 | `missing_values` | Attribute values to treat as missing annotation in the reference annotation. Defaults to `{0, None, ""}`. ~~Set[Any]~~                                        |
 | **RETURNS**      | A dictionary containing the score `{attr}_acc`. ~~Dict[str, float]~~                                                                                          |
 
-## Scorer.score_token_attr_per_feat {#score_token_attr_per_feat tag="staticmethod" new="3"}
+## Scorer.score_token_attr_per_feat {id="score_token_attr_per_feat",tag="staticmethod",version="3"}
 
 Scores a single token attribute per feature for a token attribute in the
 Universal Dependencies
@@ -138,7 +138,7 @@ scoring.
 | `missing_values` | Attribute values to treat as missing annotation in the reference annotation. Defaults to `{0, None, ""}`. ~~Set[Any]~~                                                  |
 | **RETURNS**      | A dictionary containing the micro PRF scores under the key `{attr}_micro_p/r/f` and the per-feature PRF scores under `{attr}_per_feat`. ~~Dict[str, Dict[str, float]]~~ |
 
-## Scorer.score_spans {#score_spans tag="staticmethod" new="3"}
+## Scorer.score_spans {id="score_spans",tag="staticmethod",version="3"}
 
 Returns PRF scores for labeled or unlabeled spans.
 
@@ -160,7 +160,7 @@ Returns PRF scores for labeled or unlabeled spans.
 | `allow_overlap`  | Defaults to `False`. Whether or not to allow overlapping spans. If set to `False`, the alignment will automatically resolve conflicts. ~~bool~~                                             |
 | **RETURNS**      | A dictionary containing the PRF scores under the keys `{attr}_p`, `{attr}_r`, `{attr}_f` and the per-type PRF scores under `{attr}_per_type`. ~~Dict[str, Union[float, Dict[str, float]]]~~ |
 
-## Scorer.score_deps {#score_deps tag="staticmethod" new="3"}
+## Scorer.score_deps {id="score_deps",tag="staticmethod",version="3"}
 
 Calculate the UAS, LAS, and LAS per type scores for dependency parses. Tokens
 with missing values for the `attr` (typically `dep`) are skipped during scoring.
@@ -194,7 +194,7 @@ with missing values for the `attr` (typically `dep`) are skipped during scoring.
 | `missing_values` | Attribute values to treat as missing annotation in the reference annotation. Defaults to `{0, None, ""}`. ~~Set[Any]~~                                        |
 | **RETURNS**      | A dictionary containing the scores: `{attr}_uas`, `{attr}_las`, and `{attr}_las_per_type`. ~~Dict[str, Union[float, Dict[str, float]]]~~                      |
 
-## Scorer.score_cats {#score_cats tag="staticmethod" new="3"}
+## Scorer.score_cats {id="score_cats",tag="staticmethod",version="3"}
 
 Calculate PRF and ROC AUC scores for a doc-level attribute that is a dict
 containing scores for each label like `Doc.cats`. The returned dictionary
@@ -241,7 +241,7 @@ The reported `{attr}_score` depends on the classification properties:
 | `threshold`      | Cutoff to consider a prediction "positive". Defaults to `0.5` for multi-label, and `0.0` (i.e. whatever's highest scoring) otherwise. ~~float~~                                                    |
 | **RETURNS**      | A dictionary containing the scores, with inapplicable scores as `None`. ~~Dict[str, Optional[float]]~~                                                                                             |
 
-## Scorer.score_links {#score_links tag="staticmethod" new="3"}
+## Scorer.score_links {id="score_links",tag="staticmethod",version="3"}
 
 Returns PRF for predicted links on the entity level. To disentangle the
 performance of the NEL from the NER, this method only evaluates NEL links for
@@ -264,7 +264,7 @@ entities that overlap between the gold reference and the predictions.
 | `negative_labels` | The string values that refer to no annotation (e.g. "NIL"). ~~Iterable[str]~~                                       |
 | **RETURNS**       | A dictionary containing the scores. ~~Dict[str, Optional[float]]~~                                                  |
 
-## get_ner_prf {#get_ner_prf new="3"}
+## get_ner_prf {id="get_ner_prf",version="3"}
 
 Compute micro-PRF and per-entity PRF scores.
 
@@ -272,7 +272,7 @@ Compute micro-PRF and per-entity PRF scores.
 | ---------- | ------------------------------------------------------------------------------------------------------------------- |
 | `examples` | The `Example` objects holding both the predictions and the correct gold-standard annotations. ~~Iterable[Example]~~ |
 
-## score_coref_clusters {#score_coref_clusters tag="experimental"}
+## score_coref_clusters {id="score_coref_clusters",tag="experimental"}
 
 Returns LEA ([Moosavi and Strube, 2016](https://aclanthology.org/P16-1060/)) PRF
 scores for coreference clusters.
@@ -301,7 +301,7 @@ the [CoreferenceResolver](/api/coref) docs.
 | `span_cluster_prefix` | The prefix used for spans representing coreference clusters. ~~str~~                                                |
 | **RETURNS**           | A dictionary containing the scores. ~~Dict[str, Optional[float]]~~                                                  |
 
-## score_span_predictions {#score_span_predictions tag="experimental"}
+## score_span_predictions {id="score_span_predictions",tag="experimental"}
 
 Return accuracy for reconstructions of spans from single tokens. Only exactly
 correct predictions are counted as correct, there is no partial credit for near

website/docs/api/sentencerecognizer.mdx

@@ -2,7 +2,7 @@
 title: SentenceRecognizer
 tag: class
 source: spacy/pipeline/senter.pyx
-new: 3
+version: 3
 teaser: 'Pipeline component for sentence segmentation'
 api_base_class: /api/tagger
 api_string_name: senter
@@ -12,7 +12,7 @@ api_trainable: true
 A trainable pipeline component for sentence segmentation. For a simpler,
 rule-based strategy, see the [`Sentencizer`](/api/sentencizer).
 
-## Assigned Attributes {#assigned-attributes}
+## Assigned Attributes {id="assigned-attributes"}
 
 Predicted values will be assigned to `Token.is_sent_start`. The resulting
 sentences can be accessed using `Doc.sents`.
@@ -22,7 +22,7 @@ sentences can be accessed using `Doc.sents`.
 | `Token.is_sent_start` | A boolean value indicating whether the token starts a sentence. This will be either `True` or `False` for all tokens. ~~bool~~ |
 | `Doc.sents`           | An iterator over sentences in the `Doc`, determined by `Token.is_sent_start` values. ~~Iterator[Span]~~                        |
 
-## Config and implementation {#config}
+## Config and implementation {id="config"}
 
 The default config is defined by the pipeline component factory and describes
 how the component should be configured. You can override its settings via the
@@ -49,7 +49,7 @@ architectures and their arguments and hyperparameters.
 %%GITHUB_SPACY/spacy/pipeline/senter.pyx
 ```
 
-## SentenceRecognizer.\_\_init\_\_ {#init tag="method"}
+## SentenceRecognizer.\_\_init\_\_ {id="init",tag="method"}
 
 Initialize the sentence recognizer.
 
@@ -81,7 +81,7 @@ shortcut for this and instantiate the component using its string name and
 | `overwrite` <Tag variant="new">3.2</Tag> | Whether existing annotation is overwritten. Defaults to `False`. ~~bool~~                                                           |
 | `scorer` <Tag variant="new">3.2</Tag>    | The scoring method. Defaults to [`Scorer.score_spans`](/api/scorer#score_spans) for the attribute `"sents"`. ~~Optional[Callable]~~ |
 
-## SentenceRecognizer.\_\_call\_\_ {#call tag="method"}
+## SentenceRecognizer.\_\_call\_\_ {id="call",tag="method"}
 
 Apply the pipe to one document. The document is modified in place, and returned.
 This usually happens under the hood when the `nlp` object is called on a text
@@ -105,7 +105,7 @@ and all pipeline components are applied to the `Doc` in order. Both
 | `doc`       | The document to process. ~~Doc~~ |
 | **RETURNS** | The processed document. ~~Doc~~  |
 
-## SentenceRecognizer.pipe {#pipe tag="method"}
+## SentenceRecognizer.pipe {id="pipe",tag="method"}
 
 Apply the pipe to a stream of documents. This usually happens under the hood
 when the `nlp` object is called on a text and all pipeline components are
@@ -129,7 +129,7 @@ and [`pipe`](/api/sentencerecognizer#pipe) delegate to the
 | `batch_size`   | The number of documents to buffer. Defaults to `128`. ~~int~~ |
 | **YIELDS**     | The processed documents in order. ~~Doc~~                     |
 
-## SentenceRecognizer.initialize {#initialize tag="method"}
+## SentenceRecognizer.initialize {id="initialize",tag="method"}
 
 Initialize the component for training. `get_examples` should be a function that
 returns an iterable of [`Example`](/api/example) objects. **At least one example
@@ -153,7 +153,7 @@ by [`Language.initialize`](/api/language#initialize).
 | _keyword-only_ |                                                                                                                                                                            |
 | `nlp`          | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~                                                                                                       |
 
-## SentenceRecognizer.predict {#predict tag="method"}
+## SentenceRecognizer.predict {id="predict",tag="method"}
 
 Apply the component's model to a batch of [`Doc`](/api/doc) objects, without
 modifying them.
@@ -170,7 +170,7 @@ modifying them.
 | `docs`      | The documents to predict. ~~Iterable[Doc]~~ |
 | **RETURNS** | The model's prediction for each document.   |
 
-## SentenceRecognizer.set_annotations {#set_annotations tag="method"}
+## SentenceRecognizer.set_annotations {id="set_annotations",tag="method"}
 
 Modify a batch of [`Doc`](/api/doc) objects, using pre-computed scores.
 
@@ -187,7 +187,7 @@ Modify a batch of [`Doc`](/api/doc) objects, using pre-computed scores.
 | `docs`   | The documents to modify. ~~Iterable[Doc]~~                   |
 | `scores` | The scores to set, produced by `SentenceRecognizer.predict`. |
 
-## SentenceRecognizer.update {#update tag="method"}
+## SentenceRecognizer.update {id="update",tag="method"}
 
 Learn from a batch of [`Example`](/api/example) objects containing the
 predictions and gold-standard annotations, and update the component's model.
@@ -211,7 +211,7 @@ Delegates to [`predict`](/api/sentencerecognizer#predict) and
 | `losses`       | Optional record of the loss during training. Updated using the component name as the key. ~~Optional[Dict[str, float]]~~ |
 | **RETURNS**    | The updated `losses` dictionary. ~~Dict[str, float]~~                                                                    |
 
-## SentenceRecognizer.rehearse {#rehearse tag="method,experimental" new="3"}
+## SentenceRecognizer.rehearse {id="rehearse",tag="method,experimental",version="3"}
 
 Perform a "rehearsal" update from a batch of data. Rehearsal updates teach the
 current model to make predictions similar to an initial model to try to address
@@ -234,7 +234,7 @@ the "catastrophic forgetting" problem. This feature is experimental.
 | `losses`       | Optional record of the loss during training. Updated using the component name as the key. ~~Optional[Dict[str, float]]~~ |
 | **RETURNS**    | The updated `losses` dictionary. ~~Dict[str, float]~~                                                                    |
 
-## SentenceRecognizer.get_loss {#get_loss tag="method"}
+## SentenceRecognizer.get_loss {id="get_loss",tag="method"}
 
 Find the loss and gradient of loss for the batch of documents and their
 predicted scores.
@@ -253,7 +253,7 @@ predicted scores.
 | `scores`    | Scores representing the model's predictions.                                |
 | **RETURNS** | The loss and the gradient, i.e. `(loss, gradient)`. ~~Tuple[float, float]~~ |
 
-## SentenceRecognizer.create_optimizer {#create_optimizer tag="method"}
+## SentenceRecognizer.create_optimizer {id="create_optimizer",tag="method"}
 
 Create an optimizer for the pipeline component.
 
@@ -268,7 +268,7 @@ Create an optimizer for the pipeline component.
 | ----------- | ---------------------------- |
 | **RETURNS** | The optimizer. ~~Optimizer~~ |
 
-## SentenceRecognizer.use_params {#use_params tag="method, contextmanager"}
+## SentenceRecognizer.use_params {id="use_params",tag="method, contextmanager"}
 
 Modify the pipe's model, to use the given parameter values. At the end of the
 context, the original parameters are restored.
@@ -285,7 +285,7 @@ context, the original parameters are restored.
 | -------- | -------------------------------------------------- |
 | `params` | The parameter values to use in the model. ~~dict~~ |
 
-## SentenceRecognizer.to_disk {#to_disk tag="method"}
+## SentenceRecognizer.to_disk {id="to_disk",tag="method"}
 
 Serialize the pipe to disk.
 
@@ -302,7 +302,7 @@ Serialize the pipe to disk.
 | _keyword-only_ |                                                                                                                                            |
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~                                                |
 
-## SentenceRecognizer.from_disk {#from_disk tag="method"}
+## SentenceRecognizer.from_disk {id="from_disk",tag="method"}
 
 Load the pipe from disk. Modifies the object in place and returns it.
 
@@ -320,7 +320,7 @@ Load the pipe from disk. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~     |
 | **RETURNS**    | The modified `SentenceRecognizer` object. ~~SentenceRecognizer~~                                |
 
-## SentenceRecognizer.to_bytes {#to_bytes tag="method"}
+## SentenceRecognizer.to_bytes {id="to_bytes",tag="method"}
 
 > #### Example
 >
@@ -337,7 +337,7 @@ Serialize the pipe to a bytestring.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The serialized form of the `SentenceRecognizer` object. ~~bytes~~                           |
 
-## SentenceRecognizer.from_bytes {#from_bytes tag="method"}
+## SentenceRecognizer.from_bytes {id="from_bytes",tag="method"}
 
 Load the pipe from a bytestring. Modifies the object in place and returns it.
 
@@ -356,7 +356,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The `SentenceRecognizer` object. ~~SentenceRecognizer~~                                     |
 
-## Serialization fields {#serialization-fields}
+## Serialization fields {id="serialization-fields"}
 
 During serialization, spaCy will export several data fields used to restore
 different aspects of the object. If needed, you can exclude them from

website/docs/api/sentencizer.mdx

@@ -13,7 +13,7 @@ performed by the [`DependencyParser`](/api/dependencyparser), so the
 `Sentencizer` lets you implement a simpler, rule-based strategy that doesn't
 require a statistical model to be loaded.
 
-## Assigned Attributes {#assigned-attributes}
+## Assigned Attributes {id="assigned-attributes"}
 
 Calculated values will be assigned to `Token.is_sent_start`. The resulting
 sentences can be accessed using `Doc.sents`.
@@ -23,7 +23,7 @@ sentences can be accessed using `Doc.sents`.
 | `Token.is_sent_start` | A boolean value indicating whether the token starts a sentence. This will be either `True` or `False` for all tokens. ~~bool~~ |
 | `Doc.sents`           | An iterator over sentences in the `Doc`, determined by `Token.is_sent_start` values. ~~Iterator[Span]~~                        |
 
-## Config and implementation {#config}
+## Config and implementation {id="config"}
 
 The default config is defined by the pipeline component factory and describes
 how the component should be configured. You can override its settings via the
@@ -39,7 +39,7 @@ how the component should be configured. You can override its settings via the
 
 | Setting                                  | Description                                                                                                                                            |
 | ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| `punct_chars`                            | Optional custom list of punctuation characters that mark sentence ends. See below for defaults if not set. Defaults to `None`. ~~Optional[List[str]]~~ | `None` |
+| `punct_chars`                            | Optional custom list of punctuation characters that mark sentence ends. See below for defaults if not set. Defaults to `None`. ~~Optional[List[str]]~~ |
 | `overwrite` <Tag variant="new">3.2</Tag> | Whether existing annotation is overwritten. Defaults to `False`. ~~bool~~                                                                              |
 | `scorer` <Tag variant="new">3.2</Tag>    | The scoring method. Defaults to [`Scorer.score_spans`](/api/scorer#score_spans) for the attribute `"sents"` ~~Optional[Callable]~~                     |
 
@@ -47,7 +47,7 @@ how the component should be configured. You can override its settings via the
 %%GITHUB_SPACY/spacy/pipeline/sentencizer.pyx
 ```
 
-## Sentencizer.\_\_init\_\_ {#init tag="method"}
+## Sentencizer.\_\_init\_\_ {id="init",tag="method"}
 
 Initialize the sentencizer.
 
@@ -69,8 +69,7 @@ Initialize the sentencizer.
 | `overwrite` <Tag variant="new">3.2</Tag> | Whether existing annotation is overwritten. Defaults to `False`. ~~bool~~                                                          |
 | `scorer` <Tag variant="new">3.2</Tag>    | The scoring method. Defaults to [`Scorer.score_spans`](/api/scorer#score_spans) for the attribute `"sents"` ~~Optional[Callable]~~ |
 
-```python
+```python {title="punct_chars defaults"}
-### punct_chars defaults
 ['!', '.', '?', '։', '؟', '۔', '܀', '܁', '܂', '߹', '।', '॥', '၊', '။', '።',
  '፧', '፨', '᙮', '᜵', '᜶', '᠃', '᠉', '᥄', '᥅', '᪨', '᪩', '᪪', '᪫',
  '᭚', '᭛', '᭞', '᭟', '᰻', '᰼', '᱾', '᱿', '‼', '‽', '⁇', '⁈', '⁉',
@@ -83,7 +82,7 @@ Initialize the sentencizer.
  '𑪜', '𑱁', '𑱂', '𖩮', '𖩯', '𖫵', '𖬷', '𖬸', '𖭄', '𛲟', '𝪈', '｡', '。']
 ```
 
-## Sentencizer.\_\_call\_\_ {#call tag="method"}
+## Sentencizer.\_\_call\_\_ {id="call",tag="method"}
 
 Apply the sentencizer on a `Doc`. Typically, this happens automatically after
 the component has been added to the pipeline using
@@ -105,7 +104,7 @@ the component has been added to the pipeline using
 | `doc`       | The `Doc` object to process, e.g. the `Doc` in the pipeline. ~~Doc~~ |
 | **RETURNS** | The modified `Doc` with added sentence boundaries. ~~Doc~~           |
 
-## Sentencizer.pipe {#pipe tag="method"}
+## Sentencizer.pipe {id="pipe",tag="method"}
 
 Apply the pipe to a stream of documents. This usually happens under the hood
 when the `nlp` object is called on a text and all pipeline components are
@@ -126,7 +125,7 @@ applied to the `Doc` in order.
 | `batch_size`   | The number of documents to buffer. Defaults to `128`. ~~int~~ |
 | **YIELDS**     | The processed documents in order. ~~Doc~~                     |
 
-## Sentencizer.to_disk {#to_disk tag="method"}
+## Sentencizer.to_disk {id="to_disk",tag="method"}
 
 Save the sentencizer settings (punctuation characters) to a directory. Will
 create a file `sentencizer.json`. This also happens automatically when you save
@@ -144,7 +143,7 @@ an `nlp` object with a sentencizer added to its pipeline.
 | ------ | ------------------------------------------------------------------------------------------------------------------------------------------ |
 | `path` | A path to a JSON file, which will be created if it doesn't exist. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ |
 
-## Sentencizer.from_disk {#from_disk tag="method"}
+## Sentencizer.from_disk {id="from_disk",tag="method"}
 
 Load the sentencizer settings from a file. Expects a JSON file. This also
 happens automatically when you load an `nlp` object or model with a sentencizer
@@ -162,7 +161,7 @@ added to its pipeline.
 | `path`      | A path to a JSON file. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ |
 | **RETURNS** | The modified `Sentencizer` object. ~~Sentencizer~~                                              |
 
-## Sentencizer.to_bytes {#to_bytes tag="method"}
+## Sentencizer.to_bytes {id="to_bytes",tag="method"}
 
 Serialize the sentencizer settings to a bytestring.
 
@@ -178,7 +177,7 @@ Serialize the sentencizer settings to a bytestring.
 | ----------- | ------------------------------ |
 | **RETURNS** | The serialized data. ~~bytes~~ |
 
-## Sentencizer.from_bytes {#from_bytes tag="method"}
+## Sentencizer.from_bytes {id="from_bytes",tag="method"}
 
 Load the pipe from a bytestring. Modifies the object in place and returns it.