Merge pull request #13287 from explosion/docs/llm_main

Sync `docs/llm_develop` with `docs/llm_main`

.github/FUNDING.yml

@@ -0,0 +1 @@
+custom: [https://explosion.ai/merch, https://explosion.ai/tailored-solutions]

.github/workflows/tests.yml

@@ -58,7 +58,7 @@ jobs:
       fail-fast: true
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
-        python_version: ["3.11", "3.12.0-rc.2"]
+        python_version: ["3.12"]
         include:
           - os: windows-latest
             python_version: "3.7"
@@ -68,6 +68,8 @@ jobs:
             python_version: "3.9"
           - os: windows-latest
             python_version: "3.10"
+          - os: macos-latest
+            python_version: "3.11"
 
     runs-on: ${{ matrix.os }}
 

LICENSE

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (C) 2016-2022 ExplosionAI GmbH, 2016 spaCy GmbH, 2015 Matthew Honnibal
+Copyright (C) 2016-2023 ExplosionAI GmbH, 2016 spaCy GmbH, 2015 Matthew Honnibal
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -39,28 +39,35 @@ open-source software, released under the
 | 🚀 **[New in v3.0]**                                                                                                                                                                                                      | New features, backwards incompatibilities and migration guide.                                                                                                                                                                                                                                                                               |
 | 🪐 **[Project Templates]**                                                                                                                                                                                                | End-to-end workflows you can clone, modify and run.                                                                                                                                                                                                                                                                                          |
 | 🎛 **[API Reference]**                                                                                                                                                                                                     | The detailed reference for spaCy's API.                                                                                                                                                                                                                                                                                                      |
+| ⏩ **[GPU Processing]**                                                                                                                                                                                                    | Use spaCy with CUDA-compatible GPU processing.                                                                                                                                                                                                                                                                                               |
 | 📦 **[Models]**                                                                                                                                                                                                           | Download trained pipelines for spaCy.                                                                                                                                                                                                                                                                                                        |
+| 🦙 **[Large Language Models]**                                                                                                                                                                                            | Integrate LLMs into spaCy pipelines.                                                                                                                                                                                                                                                                                                        |
 | 🌌 **[Universe]**                                                                                                                                                                                                         | Plugins, extensions, demos and books from the spaCy ecosystem.                                                                                                                                                                                                                                                                               |
 | ⚙️ **[spaCy VS Code Extension]**                                                                                                                                                                                          | Additional tooling and features for working with spaCy's config files.                                                                                                                                                                                                                                                                       |
 | 👩‍🏫 **[Online Course]**                                                                                                                                                                                                    | Learn spaCy in this free and interactive online course.                                                                                                                                                                                                                                                                                      |
+| 📰 **[Blog]**                                                                                                                                                                                                             | Read about current spaCy and Prodigy development, releases, talks and more from Explosion.                                                                                                                                                                                                                 |
 | 📺 **[Videos]**                                                                                                                                                                                                           | Our YouTube channel with video tutorials, talks and more.                                                                                                                                                                                                                                                                                    |
 | 🛠 **[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)**                 |
+| 👕 **[Swag]**                                                                                                                                                                                                             | Support us and our work with unique, custom-designed swag!                                                                                                                                                                                                                                                                                   |
-| <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)** |
+| <a href="https://explosion.ai/tailored-solutions"><img src="https://github.com/explosion/spaCy/assets/13643239/36d2a42e-98c0-4599-90e1-788ef75181be" width="150" alt="Tailored Solutions"/></a> | Custom NLP consulting, implementation and strategic advice by spaCy’s core development team. Streamlined, production-ready, predictable and maintainable. Send us an email or take our 5-minute questionnaire, and well'be in touch! **[Learn more &rarr;](https://explosion.ai/tailored-solutions)**                 |
 
 [spacy 101]: https://spacy.io/usage/spacy-101
 [new in v3.0]: https://spacy.io/usage/v3
 [usage guides]: https://spacy.io/usage/
 [api reference]: https://spacy.io/api/
+[gpu processing]: https://spacy.io/usage#gpu
 [models]: https://spacy.io/models
+[large language models]: https://spacy.io/usage/large-language-models
 [universe]: https://spacy.io/universe
 [spacy vs code extension]: https://github.com/explosion/spacy-vscode
 [videos]: https://www.youtube.com/c/ExplosionAI
 [online course]: https://course.spacy.io
+[blog]: https://explosion.ai
 [project templates]: https://github.com/explosion/projects
 [changelog]: https://spacy.io/usage#changelog
 [contribute]: https://github.com/explosion/spaCy/blob/master/CONTRIBUTING.md
+[swag]: https://explosion.ai/merch
 
 ## 💬 Where to ask questions
 

licenses/3rd_party_licenses.txt

@@ -158,3 +158,45 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
+
+
+SciPy
+-----
+
+* Files: scorer.py
+
+The implementation of trapezoid() is adapted from SciPy, which is distributed
+under the following license:
+
+New BSD License
+
+Copyright (c) 2001-2002 Enthought, Inc. 2003-2023, SciPy Developers.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions
+are met:
+
+1. Redistributions of source code must retain the above copyright
+   notice, this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above
+   copyright notice, this list of conditions and the following
+   disclaimer in the documentation and/or other materials provided
+   with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived
+   from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

pyproject.toml

@@ -5,7 +5,7 @@ requires = [
     "cymem>=2.0.2,<2.1.0",
     "preshed>=3.0.2,<3.1.0",
     "murmurhash>=0.28.0,<1.1.0",
-    "thinc>=8.1.8,<8.3.0",
+    "thinc>=8.2.2,<8.3.0",
     "numpy>=1.15.0; python_version < '3.9'",
     "numpy>=1.25.0; python_version >= '3.9'",
 ]

requirements.txt

@@ -3,7 +3,7 @@ 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>=8.1.8,<8.3.0
+thinc>=8.2.2,<8.3.0
 ml_datasets>=0.2.0,<0.3.0
 murmurhash>=0.28.0,<1.1.0
 wasabi>=0.9.1,<1.2.0

setup.cfg

@@ -41,7 +41,7 @@ setup_requires =
     cymem>=2.0.2,<2.1.0
     preshed>=3.0.2,<3.1.0
     murmurhash>=0.28.0,<1.1.0
-    thinc>=8.1.8,<8.3.0
+    thinc>=8.2.2,<8.3.0
 install_requires =
     # Our libraries
     spacy-legacy>=3.0.11,<3.1.0
@@ -49,7 +49,7 @@ install_requires =
     murmurhash>=0.28.0,<1.1.0
     cymem>=2.0.2,<2.1.0
     preshed>=3.0.2,<3.1.0
-    thinc>=8.1.8,<8.3.0
+    thinc>=8.2.2,<8.3.0
     wasabi>=0.9.1,<1.2.0
     srsly>=2.4.3,<3.0.0
     catalogue>=2.0.6,<2.1.0

spacy/about.py

@@ -1,5 +1,5 @@
 # fmt: off
 __title__ = "spacy"
-__version__ = "3.7.1"
+__version__ = "3.7.2"
 __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
 __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"

spacy/cli/__init__.py

@@ -22,8 +22,17 @@ from .init_pipeline import init_pipeline_cli  # noqa: F401
 from .package import package  # noqa: F401
 from .pretrain import pretrain  # noqa: F401
 from .profile import profile  # noqa: F401
-from .train import train_cli  # noqa: F401
+from .project.assets import project_assets  # type: ignore[attr-defined]  # noqa: F401
-from .validate import validate  # noqa: F401
+from .project.clone import project_clone  # type: ignore[attr-defined]  # noqa: F401
+from .project.document import (  # type: ignore[attr-defined]  # noqa: F401
+    project_document,
+)
+from .project.dvc import project_update_dvc  # type: ignore[attr-defined]  # noqa: F401
+from .project.pull import project_pull  # type: ignore[attr-defined]  # noqa: F401
+from .project.push import project_push  # type: ignore[attr-defined]  # noqa: F401
+from .project.run import project_run  # type: ignore[attr-defined]  # noqa: F401
+from .train import train_cli  # type: ignore[attr-defined]  # noqa: F401
+from .validate import validate  # type: ignore[attr-defined]  # noqa: F401
 
 
 @app.command("link", no_args_is_help=True, deprecated=True, hidden=True)

spacy/cli/benchmark_speed.py

@@ -13,7 +13,7 @@ from .. import util
 from ..language import Language
 from ..tokens import Doc
 from ..training import Corpus
-from ._util import Arg, Opt, benchmark_cli, setup_gpu
+from ._util import Arg, Opt, benchmark_cli, import_code, setup_gpu
 
 
 @benchmark_cli.command(
@@ -30,12 +30,14 @@ def benchmark_speed_cli(
     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"),
+    code_path: Optional[Path] = Opt(None, "--code", "-c", help="Path to Python file with additional code (registered functions) to be imported"),
     # fmt: on
 ):
     """
     Benchmark a pipeline. Expects a loadable spaCy pipeline and benchmark
     data in the binary .spacy format.
     """
+    import_code(code_path)
     setup_gpu(use_gpu=use_gpu, silent=False)
 
     nlp = util.load_model(model)
@@ -171,5 +173,5 @@ def print_outliers(sample: numpy.ndarray):
 def warmup(
     nlp: Language, docs: List[Doc], warmup_epochs: int, batch_size: Optional[int]
 ) -> numpy.ndarray:
-    docs = warmup_epochs * docs
+    docs = [doc.copy() for doc in docs * warmup_epochs]
     return annotate(nlp, docs, batch_size)

spacy/cli/download.py

@@ -7,7 +7,14 @@ from wasabi import msg
 
 from .. import about
 from ..errors import OLD_MODEL_SHORTCUTS
-from ..util import get_minor_version, is_package, is_prerelease_version, run_command
+from ..util import (
+    get_minor_version,
+    is_in_interactive,
+    is_in_jupyter,
+    is_package,
+    is_prerelease_version,
+    run_command,
+)
 from ._util import SDIST_SUFFIX, WHEEL_SUFFIX, Arg, Opt, app
 
 
@@ -77,6 +84,27 @@ def download(
         "Download and installation successful",
         f"You can now load the package via spacy.load('{model_name}')",
     )
+    if is_in_jupyter():
+        reload_deps_msg = (
+            "If you are in a Jupyter or Colab notebook, you may need to "
+            "restart Python in order to load all the package's dependencies. "
+            "You can do this by selecting the 'Restart kernel' or 'Restart "
+            "runtime' option."
+        )
+        msg.warn(
+            "Restart to reload dependencies",
+            reload_deps_msg,
+        )
+    elif is_in_interactive():
+        reload_deps_msg = (
+            "If you are in an interactive Python session, you may need to "
+            "exit and restart Python to load all the package's dependencies. "
+            "You can exit with Ctrl-D (or Ctrl-Z and Enter on Windows)."
+        )
+        msg.warn(
+            "Restart to reload dependencies",
+            reload_deps_msg,
+        )
 
 
 def get_model_filename(model_name: str, version: str, sdist: bool = False) -> str:

spacy/cli/package.py

@@ -1,5 +1,7 @@
+import os
 import re
 import shutil
+import subprocess
 import sys
 from collections import defaultdict
 from pathlib import Path
@@ -11,6 +13,7 @@ from thinc.api import Config
 from wasabi import MarkdownRenderer, Printer, get_raw_input
 
 from .. import about, util
+from ..compat import importlib_metadata
 from ..schemas import ModelMetaSchema, validate
 from ._util import SDIST_SUFFIX, WHEEL_SUFFIX, Arg, Opt, app, string_to_list
 
@@ -35,7 +38,7 @@ def package_cli(
     specified output directory, and the data will be copied over. If
     --create-meta is set and a meta.json already exists in the output directory,
     the existing values will be used as the defaults in the command-line prompt.
-    After packaging, "python setup.py sdist" is run in the package directory,
+    After packaging, "python -m build --sdist" is run in the package directory,
     which will create a .tar.gz archive that can be installed via "pip install".
 
     If additional code files are provided (e.g. Python files containing custom
@@ -78,9 +81,17 @@ def package(
     input_path = util.ensure_path(input_dir)
     output_path = util.ensure_path(output_dir)
     meta_path = util.ensure_path(meta_path)
-    if create_wheel and not has_wheel():
+    if create_wheel and not has_wheel() and not has_build():
-        err = "Generating a binary .whl file requires wheel to be installed"
+        err = (
-        msg.fail(err, "pip install wheel", exits=1)
+            "Generating wheels requires 'build' or 'wheel' (deprecated) to be installed"
+        )
+        msg.fail(err, "pip install build", exits=1)
+    if not has_build():
+        msg.warn(
+            "Generating packages without the 'build' package is deprecated and "
+            "will not be supported in the future. To install 'build': pip "
+            "install build"
+        )
     if not input_path or not input_path.exists():
         msg.fail("Can't locate pipeline data", input_path, exits=1)
     if not output_path or not output_path.exists():
@@ -184,12 +195,37 @@ def package(
     msg.good(f"Successfully created package directory '{model_name_v}'", main_path)
     if create_sdist:
         with util.working_dir(main_path):
+            # run directly, since util.run_command is not designed to continue
+            # after a command fails
+            ret = subprocess.run(
+                [sys.executable, "-m", "build", ".", "--sdist"],
+                env=os.environ.copy(),
+            )
+            if ret.returncode != 0:
+                msg.warn(
+                    "Creating sdist with 'python -m build' failed. Falling "
+                    "back to deprecated use of 'python setup.py sdist'"
+                )
                 util.run_command([sys.executable, "setup.py", "sdist"], capture=False)
         zip_file = main_path / "dist" / f"{model_name_v}{SDIST_SUFFIX}"
         msg.good(f"Successfully created zipped Python package", zip_file)
     if create_wheel:
         with util.working_dir(main_path):
-            util.run_command([sys.executable, "setup.py", "bdist_wheel"], capture=False)
+            # run directly, since util.run_command is not designed to continue
+            # after a command fails
+            ret = subprocess.run(
+                [sys.executable, "-m", "build", ".", "--wheel"],
+                env=os.environ.copy(),
+            )
+            if ret.returncode != 0:
+                msg.warn(
+                    "Creating wheel with 'python -m build' failed. Falling "
+                    "back to deprecated use of 'wheel' with "
+                    "'python setup.py bdist_wheel'"
+                )
+                util.run_command(
+                    [sys.executable, "setup.py", "bdist_wheel"], capture=False
+                )
         wheel_name_squashed = re.sub("_+", "_", model_name_v)
         wheel = main_path / "dist" / f"{wheel_name_squashed}{WHEEL_SUFFIX}"
         msg.good(f"Successfully created binary wheel", wheel)
@@ -209,6 +245,17 @@ def has_wheel() -> bool:
         return False
 
 
+def has_build() -> bool:
+    # it's very likely that there is a local directory named build/ (especially
+    # in an editable install), so an import check is not sufficient; instead
+    # check that there is a package version
+    try:
+        importlib_metadata.version("build")
+        return True
+    except importlib_metadata.PackageNotFoundError:  # type: ignore[attr-defined]
+        return False
+
+
 def get_third_party_dependencies(
     config: Config, exclude: List[str] = util.SimpleFrozenList()
 ) -> List[str]:

spacy/cli/project/assets.py

@@ -0,0 +1 @@
+from weasel.cli.assets import *

spacy/cli/project/clone.py

@@ -0,0 +1 @@
+from weasel.cli.clone import *

spacy/cli/project/document.py

@@ -0,0 +1 @@
+from weasel.cli.document import *

spacy/cli/project/dvc.py

@@ -0,0 +1 @@
+from weasel.cli.dvc import *

spacy/cli/project/pull.py

@@ -0,0 +1 @@
+from weasel.cli.pull import *

spacy/cli/project/push.py

@@ -0,0 +1 @@
+from weasel.cli.push import *

spacy/cli/project/remote_storage.py

@@ -0,0 +1 @@
+from weasel.cli.remote_storage import *

spacy/cli/project/run.py

@@ -0,0 +1 @@
+from weasel.cli.run import *

spacy/cli/templates/quickstart_training.jinja

@@ -271,8 +271,9 @@ grad_factor = 1.0
 @layers = "reduce_mean.v1"
 
 [components.textcat.model.linear_model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
+length = 262144
 ngram_size = 1
 no_output_layer = false
 
@@ -308,8 +309,9 @@ grad_factor = 1.0
 @layers = "reduce_mean.v1"
 
 [components.textcat_multilabel.model.linear_model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = false
+length = 262144
 ngram_size = 1
 no_output_layer = false
 
@@ -542,14 +544,15 @@ nO = null
 width = ${components.tok2vec.model.encode.width}
 
 [components.textcat.model.linear_model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
+length = 262144
 ngram_size = 1
 no_output_layer = false
 
 {% else -%}
 [components.textcat.model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
 ngram_size = 1
 no_output_layer = false
@@ -570,15 +573,17 @@ nO = null
 width = ${components.tok2vec.model.encode.width}
 
 [components.textcat_multilabel.model.linear_model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = false
+length = 262144
 ngram_size = 1
 no_output_layer = false
 
 {% else -%}
 [components.textcat_multilabel.model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = false
+length = 262144
 ngram_size = 1
 no_output_layer = false
 {%- endif %}

spacy/displacy/render.py

@@ -142,7 +142,25 @@ class SpanRenderer:
         spans (list): Individual entity spans and their start, end, label, kb_id and kb_url.
         title (str / None): Document title set in Doc.user_data['title'].
         """
-        per_token_info = []
+        per_token_info = self._assemble_per_token_info(tokens, spans)
+        markup = self._render_markup(per_token_info)
+        markup = TPL_SPANS.format(content=markup, dir=self.direction)
+        if title:
+            markup = TPL_TITLE.format(title=title) + markup
+        return markup
+
+    @staticmethod
+    def _assemble_per_token_info(
+        tokens: List[str], spans: List[Dict[str, Any]]
+    ) -> List[Dict[str, List[Dict[str, Any]]]]:
+        """Assembles token info used to generate markup in render_spans().
+        tokens (List[str]): Tokens in text.
+        spans (List[Dict[str, Any]]): Spans in text.
+        RETURNS (List[Dict[str, List[Dict, str, Any]]]): Per token info needed to render HTML markup for given tokens
+            and spans.
+        """
+        per_token_info: List[Dict[str, List[Dict[str, Any]]]] = []
+
         # we must sort so that we can correctly describe when spans need to "stack"
         # which is determined by their start token, then span length (longer spans on top),
         # then break any remaining ties with the span label
@@ -154,21 +172,22 @@ class SpanRenderer:
                 s["label"],
             ),
         )
+
         for s in spans:
             # this is the vertical 'slot' that the span will be rendered in
             # vertical_position = span_label_offset + (offset_step * (slot - 1))
             s["render_slot"] = 0
+
         for idx, token in enumerate(tokens):
             # Identify if a token belongs to a Span (and which) and if it's a
             # start token of said Span. We'll use this for the final HTML render
             token_markup: Dict[str, Any] = {}
             token_markup["text"] = token
-            concurrent_spans = 0
+            intersecting_spans: List[Dict[str, Any]] = []
             entities = []
             for span in spans:
                 ent = {}
                 if span["start_token"] <= idx < span["end_token"]:
-                    concurrent_spans += 1
                     span_start = idx == span["start_token"]
                     ent["label"] = span["label"]
                     ent["is_start"] = span_start
@@ -176,7 +195,12 @@ class SpanRenderer:
                         # When the span starts, we need to know how many other
                         # spans are on the 'span stack' and will be rendered.
                         # This value becomes the vertical render slot for this entire span
-                        span["render_slot"] = concurrent_spans
+                        span["render_slot"] = (
+                            intersecting_spans[-1]["render_slot"]
+                            if len(intersecting_spans)
+                            else 0
+                        ) + 1
+                    intersecting_spans.append(span)
                     ent["render_slot"] = span["render_slot"]
                     kb_id = span.get("kb_id", "")
                     kb_url = span.get("kb_url", "#")
@@ -193,11 +217,8 @@ class SpanRenderer:
                     span["render_slot"] = 0
             token_markup["entities"] = entities
             per_token_info.append(token_markup)
-        markup = self._render_markup(per_token_info)
+
-        markup = TPL_SPANS.format(content=markup, dir=self.direction)
+        return per_token_info
-        if title:
-            markup = TPL_TITLE.format(title=title) + markup
-        return markup
 
     def _render_markup(self, per_token_info: List[Dict[str, Any]]) -> str:
         """Render the markup from per-token information"""

spacy/errors.py

@@ -227,7 +227,6 @@ class Errors(metaclass=ErrorsWithCodes):
     E002 = ("Can't find factory for '{name}' for language {lang} ({lang_code}). "
             "This usually happens when spaCy calls `nlp.{method}` with a custom "
             "component name that's not registered on the current language class. "
-            "If you're using a Transformer, make sure to install 'spacy-transformers'. "
             "If you're using a custom component, make sure you've added the "
             "decorator `@Language.component` (for function components) or "
             "`@Language.factory` (for class components).\n\nAvailable "
@@ -984,6 +983,10 @@ class Errors(metaclass=ErrorsWithCodes):
              "predicted docs when training {component}.")
     E1055 = ("The 'replace_listener' callback expects {num_params} parameters, "
              "but only callbacks with one or three parameters are supported")
+    E1056 = ("The `TextCatBOW` architecture expects a length of at least 1, was {length}.")
+    E1057 = ("The `TextCatReduce` architecture must be used with at least one "
+             "reduction. Please enable one of `use_reduce_first`, "
+             "`use_reduce_last`, `use_reduce_max` or `use_reduce_mean`.")
 
 
 # Deprecated model shortcuts, only used in errors and warnings

spacy/kb/__init__.py

@@ -1,3 +1,11 @@
 from .candidate import Candidate, get_candidates, get_candidates_batch
 from .kb import KnowledgeBase
 from .kb_in_memory import InMemoryLookupKB
+
+__all__ = [
+    "Candidate",
+    "KnowledgeBase",
+    "InMemoryLookupKB",
+    "get_candidates",
+    "get_candidates_batch",
+]

spacy/lang/en/lex_attrs.py

@@ -6,7 +6,8 @@ _num_words = [
     "nine", "ten", "eleven", "twelve", "thirteen", "fourteen", "fifteen",
     "sixteen", "seventeen", "eighteen", "nineteen", "twenty", "thirty", "forty",
     "fifty", "sixty", "seventy", "eighty", "ninety", "hundred", "thousand",
-    "million", "billion", "trillion", "quadrillion", "gajillion", "bazillion"
+    "million", "billion", "trillion", "quadrillion", "quintillion", "sextillion",
+    "septillion", "octillion", "nonillion", "decillion", "gajillion", "bazillion"
 ]
 _ordinal_words = [
     "first", "second", "third", "fourth", "fifth", "sixth", "seventh", "eighth",
@@ -14,7 +15,8 @@ _ordinal_words = [
     "fifteenth", "sixteenth", "seventeenth", "eighteenth", "nineteenth",
     "twentieth", "thirtieth", "fortieth", "fiftieth", "sixtieth", "seventieth",
     "eightieth", "ninetieth", "hundredth", "thousandth", "millionth", "billionth",
-    "trillionth", "quadrillionth", "gajillionth", "bazillionth"
+    "trillionth", "quadrillionth", "quintillionth", "sextillionth", "septillionth",
+    "octillionth", "nonillionth", "decillionth", "gajillionth", "bazillionth"
 ]
 # fmt: on
 

spacy/lang/fo/__init__.py

@@ -0,0 +1,18 @@
+from ...language import BaseDefaults, Language
+from ..punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
+from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
+
+
+class FaroeseDefaults(BaseDefaults):
+    tokenizer_exceptions = TOKENIZER_EXCEPTIONS
+    infixes = TOKENIZER_INFIXES
+    suffixes = TOKENIZER_SUFFIXES
+    prefixes = TOKENIZER_PREFIXES
+
+
+class Faroese(Language):
+    lang = "fo"
+    Defaults = FaroeseDefaults
+
+
+__all__ = ["Faroese"]

spacy/lang/fo/tokenizer_exceptions.py

@@ -0,0 +1,90 @@
+from ...symbols import ORTH
+from ...util import update_exc
+from ..tokenizer_exceptions import BASE_EXCEPTIONS
+
+_exc = {}
+
+for orth in [
+    "apr.",
+    "aug.",
+    "avgr.",
+    "árg.",
+    "ávís.",
+    "beinl.",
+    "blkv.",
+    "blaðkv.",
+    "blm.",
+    "blaðm.",
+    "bls.",
+    "blstj.",
+    "blaðstj.",
+    "des.",
+    "eint.",
+    "febr.",
+    "fyrrv.",
+    "góðk.",
+    "h.m.",
+    "innt.",
+    "jan.",
+    "kl.",
+    "m.a.",
+    "mðr.",
+    "mió.",
+    "nr.",
+    "nto.",
+    "nov.",
+    "nút.",
+    "o.a.",
+    "o.a.m.",
+    "o.a.tíl.",
+    "o.fl.",
+    "ff.",
+    "o.m.a.",
+    "o.o.",
+    "o.s.fr.",
+    "o.tíl.",
+    "o.ø.",
+    "okt.",
+    "omf.",
+    "pst.",
+    "ritstj.",
+    "sbr.",
+    "sms.",
+    "smst.",
+    "smb.",
+    "sb.",
+    "sbrt.",
+    "sp.",
+    "sept.",
+    "spf.",
+    "spsk.",
+    "t.e.",
+    "t.s.",
+    "t.s.s.",
+    "tlf.",
+    "tel.",
+    "tsk.",
+    "t.o.v.",
+    "t.d.",
+    "uml.",
+    "ums.",
+    "uppl.",
+    "upprfr.",
+    "uppr.",
+    "útg.",
+    "útl.",
+    "útr.",
+    "vanl.",
+    "v.",
+    "v.h.",
+    "v.ø.o.",
+    "viðm.",
+    "viðv.",
+    "vm.",
+    "v.m.",
+]:
+    _exc[orth] = [{ORTH: orth}]
+    capitalized = orth.capitalize()
+    _exc[capitalized] = [{ORTH: capitalized}]
+
+TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)

spacy/lang/nn/__init__.py

@@ -0,0 +1,20 @@
+from ...language import BaseDefaults, Language
+from ..nb import SYNTAX_ITERATORS
+from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
+from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
+
+
+class NorwegianNynorskDefaults(BaseDefaults):
+    tokenizer_exceptions = TOKENIZER_EXCEPTIONS
+    prefixes = TOKENIZER_PREFIXES
+    infixes = TOKENIZER_INFIXES
+    suffixes = TOKENIZER_SUFFIXES
+    syntax_iterators = SYNTAX_ITERATORS
+
+
+class NorwegianNynorsk(Language):
+    lang = "nn"
+    Defaults = NorwegianNynorskDefaults
+
+
+__all__ = ["NorwegianNynorsk"]

spacy/lang/nn/examples.py

@@ -0,0 +1,15 @@
+"""
+Example sentences to test spaCy and its language models.
+
+>>> from spacy.lang.nn.examples import sentences
+>>> docs = nlp.pipe(sentences)
+"""
+
+
+# sentences taken from Omsetjingsminne frå Nynorsk pressekontor 2022 (https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-80/)
+sentences = [
+    "Konseptet går ut på at alle tre omgangar tel, alle hopparar må stille i kvalifiseringa og poengsummen skal telje.",
+    "Det er ein meir enn i same periode i fjor.",
+    "Det har lava ned enorme snømengder i store delar av Europa den siste tida.",
+    "Akhtar Chaudhry er ikkje innstilt på Oslo-lista til SV, men utfordrar Heikki Holmås om førsteplassen.",
+]

spacy/lang/nn/punctuation.py

@@ -0,0 +1,74 @@
+from ..char_classes import (
+    ALPHA,
+    ALPHA_LOWER,
+    ALPHA_UPPER,
+    CONCAT_QUOTES,
+    CURRENCY,
+    LIST_CURRENCY,
+    LIST_ELLIPSES,
+    LIST_ICONS,
+    LIST_PUNCT,
+    LIST_QUOTES,
+    PUNCT,
+    UNITS,
+)
+from ..punctuation import TOKENIZER_SUFFIXES
+
+_quotes = CONCAT_QUOTES.replace("'", "")
+_list_punct = [x for x in LIST_PUNCT if x != "#"]
+_list_icons = [x for x in LIST_ICONS if x != "°"]
+_list_icons = [x.replace("\\u00B0", "") for x in _list_icons]
+_list_quotes = [x for x in LIST_QUOTES if x != "\\'"]
+
+
+_prefixes = (
+    ["§", "%", "=", "—", "–", r"\+(?![0-9])"]
+    + _list_punct
+    + LIST_ELLIPSES
+    + LIST_QUOTES
+    + LIST_CURRENCY
+    + LIST_ICONS
+)
+
+
+_infixes = (
+    LIST_ELLIPSES
+    + _list_icons
+    + [
+        r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
+        r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}])[:<>=/](?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}])([{q}\)\]\(\[])(?=[{a}])".format(a=ALPHA, q=_quotes),
+        r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
+    ]
+)
+
+_suffixes = (
+    LIST_PUNCT
+    + LIST_ELLIPSES
+    + _list_quotes
+    + _list_icons
+    + ["—", "–"]
+    + [
+        r"(?<=[0-9])\+",
+        r"(?<=°[FfCcKk])\.",
+        r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
+        r"(?<=[0-9])(?:{u})".format(u=UNITS),
+        r"(?<=[{al}{e}{p}(?:{q})])\.".format(
+            al=ALPHA_LOWER, e=r"%²\-\+", q=_quotes, p=PUNCT
+        ),
+        r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
+    ]
+    + [r"(?<=[^sSxXzZ])'"]
+)
+_suffixes += [
+    suffix
+    for suffix in TOKENIZER_SUFFIXES
+    if suffix not in ["'s", "'S", "’s", "’S", r"\'"]
+]
+
+
+TOKENIZER_PREFIXES = _prefixes
+TOKENIZER_INFIXES = _infixes
+TOKENIZER_SUFFIXES = _suffixes

spacy/lang/nn/tokenizer_exceptions.py

@@ -0,0 +1,228 @@
+from ...symbols import NORM, ORTH
+from ...util import update_exc
+from ..tokenizer_exceptions import BASE_EXCEPTIONS
+
+_exc = {}
+
+
+for exc_data in [
+    {ORTH: "jan.", NORM: "januar"},
+    {ORTH: "feb.", NORM: "februar"},
+    {ORTH: "mar.", NORM: "mars"},
+    {ORTH: "apr.", NORM: "april"},
+    {ORTH: "jun.", NORM: "juni"},
+    # note: "jul." is in the simple list below without a NORM exception
+    {ORTH: "aug.", NORM: "august"},
+    {ORTH: "sep.", NORM: "september"},
+    {ORTH: "okt.", NORM: "oktober"},
+    {ORTH: "nov.", NORM: "november"},
+    {ORTH: "des.", NORM: "desember"},
+]:
+    _exc[exc_data[ORTH]] = [exc_data]
+
+
+for orth in [
+    "Ap.",
+    "Aq.",
+    "Ca.",
+    "Chr.",
+    "Co.",
+    "Dr.",
+    "F.eks.",
+    "Fr.p.",
+    "Frp.",
+    "Grl.",
+    "Kr.",
+    "Kr.F.",
+    "Kr.F.s",
+    "Mr.",
+    "Mrs.",
+    "Pb.",
+    "Pr.",
+    "Sp.",
+    "St.",
+    "a.m.",
+    "ad.",
+    "adm.dir.",
+    "adr.",
+    "b.c.",
+    "bl.a.",
+    "bla.",
+    "bm.",
+    "bnr.",
+    "bto.",
+    "c.c.",
+    "ca.",
+    "cand.mag.",
+    "co.",
+    "d.d.",
+    "d.m.",
+    "d.y.",
+    "dept.",
+    "dr.",
+    "dr.med.",
+    "dr.philos.",
+    "dr.psychol.",
+    "dss.",
+    "dvs.",
+    "e.Kr.",
+    "e.l.",
+    "eg.",
+    "eig.",
+    "ekskl.",
+    "el.",
+    "et.",
+    "etc.",
+    "etg.",
+    "ev.",
+    "evt.",
+    "f.",
+    "f.Kr.",
+    "f.eks.",
+    "f.o.m.",
+    "fhv.",
+    "fk.",
+    "foreg.",
+    "fork.",
+    "fv.",
+    "fvt.",
+    "g.",
+    "gl.",
+    "gno.",
+    "gnr.",
+    "grl.",
+    "gt.",
+    "h.r.adv.",
+    "hhv.",
+    "hoh.",
+    "hr.",
+    "ifb.",
+    "ifm.",
+    "iht.",
+    "inkl.",
+    "istf.",
+    "jf.",
+    "jr.",
+    "jul.",
+    "juris.",
+    "kfr.",
+    "kgl.",
+    "kgl.res.",
+    "kl.",
+    "komm.",
+    "kr.",
+    "kst.",
+    "lat.",
+    "lø.",
+    "m.a.",
+    "m.a.o.",
+    "m.fl.",
+    "m.m.",
+    "m.v.",
+    "ma.",
+    "mag.art.",
+    "md.",
+    "mfl.",
+    "mht.",
+    "mill.",
+    "min.",
+    "mnd.",
+    "moh.",
+    "mrd.",
+    "muh.",
+    "mv.",
+    "mva.",
+    "n.å.",
+    "ndf.",
+    "nr.",
+    "nto.",
+    "nyno.",
+    "o.a.",
+    "o.l.",
+    "obl.",
+    "off.",
+    "ofl.",
+    "on.",
+    "op.",
+    "org.",
+    "osv.",
+    "ovf.",
+    "p.",
+    "p.a.",
+    "p.g.a.",
+    "p.m.",
+    "p.t.",
+    "pga.",
+    "ph.d.",
+    "pkt.",
+    "pr.",
+    "pst.",
+    "pt.",
+    "red.anm.",
+    "ref.",
+    "res.",
+    "res.kap.",
+    "resp.",
+    "rv.",
+    "s.",
+    "s.d.",
+    "s.k.",
+    "s.u.",
+    "s.å.",
+    "sen.",
+    "sep.",
+    "siviling.",
+    "sms.",
+    "snr.",
+    "spm.",
+    "sr.",
+    "sst.",
+    "st.",
+    "st.meld.",
+    "st.prp.",
+    "stip.",
+    "stk.",
+    "stud.",
+    "sv.",
+    "såk.",
+    "sø.",
+    "t.d.",
+    "t.h.",
+    "t.o.m.",
+    "t.v.",
+    "temp.",
+    "ti.",
+    "tils.",
+    "tilsv.",
+    "tl;dr",
+    "tlf.",
+    "to.",
+    "ult.",
+    "utg.",
+    "v.",
+    "vedk.",
+    "vedr.",
+    "vg.",
+    "vgs.",
+    "vha.",
+    "vit.ass.",
+    "vn.",
+    "vol.",
+    "vs.",
+    "vsa.",
+    "§§",
+    "©NTB",
+    "årg.",
+    "årh.",
+]:
+    _exc[orth] = [{ORTH: orth}]
+
+# Dates
+for h in range(1, 31 + 1):
+    for period in ["."]:
+        _exc[f"{h}{period}"] = [{ORTH: f"{h}."}]
+
+_custom_base_exc = {"i.": [{ORTH: "i", NORM: "i"}, {ORTH: "."}]}
+_exc.update(_custom_base_exc)
+
+TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)

spacy/language.py

@@ -1683,6 +1683,12 @@ class Language:
         for proc in procs:
             proc.start()
 
+        # Close writing-end of channels. This is needed to avoid that reading
+        # from the channel blocks indefinitely when the worker closes the
+        # channel.
+        for tx in bytedocs_send_ch:
+            tx.close()
+
         # Cycle channels not to break the order of docs.
         # The received object is a batch of byte-encoded docs, so flatten them with chain.from_iterable.
         byte_tuples = chain.from_iterable(
@@ -1705,8 +1711,23 @@ class Language:
                     # tell `sender` that one batch was consumed.
                     sender.step()
         finally:
+            # If we are stopping in an orderly fashion, the workers' queues
+            # are empty. Put the sentinel in their queues to signal that work
+            # is done, so that they can exit gracefully.
+            for q in texts_q:
+                q.put(_WORK_DONE_SENTINEL)
+
+            # Otherwise, we are stopping because the error handler raised an
+            # exception. The sentinel will be last to go out of the queue.
+            # To avoid doing unnecessary work or hanging on platforms that
+            # block on sending (Windows), we'll close our end of the channel.
+            # This signals to the worker that it can exit the next time it
+            # attempts to send data down the channel.
+            for r in bytedocs_recv_ch:
+                r.close()
+
             for proc in procs:
-                proc.terminate()
+                proc.join()
 
     def _link_components(self) -> None:
         """Register 'listeners' within pipeline components, to allow them to
@@ -2323,6 +2344,11 @@ def _apply_pipes(
     while True:
         try:
             texts_with_ctx = receiver.get()
+
+            # Stop working if we encounter the end-of-work sentinel.
+            if isinstance(texts_with_ctx, _WorkDoneSentinel):
+                return
+
             docs = (
                 ensure_doc(doc_like, context) for doc_like, context in texts_with_ctx
             )
@@ -2331,11 +2357,21 @@ def _apply_pipes(
             # Connection does not accept unpickable objects, so send list.
             byte_docs = [(doc.to_bytes(), doc._context, None) for doc in docs]
             padding = [(None, None, None)] * (len(texts_with_ctx) - len(byte_docs))
-            sender.send(byte_docs + padding)  # type: ignore[operator]
+            data: Sequence[Tuple[Optional[bytes], Optional[Any], Optional[bytes]]] = (
+                byte_docs + padding  # type: ignore[operator]
+            )
         except Exception:
             error_msg = [(None, None, srsly.msgpack_dumps(traceback.format_exc()))]
             padding = [(None, None, None)] * (len(texts_with_ctx) - 1)
-            sender.send(error_msg + padding)
+            data = error_msg + padding
+
+        try:
+            sender.send(data)
+        except BrokenPipeError:
+            # Parent has closed the pipe prematurely. This happens when a
+            # worker encounters an error and the error handler is set to
+            # stop processing.
+            return
 
 
 class _Sender:
@@ -2365,3 +2401,10 @@ class _Sender:
         if self.count >= self.chunk_size:
             self.count = 0
             self.send()
+
+
+class _WorkDoneSentinel:
+    pass
+
+
+_WORK_DONE_SENTINEL = _WorkDoneSentinel()

spacy/matcher/__init__.py

@@ -3,4 +3,4 @@ from .levenshtein import levenshtein
 from .matcher import Matcher
 from .phrasematcher import PhraseMatcher
 
-__all__ = ["Matcher", "PhraseMatcher", "DependencyMatcher", "levenshtein"]
+__all__ = ["DependencyMatcher", "Matcher", "PhraseMatcher", "levenshtein"]

spacy/ml/models/textcat.py

@@ -1,21 +1,27 @@
 from functools import partial
-from typing import List, Optional, cast
+from typing import List, Optional, Tuple, cast
 
 from thinc.api import (
     Dropout,
+    Gelu,
     LayerNorm,
     Linear,
     Logistic,
     Maxout,
     Model,
     ParametricAttention,
+    ParametricAttention_v2,
     Relu,
     Softmax,
     SparseLinear,
+    SparseLinear_v2,
     chain,
     clone,
     concatenate,
     list2ragged,
+    reduce_first,
+    reduce_last,
+    reduce_max,
     reduce_mean,
     reduce_sum,
     residual,
@@ -25,9 +31,10 @@ from thinc.api import (
 )
 from thinc.layers.chain import init as init_chain
 from thinc.layers.resizable import resize_linear_weighted, resize_model
-from thinc.types import Floats2d
+from thinc.types import ArrayXd, Floats2d
 
 from ...attrs import ORTH
+from ...errors import Errors
 from ...tokens import Doc
 from ...util import registry
 from ..extract_ngrams import extract_ngrams
@@ -47,39 +54,15 @@ def build_simple_cnn_text_classifier(
     outputs sum to 1. If exclusive_classes=False, a logistic non-linearity
     is applied instead, so that outputs are in the range [0, 1].
     """
-    fill_defaults = {"b": 0, "W": 0}
+    return build_reduce_text_classifier(
-    with Model.define_operators({">>": chain}):
+        tok2vec=tok2vec,
-        cnn = tok2vec >> list2ragged() >> reduce_mean()
+        exclusive_classes=exclusive_classes,
-        nI = tok2vec.maybe_get_dim("nO")
+        use_reduce_first=False,
-        if exclusive_classes:
+        use_reduce_last=False,
-            output_layer = Softmax(nO=nO, nI=nI)
+        use_reduce_max=False,
-            fill_defaults["b"] = NEG_VALUE
+        use_reduce_mean=True,
-            resizable_layer: Model = resizable(
+        nO=nO,
-                output_layer,
-                resize_layer=partial(
-                    resize_linear_weighted, fill_defaults=fill_defaults
-                ),
     )
-            model = cnn >> resizable_layer
-        else:
-            output_layer = Linear(nO=nO, nI=nI)
-            resizable_layer = resizable(
-                output_layer,
-                resize_layer=partial(
-                    resize_linear_weighted, fill_defaults=fill_defaults
-                ),
-            )
-            model = cnn >> resizable_layer >> Logistic()
-        model.set_ref("output_layer", output_layer)
-        model.attrs["resize_output"] = partial(
-            resize_and_set_ref,
-            resizable_layer=resizable_layer,
-        )
-    model.set_ref("tok2vec", tok2vec)
-    if nO is not None:
-        model.set_dim("nO", cast(int, nO))
-    model.attrs["multi_label"] = not exclusive_classes
-    return model
 
 
 def resize_and_set_ref(model, new_nO, resizable_layer):
@@ -95,10 +78,48 @@ def build_bow_text_classifier(
     ngram_size: int,
     no_output_layer: bool,
     nO: Optional[int] = None,
+) -> Model[List[Doc], Floats2d]:
+    return _build_bow_text_classifier(
+        exclusive_classes=exclusive_classes,
+        ngram_size=ngram_size,
+        no_output_layer=no_output_layer,
+        nO=nO,
+        sparse_linear=SparseLinear(nO=nO),
+    )
+
+
+@registry.architectures("spacy.TextCatBOW.v3")
+def build_bow_text_classifier_v3(
+    exclusive_classes: bool,
+    ngram_size: int,
+    no_output_layer: bool,
+    length: int = 262144,
+    nO: Optional[int] = None,
+) -> Model[List[Doc], Floats2d]:
+    if length < 1:
+        raise ValueError(Errors.E1056.format(length=length))
+
+    # Find k such that 2**(k-1) < length <= 2**k.
+    length = 2 ** (length - 1).bit_length()
+
+    return _build_bow_text_classifier(
+        exclusive_classes=exclusive_classes,
+        ngram_size=ngram_size,
+        no_output_layer=no_output_layer,
+        nO=nO,
+        sparse_linear=SparseLinear_v2(nO=nO, length=length),
+    )
+
+
+def _build_bow_text_classifier(
+    exclusive_classes: bool,
+    ngram_size: int,
+    no_output_layer: bool,
+    sparse_linear: Model[Tuple[ArrayXd, ArrayXd, ArrayXd], ArrayXd],
+    nO: Optional[int] = None,
 ) -> Model[List[Doc], Floats2d]:
     fill_defaults = {"b": 0, "W": 0}
     with Model.define_operators({">>": chain}):
-        sparse_linear = SparseLinear(nO=nO)
         output_layer = None
         if not no_output_layer:
             fill_defaults["b"] = NEG_VALUE
@@ -127,6 +148,9 @@ def build_text_classifier_v2(
     linear_model: Model[List[Doc], Floats2d],
     nO: Optional[int] = None,
 ) -> Model[List[Doc], Floats2d]:
+    # TODO: build the model with _build_parametric_attention_with_residual_nonlinear
+    # in spaCy v4. We don't do this in spaCy v3 to preserve model
+    # compatibility.
     exclusive_classes = not linear_model.attrs["multi_label"]
     with Model.define_operators({">>": chain, "|": concatenate}):
         width = tok2vec.maybe_get_dim("nO")
@@ -190,3 +214,145 @@ def build_text_classifier_lowdata(
             model = model >> Dropout(dropout)
         model = model >> Logistic()
     return model
+
+
+@registry.architectures("spacy.TextCatParametricAttention.v1")
+def build_textcat_parametric_attention_v1(
+    tok2vec: Model[List[Doc], List[Floats2d]],
+    exclusive_classes: bool,
+    nO: Optional[int] = None,
+) -> Model[List[Doc], Floats2d]:
+    width = tok2vec.maybe_get_dim("nO")
+    parametric_attention = _build_parametric_attention_with_residual_nonlinear(
+        tok2vec=tok2vec,
+        nonlinear_layer=Maxout(nI=width, nO=width),
+        key_transform=Gelu(nI=width, nO=width),
+    )
+    with Model.define_operators({">>": chain}):
+        if exclusive_classes:
+            output_layer = Softmax(nO=nO)
+        else:
+            output_layer = Linear(nO=nO) >> Logistic()
+        model = parametric_attention >> output_layer
+    if model.has_dim("nO") is not False and nO is not None:
+        model.set_dim("nO", cast(int, nO))
+    model.set_ref("output_layer", output_layer)
+    model.attrs["multi_label"] = not exclusive_classes
+
+    return model
+
+
+def _build_parametric_attention_with_residual_nonlinear(
+    *,
+    tok2vec: Model[List[Doc], List[Floats2d]],
+    nonlinear_layer: Model[Floats2d, Floats2d],
+    key_transform: Optional[Model[Floats2d, Floats2d]] = None,
+) -> Model[List[Doc], Floats2d]:
+    with Model.define_operators({">>": chain, "|": concatenate}):
+        width = tok2vec.maybe_get_dim("nO")
+        attention_layer = ParametricAttention_v2(nO=width, key_transform=key_transform)
+        norm_layer = LayerNorm(nI=width)
+        parametric_attention = (
+            tok2vec
+            >> list2ragged()
+            >> attention_layer
+            >> reduce_sum()
+            >> residual(nonlinear_layer >> norm_layer >> Dropout(0.0))
+        )
+
+        parametric_attention.init = _init_parametric_attention_with_residual_nonlinear
+
+        parametric_attention.set_ref("tok2vec", tok2vec)
+        parametric_attention.set_ref("attention_layer", attention_layer)
+        parametric_attention.set_ref("nonlinear_layer", nonlinear_layer)
+        parametric_attention.set_ref("norm_layer", norm_layer)
+
+        return parametric_attention
+
+
+def _init_parametric_attention_with_residual_nonlinear(model, X, Y) -> Model:
+    tok2vec_width = get_tok2vec_width(model)
+    model.get_ref("attention_layer").set_dim("nO", tok2vec_width)
+    model.get_ref("nonlinear_layer").set_dim("nO", tok2vec_width)
+    model.get_ref("nonlinear_layer").set_dim("nI", tok2vec_width)
+    model.get_ref("norm_layer").set_dim("nI", tok2vec_width)
+    model.get_ref("norm_layer").set_dim("nO", tok2vec_width)
+    init_chain(model, X, Y)
+    return model
+
+
+@registry.architectures("spacy.TextCatReduce.v1")
+def build_reduce_text_classifier(
+    tok2vec: Model,
+    exclusive_classes: bool,
+    use_reduce_first: bool,
+    use_reduce_last: bool,
+    use_reduce_max: bool,
+    use_reduce_mean: bool,
+    nO: Optional[int] = None,
+) -> Model[List[Doc], Floats2d]:
+    """Build a model that classifies pooled `Doc` representations.
+
+    Pooling is performed using reductions. Reductions are concatenated when
+    multiple reductions are used.
+
+    tok2vec (Model): the tok2vec layer to pool over.
+    exclusive_classes (bool): Whether or not classes are mutually exclusive.
+    use_reduce_first (bool): Pool by using the hidden representation of the
+        first token of a `Doc`.
+    use_reduce_last (bool): Pool by using the hidden representation of the
+        last token of a `Doc`.
+    use_reduce_max (bool): Pool by taking the maximum values of the hidden
+        representations of a `Doc`.
+    use_reduce_mean (bool): Pool by taking the mean of all hidden
+        representations of a `Doc`.
+    nO (Optional[int]): Number of classes.
+    """
+
+    fill_defaults = {"b": 0, "W": 0}
+    reductions = []
+    if use_reduce_first:
+        reductions.append(reduce_first())
+    if use_reduce_last:
+        reductions.append(reduce_last())
+    if use_reduce_max:
+        reductions.append(reduce_max())
+    if use_reduce_mean:
+        reductions.append(reduce_mean())
+
+    if not len(reductions):
+        raise ValueError(Errors.E1057)
+
+    with Model.define_operators({">>": chain}):
+        cnn = tok2vec >> list2ragged() >> concatenate(*reductions)
+        nO_tok2vec = tok2vec.maybe_get_dim("nO")
+        nI = nO_tok2vec * len(reductions) if nO_tok2vec is not None else None
+        if exclusive_classes:
+            output_layer = Softmax(nO=nO, nI=nI)
+            fill_defaults["b"] = NEG_VALUE
+            resizable_layer: Model = resizable(
+                output_layer,
+                resize_layer=partial(
+                    resize_linear_weighted, fill_defaults=fill_defaults
+                ),
+            )
+            model = cnn >> resizable_layer
+        else:
+            output_layer = Linear(nO=nO, nI=nI)
+            resizable_layer = resizable(
+                output_layer,
+                resize_layer=partial(
+                    resize_linear_weighted, fill_defaults=fill_defaults
+                ),
+            )
+            model = cnn >> resizable_layer >> Logistic()
+        model.set_ref("output_layer", output_layer)
+        model.attrs["resize_output"] = partial(
+            resize_and_set_ref,
+            resizable_layer=resizable_layer,
+        )
+    model.set_ref("tok2vec", tok2vec)
+    if nO is not None:
+        model.set_dim("nO", cast(int, nO))
+    model.attrs["multi_label"] = not exclusive_classes
+    return model

spacy/pipeline/__init__.py

@@ -22,6 +22,7 @@ from .trainable_pipe import TrainablePipe
 __all__ = [
     "AttributeRuler",
     "DependencyParser",
+    "EditTreeLemmatizer",
     "EntityLinker",
     "EntityRecognizer",
     "EntityRuler",

spacy/pipeline/_parser_internals/stateclass.pyx

@@ -29,7 +29,7 @@ cdef class StateClass:
         return [self.B(i) for i in range(self.c.buffer_length())]
 
     @property
-    def token_vector_lenth(self):
+    def token_vector_length(self):
         return self.doc.tensor.shape[1]
 
     @property

spacy/pipeline/textcat.py

@@ -36,8 +36,9 @@ maxout_pieces = 3
 depth = 2
 
 [model.linear_model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
+length = 262144
 ngram_size = 1
 no_output_layer = false
 """
@@ -45,16 +46,21 @@ DEFAULT_SINGLE_TEXTCAT_MODEL = Config().from_str(single_label_default_config)["m
 
 single_label_bow_config = """
 [model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
+length = 262144
 ngram_size = 1
 no_output_layer = false
 """
 
 single_label_cnn_config = """
 [model]
-@architectures = "spacy.TextCatCNN.v2"
+@architectures = "spacy.TextCatReduce.v1"
 exclusive_classes = true
+use_reduce_first = false
+use_reduce_last = false
+use_reduce_max = false
+use_reduce_mean = true
 
 [model.tok2vec]
 @architectures = "spacy.HashEmbedCNN.v2"

spacy/pipeline/textcat_multilabel.py

@@ -35,8 +35,9 @@ maxout_pieces = 3
 depth = 2
 
 [model.linear_model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = false
+length = 262144
 ngram_size = 1
 no_output_layer = false
 """
@@ -44,7 +45,7 @@ DEFAULT_MULTI_TEXTCAT_MODEL = Config().from_str(multi_label_default_config)["mod
 
 multi_label_bow_config = """
 [model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = false
 ngram_size = 1
 no_output_layer = false
@@ -52,8 +53,12 @@ no_output_layer = false
 
 multi_label_cnn_config = """
 [model]
-@architectures = "spacy.TextCatCNN.v2"
+@architectures = "spacy.TextCatReduce.v1"
 exclusive_classes = false
+use_reduce_first = false
+use_reduce_last = false
+use_reduce_max = false
+use_reduce_mean = true
 
 [model.tok2vec]
 @architectures = "spacy.HashEmbedCNN.v2"

spacy/scorer.py

@@ -802,6 +802,140 @@ def get_ner_prf(examples: Iterable[Example], **kwargs) -> Dict[str, Any]:
         }
 
 
+# The following implementation of trapezoid() is adapted from SciPy,
+# which is distributed under the New BSD License.
+# Copyright (c) 2001-2002 Enthought, Inc. 2003-2023, SciPy Developers.
+# See licenses/3rd_party_licenses.txt
+def trapezoid(y, x=None, dx=1.0, axis=-1):
+    r"""
+    Integrate along the given axis using the composite trapezoidal rule.
+
+    If `x` is provided, the integration happens in sequence along its
+    elements - they are not sorted.
+
+    Integrate `y` (`x`) along each 1d slice on the given axis, compute
+    :math:`\int y(x) dx`.
+    When `x` is specified, this integrates along the parametric curve,
+    computing :math:`\int_t y(t) dt =
+    \int_t y(t) \left.\frac{dx}{dt}\right|_{x=x(t)} dt`.
+
+    Parameters
+    ----------
+    y : array_like
+        Input array to integrate.
+    x : array_like, optional
+        The sample points corresponding to the `y` values. If `x` is None,
+        the sample points are assumed to be evenly spaced `dx` apart. The
+        default is None.
+    dx : scalar, optional
+        The spacing between sample points when `x` is None. The default is 1.
+    axis : int, optional
+        The axis along which to integrate.
+
+    Returns
+    -------
+    trapezoid : float or ndarray
+        Definite integral of `y` = n-dimensional array as approximated along
+        a single axis by the trapezoidal rule. If `y` is a 1-dimensional array,
+        then the result is a float. If `n` is greater than 1, then the result
+        is an `n`-1 dimensional array.
+
+    See Also
+    --------
+    cumulative_trapezoid, simpson, romb
+
+    Notes
+    -----
+    Image [2]_ illustrates trapezoidal rule -- y-axis locations of points
+    will be taken from `y` array, by default x-axis distances between
+    points will be 1.0, alternatively they can be provided with `x` array
+    or with `dx` scalar.  Return value will be equal to combined area under
+    the red lines.
+
+    References
+    ----------
+    .. [1] Wikipedia page: https://en.wikipedia.org/wiki/Trapezoidal_rule
+
+    .. [2] Illustration image:
+           https://en.wikipedia.org/wiki/File:Composite_trapezoidal_rule_illustration.png
+
+    Examples
+    --------
+    Use the trapezoidal rule on evenly spaced points:
+
+    >>> import numpy as np
+    >>> from scipy import integrate
+    >>> integrate.trapezoid([1, 2, 3])
+    4.0
+
+    The spacing between sample points can be selected by either the
+    ``x`` or ``dx`` arguments:
+
+    >>> integrate.trapezoid([1, 2, 3], x=[4, 6, 8])
+    8.0
+    >>> integrate.trapezoid([1, 2, 3], dx=2)
+    8.0
+
+    Using a decreasing ``x`` corresponds to integrating in reverse:
+
+    >>> integrate.trapezoid([1, 2, 3], x=[8, 6, 4])
+    -8.0
+
+    More generally ``x`` is used to integrate along a parametric curve. We can
+    estimate the integral :math:`\int_0^1 x^2 = 1/3` using:
+
+    >>> x = np.linspace(0, 1, num=50)
+    >>> y = x**2
+    >>> integrate.trapezoid(y, x)
+    0.33340274885464394
+
+    Or estimate the area of a circle, noting we repeat the sample which closes
+    the curve:
+
+    >>> theta = np.linspace(0, 2 * np.pi, num=1000, endpoint=True)
+    >>> integrate.trapezoid(np.cos(theta), x=np.sin(theta))
+    3.141571941375841
+
+    ``trapezoid`` can be applied along a specified axis to do multiple
+    computations in one call:
+
+    >>> a = np.arange(6).reshape(2, 3)
+    >>> a
+    array([[0, 1, 2],
+           [3, 4, 5]])
+    >>> integrate.trapezoid(a, axis=0)
+    array([1.5, 2.5, 3.5])
+    >>> integrate.trapezoid(a, axis=1)
+    array([2.,  8.])
+    """
+    y = np.asanyarray(y)
+    if x is None:
+        d = dx
+    else:
+        x = np.asanyarray(x)
+        if x.ndim == 1:
+            d = np.diff(x)
+            # reshape to correct shape
+            shape = [1] * y.ndim
+            shape[axis] = d.shape[0]
+            d = d.reshape(shape)
+        else:
+            d = np.diff(x, axis=axis)
+    nd = y.ndim
+    slice1 = [slice(None)] * nd
+    slice2 = [slice(None)] * nd
+    slice1[axis] = slice(1, None)
+    slice2[axis] = slice(None, -1)
+    try:
+        ret = (d * (y[tuple(slice1)] + y[tuple(slice2)]) / 2.0).sum(axis)
+    except ValueError:
+        # Operations didn't work, cast to ndarray
+        d = np.asarray(d)
+        y = np.asarray(y)
+        ret = np.add.reduce(d * (y[tuple(slice1)] + y[tuple(slice2)]) / 2.0, axis)
+    return ret
+
+
 # The following implementation of roc_auc_score() is adapted from
 # scikit-learn, which is distributed under the New BSD License.
 # Copyright (c) 2007–2019 The scikit-learn developers.
@@ -1024,9 +1158,9 @@ def _auc(x, y):
         else:
             raise ValueError(Errors.E164.format(x=x))
 
-    area = direction * np.trapz(y, x)
+    area = direction * trapezoid(y, x)
     if isinstance(area, np.memmap):
-        # Reductions such as .sum used internally in np.trapz do not return a
+        # Reductions such as .sum used internally in trapezoid do not return a
         # scalar by default for numpy.memmap instances contrary to
         # regular numpy.ndarray instances.
         area = area.dtype.type(area)

spacy/tests/conftest.py

@@ -162,6 +162,11 @@ def fi_tokenizer():
     return get_lang_class("fi")().tokenizer
 
 
+@pytest.fixture(scope="session")
+def fo_tokenizer():
+    return get_lang_class("fo")().tokenizer
+
+
 @pytest.fixture(scope="session")
 def fr_tokenizer():
     return get_lang_class("fr")().tokenizer
@@ -317,6 +322,11 @@ def nl_tokenizer():
     return get_lang_class("nl")().tokenizer
 
 
+@pytest.fixture(scope="session")
+def nn_tokenizer():
+    return get_lang_class("nn")().tokenizer
+
+
 @pytest.fixture(scope="session")
 def pl_tokenizer():
     return get_lang_class("pl")().tokenizer

spacy/tests/doc/test_span.py

@@ -731,3 +731,12 @@ def test_for_no_ent_sents():
     sents = list(doc.ents[0].sents)
     assert len(sents) == 1
     assert str(sents[0]) == str(doc.ents[0].sent) == "ENTITY"
+
+
+def test_span_api_richcmp_other(en_tokenizer):
+    doc1 = en_tokenizer("a b")
+    doc2 = en_tokenizer("b c")
+    assert not doc1[1:2] == doc1[1]
+    assert not doc1[1:2] == doc2[0]
+    assert not doc1[1:2] == doc2[0:1]
+    assert not doc1[0:1] == doc2

spacy/tests/doc/test_token_api.py

@@ -294,3 +294,12 @@ def test_missing_head_dep(en_vocab):
     assert aligned_heads[0] == ref_heads[0]
     assert aligned_deps[5] == ref_deps[5]
     assert aligned_heads[5] == ref_heads[5]
+
+
+def test_token_api_richcmp_other(en_tokenizer):
+    doc1 = en_tokenizer("a b")
+    doc2 = en_tokenizer("b c")
+    assert not doc1[1] == doc1[0:1]
+    assert not doc1[1] == doc2[1:2]
+    assert not doc1[1] == doc2[0]
+    assert not doc1[0] == doc2

spacy/tests/lang/fo/test_tokenizer.py

@@ -0,0 +1,26 @@
+import pytest
+
+# examples taken from Basic LAnguage Resource Kit 1.0 for Faroese (https://maltokni.fo/en/resources) licensed with CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
+# fmt: off
+FO_TOKEN_EXCEPTION_TESTS = [
+    (
+        "Eftir løgtingslóg um samsýning og eftirløn landsstýrismanna v.m., skulu løgmaður og landsstýrismenn vanliga siga frá sær størv í almennari tænastu ella privatum virkjum, samtøkum ella stovnum. ",
+        [
+            "Eftir", "løgtingslóg", "um", "samsýning", "og", "eftirløn", "landsstýrismanna", "v.m.", ",", "skulu", "løgmaður", "og", "landsstýrismenn", "vanliga", "siga", "frá", "sær", "størv", "í", "almennari", "tænastu", "ella", "privatum", "virkjum", ",", "samtøkum", "ella", "stovnum", ".",
+        ],
+    ),
+    (
+        "Sambandsflokkurin gongur aftur við 2,7 prosentum í mun til valið í 1994, tá flokkurin fekk undirtøku frá 23,4 prosent av veljarunum.",
+        [
+            "Sambandsflokkurin", "gongur", "aftur", "við", "2,7", "prosentum", "í", "mun", "til", "valið", "í", "1994", ",", "tá", "flokkurin", "fekk", "undirtøku", "frá", "23,4", "prosent", "av", "veljarunum", ".",
+        ],
+    ),
+]
+# fmt: on
+
+
+@pytest.mark.parametrize("text,expected_tokens", FO_TOKEN_EXCEPTION_TESTS)
+def test_fo_tokenizer_handles_exception_cases(fo_tokenizer, text, expected_tokens):
+    tokens = fo_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list

spacy/tests/lang/nn/test_tokenizer.py

@@ -0,0 +1,38 @@
+import pytest
+
+# examples taken from Omsetjingsminne frå Nynorsk pressekontor 2022 (https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-80/)
+# fmt: off
+NN_TOKEN_EXCEPTION_TESTS = [
+    (
+        "Målet til direktoratet er at alle skal bli tilbydd jobb i politiet så raskt som mogleg i 2014.",
+        [
+            "Målet", "til", "direktoratet", "er", "at", "alle", "skal", "bli", "tilbydd", "jobb", "i", "politiet", "så", "raskt", "som", "mogleg", "i", "2014", ".",
+        ],
+    ),
+    (
+        "Han ønskjer ikkje at staten skal vere med på å finansiere slik undervisning, men dette er rektor på skulen ueinig i.",
+        [
+            "Han", "ønskjer", "ikkje", "at", "staten", "skal", "vere", "med", "på", "å", "finansiere", "slik", "undervisning", ",", "men", "dette", "er", "rektor", "på", "skulen", "ueinig", "i", ".",
+        ],
+    ),
+    (
+        "Ifølgje China Daily vart det 8.848 meter høge fjellet flytta 3 centimeter sørvestover under jordskjelvet, som vart målt til 7,8.",
+        [
+            "Ifølgje", "China", "Daily", "vart", "det", "8.848", "meter", "høge", "fjellet", "flytta", "3", "centimeter", "sørvestover", "under", "jordskjelvet", ",", "som", "vart", "målt", "til", "7,8", ".",
+        ],
+    ),
+    (
+        "Brukssesongen er frå nov. til mai, med ein topp i mars.",
+        [
+            "Brukssesongen", "er", "frå", "nov.", "til", "mai", ",", "med", "ein", "topp", "i", "mars", ".",
+        ],
+    ),
+]
+# fmt: on
+
+
+@pytest.mark.parametrize("text,expected_tokens", NN_TOKEN_EXCEPTION_TESTS)
+def test_nn_tokenizer_handles_exception_cases(nn_tokenizer, text, expected_tokens):
+    tokens = nn_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list

spacy/tests/pipeline/test_pipe_factories.py

@@ -203,7 +203,7 @@ def test_pipe_class_component_model():
             "@architectures": "spacy.TextCatEnsemble.v2",
             "tok2vec": DEFAULT_TOK2VEC_MODEL,
             "linear_model": {
-                "@architectures": "spacy.TextCatBOW.v2",
+                "@architectures": "spacy.TextCatBOW.v3",
                 "exclusive_classes": False,
                 "ngram_size": 1,
                 "no_output_layer": False,

spacy/tests/pipeline/test_textcat.py

@@ -414,7 +414,7 @@ def test_implicit_label(name, get_examples):
 @pytest.mark.parametrize(
     "name,textcat_config",
     [
-        # BOW
+        # BOW V1
         ("textcat", {"@architectures": "spacy.TextCatBOW.v1", "exclusive_classes": True, "no_output_layer": False, "ngram_size": 3}),
         ("textcat", {"@architectures": "spacy.TextCatBOW.v1", "exclusive_classes": True, "no_output_layer": True, "ngram_size": 3}),
         ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v1", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}),
@@ -451,14 +451,14 @@ def test_no_resize(name, textcat_config):
 @pytest.mark.parametrize(
     "name,textcat_config",
     [
-        # BOW
+        # BOW V3
-        ("textcat", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "no_output_layer": False, "ngram_size": 3}),
+        ("textcat", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "no_output_layer": False, "ngram_size": 3}),
-        ("textcat", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "no_output_layer": True, "ngram_size": 3}),
+        ("textcat", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "no_output_layer": True, "ngram_size": 3}),
-        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}),
+        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}),
-        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "no_output_layer": True, "ngram_size": 3}),
+        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "no_output_layer": True, "ngram_size": 3}),
         # CNN
-        ("textcat", {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
+        ("textcat", {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
-        ("textcat_multilabel", {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
+        ("textcat_multilabel", {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
     ],
 )
 # fmt: on
@@ -480,14 +480,14 @@ def test_resize(name, textcat_config):
 @pytest.mark.parametrize(
     "name,textcat_config",
     [
-        # BOW
+        # BOW v3
-        ("textcat", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "no_output_layer": False, "ngram_size": 3}),
+        ("textcat", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "no_output_layer": False, "ngram_size": 3}),
-        ("textcat", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "no_output_layer": True, "ngram_size": 3}),
+        ("textcat", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "no_output_layer": True, "ngram_size": 3}),
-        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}),
+        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}),
-        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "no_output_layer": True, "ngram_size": 3}),
+        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "no_output_layer": True, "ngram_size": 3}),
-        # CNN
+        # REDUCE
-        ("textcat", {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
+        ("textcat", {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
-        ("textcat_multilabel", {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
+        ("textcat_multilabel", {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
     ],
 )
 # fmt: on
@@ -693,12 +693,23 @@ def test_overfitting_IO_multi():
         ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "ngram_size": 4, "no_output_layer": False}),
         ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "ngram_size": 3, "no_output_layer": True}),
         ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "ngram_size": 2, "no_output_layer": True}),
+        # BOW V3
+        ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "ngram_size": 1, "no_output_layer": False}),
+        ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "ngram_size": 4, "no_output_layer": False}),
+        ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "ngram_size": 3, "no_output_layer": True}),
+        ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "ngram_size": 2, "no_output_layer": True}),
         # ENSEMBLE V2
-        ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "ngram_size": 1, "no_output_layer": False}}),
+        ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "ngram_size": 1, "no_output_layer": False}}),
-        ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "ngram_size": 5, "no_output_layer": False}}),
+        ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "ngram_size": 5, "no_output_layer": False}}),
-        # CNN V2
+        # CNN V2 (legacy)
         ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
         ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
+        # PARAMETRIC ATTENTION V1
+        ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatParametricAttention.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
+        ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatParametricAttention.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
+        # REDUCE V1
+        ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
+        ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
     ],
 )
 # fmt: on

spacy/tests/serialize/test_serialize_extension_attrs.py

@@ -15,7 +15,12 @@ def doc_w_attrs(en_tokenizer):
     Token.set_extension("_test_token", default="t0")
     doc[1]._._test_token = "t1"
 
-    return doc
+    yield doc
+
+    Doc.remove_extension("_test_attr")
+    Doc.remove_extension("_test_prop")
+    Doc.remove_extension("_test_method")
+    Token.remove_extension("_test_token")
 
 
 def test_serialize_ext_attrs_from_bytes(doc_w_attrs):

spacy/tests/test_cli.py

@@ -1061,3 +1061,8 @@ def test_debug_data_trainable_lemmatizer_not_annotated():
 
     data = _compile_gold(train_examples, ["trainable_lemmatizer"], nlp, True)
     assert data["no_lemma_annotations"] == 2
+
+
+def test_project_api_imports():
+    from spacy.cli import project_run
+    from spacy.cli.project.run import project_run  # noqa: F401, F811

spacy/tests/test_cli_app.py

@@ -214,9 +214,6 @@ def test_project_clone(options):
         assert (out / "README.md").is_file()
 
 
-@pytest.mark.skipif(
-    sys.version_info >= (3, 12), reason="Python 3.12+ not supported for remotes"
-)
 def test_project_push_pull(project_dir):
     proj = dict(SAMPLE_PROJECT)
     remote = "xyz"
@@ -241,7 +238,7 @@ def test_project_push_pull(project_dir):
 
 def test_find_function_valid():
     # example of architecture in main code base
-    function = "spacy.TextCatBOW.v2"
+    function = "spacy.TextCatBOW.v3"
     result = CliRunner().invoke(app, ["find-function", function, "-r", "architectures"])
     assert f"Found registered function '{function}'" in result.stdout
     assert "textcat.py" in result.stdout
@@ -260,7 +257,7 @@ def test_find_function_valid():
 
 def test_find_function_invalid():
     # invalid registry
-    function = "spacy.TextCatBOW.v2"
+    function = "spacy.TextCatBOW.v3"
     registry = "foobar"
     result = CliRunner().invoke(
         app, ["find-function", function, "--registry", registry]

spacy/tests/test_displacy.py

@@ -2,7 +2,7 @@ import numpy
 import pytest
 
 from spacy import displacy
-from spacy.displacy.render import DependencyRenderer, EntityRenderer
+from spacy.displacy.render import DependencyRenderer, EntityRenderer, SpanRenderer
 from spacy.lang.en import English
 from spacy.lang.fa import Persian
 from spacy.tokens import Doc, Span
@@ -468,3 +468,23 @@ def test_issue12816(en_vocab) -> None:
     # Verify that the HTML tag is still escaped
     html = displacy.render(doc, style="span")
     assert "<TEST>" in html
+
+
+@pytest.mark.issue(13056)
+def test_displacy_span_stacking():
+    """Test whether span stacking works properly for multiple overlapping spans."""
+    spans = [
+        {"start_token": 2, "end_token": 5, "label": "SkillNC"},
+        {"start_token": 0, "end_token": 2, "label": "Skill"},
+        {"start_token": 1, "end_token": 3, "label": "Skill"},
+    ]
+    tokens = ["Welcome", "to", "the", "Bank", "of", "China", "."]
+    per_token_info = SpanRenderer._assemble_per_token_info(spans=spans, tokens=tokens)
+
+    assert len(per_token_info) == len(tokens)
+    assert all([len(per_token_info[i]["entities"]) == 1 for i in (0, 3, 4)])
+    assert all([len(per_token_info[i]["entities"]) == 2 for i in (1, 2)])
+    assert per_token_info[1]["entities"][0]["render_slot"] == 1
+    assert per_token_info[1]["entities"][1]["render_slot"] == 2
+    assert per_token_info[2]["entities"][0]["render_slot"] == 2
+    assert per_token_info[2]["entities"][1]["render_slot"] == 3

spacy/tests/test_misc.py

@@ -376,8 +376,9 @@ def test_util_dot_section():
     factory = "textcat"
 
     [components.textcat.model]
-    @architectures = "spacy.TextCatBOW.v2"
+    @architectures = "spacy.TextCatBOW.v3"
     exclusive_classes = true
+    length = 262144
     ngram_size = 1
     no_output_layer = false
     """
@@ -485,8 +486,8 @@ def test_to_ternary_int():
 
 def test_find_available_port():
     host = "0.0.0.0"
-    port = 5000
+    port = 5001
-    assert find_available_port(port, host) == port, "Port 5000 isn't free"
+    assert find_available_port(port, host) == port, "Port 5001 isn't free"
 
     from wsgiref.simple_server import demo_app, make_server
 

spacy/tests/test_models.py

@@ -26,6 +26,7 @@ from spacy.ml.models import (
     build_Tok2Vec_model,
 )
 from spacy.ml.staticvectors import StaticVectors
+from spacy.util import registry
 
 
 def get_textcat_bow_kwargs():
@@ -284,3 +285,17 @@ def test_spancat_model_forward_backward(nO=5):
     Y, backprop = model((docs, spans), is_train=True)
     assert Y.shape == (spans.dataXd.shape[0], nO)
     backprop(Y)
+
+
+def test_textcat_reduce_invalid_args():
+    textcat_reduce = registry.architectures.get("spacy.TextCatReduce.v1")
+    tok2vec = make_test_tok2vec()
+    with pytest.raises(ValueError, match=r"must be used with at least one reduction"):
+        textcat_reduce(
+            tok2vec=tok2vec,
+            exclusive_classes=False,
+            use_reduce_first=False,
+            use_reduce_last=False,
+            use_reduce_max=False,
+            use_reduce_mean=False,
+        )

spacy/tests/tokenizer/test_explain.py

@@ -85,6 +85,18 @@ def test_tokenizer_explain_special_matcher(en_vocab):
     assert tokens == explain_tokens
 
 
+def test_tokenizer_explain_special_matcher_whitespace(en_vocab):
+    rules = {":]": [{"ORTH": ":]"}]}
+    tokenizer = Tokenizer(
+        en_vocab,
+        rules=rules,
+    )
+    text = ": ]"
+    tokens = [t.text for t in tokenizer(text)]
+    explain_tokens = [t[1] for t in tokenizer.explain(text)]
+    assert tokens == explain_tokens
+
+
 @hypothesis.strategies.composite
 def sentence_strategy(draw: hypothesis.strategies.DrawFn, max_n_words: int = 4) -> str:
     """
@@ -123,6 +135,9 @@ def test_tokenizer_explain_fuzzy(lang: str, sentence: str) -> None:
     """
 
     tokenizer: Tokenizer = spacy.blank(lang).tokenizer
-    tokens = [t.text for t in tokenizer(sentence) if not t.is_space]
+    # Tokenizer.explain is not intended to handle whitespace or control
+    # characters in the same way as Tokenizer
+    sentence = re.sub(r"\s+", " ", sentence).strip()
+    tokens = [t.text for t in tokenizer(sentence)]
     debug_tokens = [t[1] for t in tokenizer.explain(sentence)]
     assert tokens == debug_tokens, f"{tokens}, {debug_tokens}, {sentence}"

spacy/tokenizer.pyx

@@ -730,6 +730,13 @@ cdef class Tokenizer:
             if i in spans_by_start:
                 span = spans_by_start[i]
                 exc = [d[ORTH] for d in special_cases[span.label_]]
+                # The phrase matcher can overmatch for tokens separated by
+                # spaces in the text but not in the underlying rule, so skip
+                # cases where the texts aren't identical
+                if span.text != "".join([self.vocab.strings[orth] for orth in exc]):
+                    final_tokens.append(tokens[i])
+                    i += 1
+                else:
                     for j, orth in enumerate(exc):
                         final_tokens.append((f"SPECIAL-{j + 1}", self.vocab.strings[orth]))
                     i += len(span)

spacy/tokens/__init__.py

@@ -5,4 +5,4 @@ from .span import Span
 from .span_group import SpanGroup
 from .token import Token
 
-__all__ = ["Doc", "Token", "Span", "SpanGroup", "DocBin", "MorphAnalysis"]
+__all__ = ["Doc", "DocBin", "MorphAnalysis", "Span", "SpanGroup", "Token"]

spacy/tokens/doc.pyi

@@ -42,7 +42,7 @@ class Doc:
     user_hooks: Dict[str, Callable[..., Any]]
     user_token_hooks: Dict[str, Callable[..., Any]]
     user_span_hooks: Dict[str, Callable[..., Any]]
-    tensor: np.ndarray[Any, np.dtype[np.float_]]
+    tensor: np.ndarray[Any, np.dtype[np.float64]]
     user_data: Dict[str, Any]
     has_unknown_spaces: bool
     _context: Any
@@ -125,7 +125,7 @@ class Doc:
         vector: Optional[Floats1d] = ...,
         alignment_mode: str = ...,
         span_id: Union[int, str] = ...,
-    ) -> Span: ...
+    ) -> Optional[Span]: ...
     def similarity(self, other: Union[Doc, Span, Token, Lexeme]) -> float: ...
     @property
     def has_vector(self) -> bool: ...
@@ -166,7 +166,7 @@ class Doc:
     ) -> Doc: ...
     def to_array(
         self, py_attr_ids: Union[int, str, List[Union[int, str]]]
-    ) -> np.ndarray[Any, np.dtype[np.float_]]: ...
+    ) -> np.ndarray[Any, np.dtype[np.float64]]: ...
     @staticmethod
     def from_docs(
         docs: List[Doc],
@@ -179,15 +179,13 @@ class Doc:
         self, path: Union[str, Path], *, exclude: Iterable[str] = ...
     ) -> None: ...
     def from_disk(
-        self, path: Union[str, Path], *, exclude: Union[List[str], Tuple[str]] = ...
+        self, path: Union[str, Path], *, exclude: Iterable[str] = ...
     ) -> Doc: ...
-    def to_bytes(self, *, exclude: Union[List[str], Tuple[str]] = ...) -> bytes: ...
+    def to_bytes(self, *, exclude: Iterable[str] = ...) -> bytes: ...
-    def from_bytes(
+    def from_bytes(self, bytes_data: bytes, *, exclude: Iterable[str] = ...) -> Doc: ...
-        self, bytes_data: bytes, *, exclude: Union[List[str], Tuple[str]] = ...
+    def to_dict(self, *, exclude: Iterable[str] = ...) -> Dict[str, Any]: ...
-    ) -> Doc: ...
-    def to_dict(self, *, exclude: Union[List[str], Tuple[str]] = ...) -> bytes: ...
     def from_dict(
-        self, msg: bytes, *, exclude: Union[List[str], Tuple[str]] = ...
+        self, msg: Dict[str, Any], *, exclude: Iterable[str] = ...
     ) -> Doc: ...
     def extend_tensor(self, tensor: Floats2d) -> None: ...
     def retokenize(self) -> Retokenizer: ...

spacy/tokens/doc.pyx

@@ -1326,7 +1326,7 @@ cdef class Doc:
 
         path (str / Path): A path to a directory. Paths may be either
             strings or `Path`-like objects.
-        exclude (list): String names of serialization fields to exclude.
+        exclude (Iterable[str]): String names of serialization fields to exclude.
         RETURNS (Doc): The modified `Doc` object.
 
         DOCS: https://spacy.io/api/doc#from_disk
@@ -1339,7 +1339,7 @@ cdef class Doc:
     def to_bytes(self, *, exclude=tuple()):
         """Serialize, i.e. export the document contents to a binary string.
 
-        exclude (list): String names of serialization fields to exclude.
+        exclude (Iterable[str]): String names of serialization fields to exclude.
         RETURNS (bytes): A losslessly serialized copy of the `Doc`, including
             all annotations.
 
@@ -1351,7 +1351,7 @@ cdef class Doc:
         """Deserialize, i.e. import the document contents from a binary string.
 
         data (bytes): The string to load from.
-        exclude (list): String names of serialization fields to exclude.
+        exclude (Iterable[str]): String names of serialization fields to exclude.
         RETURNS (Doc): Itself.
 
         DOCS: https://spacy.io/api/doc#from_bytes
@@ -1361,11 +1361,8 @@ cdef class Doc:
     def to_dict(self, *, exclude=tuple()):
         """Export the document contents to a dictionary for serialization.
 
-        exclude (list): String names of serialization fields to exclude.
+        exclude (Iterable[str]): String names of serialization fields to exclude.
-        RETURNS (bytes): A losslessly serialized copy of the `Doc`, including
+        RETURNS (Dict[str, Any]): A dictionary representation of the `Doc`
-            all annotations.
-
-        DOCS: https://spacy.io/api/doc#to_bytes
         """
         array_head = Doc._get_array_attrs()
         strings = set()
@@ -1411,13 +1408,11 @@ cdef class Doc:
         return util.to_dict(serializers, exclude)
 
     def from_dict(self, msg, *, exclude=tuple()):
-        """Deserialize, i.e. import the document contents from a binary string.
+        """Deserialize the document contents from a dictionary representation.
 
-        data (bytes): The string to load from.
+        msg (Dict[str, Any]): The dictionary to load from.
-        exclude (list): String names of serialization fields to exclude.
+        exclude (Iterable[str]): String names of serialization fields to exclude.
         RETURNS (Doc): Itself.
-
-        DOCS: https://spacy.io/api/doc#from_dict
         """
         if self.length != 0:
             raise ValueError(Errors.E033.format(length=self.length))

spacy/tokens/span.pyx

@@ -127,14 +127,17 @@ cdef class Span:
         self._vector = vector
         self._vector_norm = vector_norm
 
-    def __richcmp__(self, Span other, int op):
+    def __richcmp__(self, object other, int op):
         if other is None:
             if op == 0 or op == 1 or op == 2:
                 return False
             else:
                 return True
+        if not isinstance(other, Span):
+            return False
+        cdef Span other_span = other
         self_tuple = (self.c.start_char, self.c.end_char, self.c.label, self.c.kb_id, self.id, self.doc)
-        other_tuple = (other.c.start_char, other.c.end_char, other.c.label, other.c.kb_id, other.id, other.doc)
+        other_tuple = (other_span.c.start_char, other_span.c.end_char, other_span.c.label, other_span.c.kb_id, other_span.id, other_span.doc)
         # <
         if op == 0:
             return self_tuple < other_tuple

spacy/tokens/token.pyi

@@ -53,7 +53,12 @@ class Token:
     def __bytes__(self) -> bytes: ...
     def __str__(self) -> str: ...
     def __repr__(self) -> str: ...
-    def __richcmp__(self, other: Token, op: int) -> bool: ...
+    def __lt__(self, other: Any) -> bool: ...
+    def __le__(self, other: Any) -> bool: ...
+    def __eq__(self, other: Any) -> bool: ...
+    def __ne__(self, other: Any) -> bool: ...
+    def __gt__(self, other: Any) -> bool: ...
+    def __ge__(self, other: Any) -> bool: ...
     @property
     def _(self) -> Underscore: ...
     def nbor(self, i: int = ...) -> Token: ...

spacy/tokens/token.pyx

@@ -139,17 +139,20 @@ cdef class Token:
     def __repr__(self):
         return self.__str__()
 
-    def __richcmp__(self, Token other, int op):
+    def __richcmp__(self, object other, int op):
         # http://cython.readthedocs.io/en/latest/src/userguide/special_methods.html
         if other is None:
             if op in (0, 1, 2):
                 return False
             else:
                 return True
+        if not isinstance(other, Token):
+            return False
+        cdef Token other_token = other
         cdef Doc my_doc = self.doc
-        cdef Doc other_doc = other.doc
+        cdef Doc other_doc = other_token.doc
         my = self.idx
-        their = other.idx
+        their = other_token.idx
         if op == 0:
             return my < their
         elif op == 2:

spacy/training/__init__.py

@@ -16,3 +16,28 @@ from .iob_utils import (  # noqa: F401
     tags_to_entities,
 )
 from .loggers import console_logger  # noqa: F401
+
+__all__ = [
+    "Alignment",
+    "Corpus",
+    "Example",
+    "JsonlCorpus",
+    "PlainTextCorpus",
+    "biluo_tags_to_offsets",
+    "biluo_tags_to_spans",
+    "biluo_to_iob",
+    "create_copy_from_base_model",
+    "docs_to_json",
+    "dont_augment",
+    "iob_to_biluo",
+    "minibatch_by_padded_size",
+    "minibatch_by_words",
+    "offsets_to_biluo_tags",
+    "orth_variants_augmenter",
+    "read_json_file",
+    "remove_bilu_prefix",
+    "split_bilu_label",
+    "tags_to_entities",
+    "validate_get_examples",
+    "validate_examples",
+]

spacy/util.py

@@ -1077,20 +1077,38 @@ def make_tempdir() -> Generator[Path, None, None]:
 
 
 def is_in_jupyter() -> bool:
-    """Check if user is running spaCy from a Jupyter notebook by detecting the
+    """Check if user is running spaCy from a Jupyter or Colab notebook by
-    IPython kernel. Mainly used for the displaCy visualizer.
+    detecting the IPython kernel. Mainly used for the displaCy visualizer.
-    RETURNS (bool): True if in Jupyter, False if not.
+    RETURNS (bool): True if in Jupyter/Colab, False if not.
     """
     # https://stackoverflow.com/a/39662359/6400719
+    # https://stackoverflow.com/questions/15411967
     try:
-        shell = get_ipython().__class__.__name__  # type: ignore[name-defined]
+        if get_ipython().__class__.__name__ == "ZMQInteractiveShell":  # type: ignore[name-defined]
-        if shell == "ZMQInteractiveShell":
             return True  # Jupyter notebook or qtconsole
+        if get_ipython().__class__.__module__ == "google.colab._shell":  # type: ignore[name-defined]
+            return True  # Colab notebook
     except NameError:
-        return False  # Probably standard Python interpreter
+        pass  # Probably standard Python interpreter
+    # additional check for Colab
+    try:
+        import google.colab
+
+        return True  # Colab notebook
+    except ImportError:
+        pass
     return False
 
 
+def is_in_interactive() -> bool:
+    """Check if user is running spaCy from an interactive Python
+    shell. Will return True in Jupyter notebooks too.
+    RETURNS (bool): True if in interactive mode, False if not.
+    """
+    # https://stackoverflow.com/questions/2356399/tell-if-python-is-in-interactive-mode
+    return hasattr(sys, "ps1") or hasattr(sys, "ps2")
+
+
 def get_object_name(obj: Any) -> str:
     """Get a human-readable name of a Python object, e.g. a pipeline component.
 

website/docs/api/architectures.mdx

@@ -79,7 +79,7 @@ subword features, and a
 consisting of a CNN and a layer-normalized maxout activation function.
 
 | Name                 | Description                                                                                                                                                                                                                                                                 |
-| -------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| -------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `width`              | The width of the input and output. These are required to be the same, so that residual connections can be used. Recommended values are `96`, `128` or `300`. ~~int~~                                                                                                        |
 | `depth`              | The number of convolutional layers to use. Recommended values are between `2` and `8`. ~~int~~                                                                                                                                                                              |
 | `embed_size`         | The number of rows in the hash embedding tables. This can be surprisingly small, due to the use of the hash embeddings. Recommended values are between `2000` and `10000`. ~~int~~                                                                                          |
@@ -962,8 +962,9 @@ single-label use-cases where `exclusive_classes = true`, while the
 > nO = null
 >
 > [model.linear_model]
-> @architectures = "spacy.TextCatBOW.v2"
+> @architectures = "spacy.TextCatBOW.v3"
 > exclusive_classes = true
+> length = 262144
 > ngram_size = 1
 > no_output_layer = false
 >
@@ -1017,54 +1018,15 @@ but used an internal `tok2vec` instead of taking it as argument:
 
 </Accordion>
 
-### spacy.TextCatCNN.v2 {id="TextCatCNN"}
+### spacy.TextCatBOW.v3 {id="TextCatBOW"}
 
 > #### Example Config
 >
 > ```ini
 > [model]
-> @architectures = "spacy.TextCatCNN.v2"
+> @architectures = "spacy.TextCatBOW.v3"
-> exclusive_classes = false
-> nO = null
->
-> [model.tok2vec]
-> @architectures = "spacy.HashEmbedCNN.v2"
-> pretrained_vectors = null
-> width = 96
-> depth = 4
-> embed_size = 2000
-> window_size = 1
-> maxout_pieces = 3
-> subword_features = true
-> ```
-
-A neural network model where token vectors are calculated using a CNN. The
-vectors are mean pooled and used as features in a feed-forward network. This
-architecture is usually less accurate than the ensemble, but runs faster.
-
-| Name                | Description                                                                                                                                                                                    |
-| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~                                                                                                                                     |
-| `tok2vec`           | The [`tok2vec`](#tok2vec) layer of the model. ~~Model~~                                                                                                                                        |
-| `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]~~                                                                                                                               |
-
-<Accordion title="spacy.TextCatCNN.v1 definition" spaced>
-
-[TextCatCNN.v1](/api/legacy#TextCatCNN_v1) had the exact same signature, but was
-not yet resizable. Since v2, new labels can be added to this component, even
-after training.
-
-</Accordion>
-
-### spacy.TextCatBOW.v2 {id="TextCatBOW"}
-
-> #### Example Config
->
-> ```ini
-> [model]
-> @architectures = "spacy.TextCatBOW.v2"
 > exclusive_classes = false
+> length = 262144
 > ngram_size = 1
 > no_output_layer = false
 > nO = null
@@ -1078,17 +1040,108 @@ the others, but may not be as accurate, especially if texts are short.
 | `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~                                                                                                                                     |
 | `ngram_size`        | Determines the maximum length of the n-grams in the BOW model. For instance, `ngram_size=3` would give unigram, trigram and bigram features. ~~int~~                                           |
 | `no_output_layer`   | Whether or not to add an output layer to the model (`Softmax` activation if `exclusive_classes` is `True`, else `Logistic`). ~~bool~~                                                          |
+| `length`            | The size of the weights vector. The length will be rounded up to the next power of two if it is not a power of two. Defaults to `262144`. ~~int~~                                              |
 | `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]~~                                                                                                                               |
 
-<Accordion title="spacy.TextCatBOW.v1 definition" spaced>
+<Accordion title="Previous versions of spacy.TextCatBOW" spaced>
 
-[TextCatBOW.v1](/api/legacy#TextCatBOW_v1) had the exact same signature, but was
+- [TextCatBOW.v1](/api/legacy#TextCatBOW_v1) was not yet resizable. Since v2,
-not yet resizable. Since v2, new labels can be added to this component, even
+  new labels can be added to this component, even after training.
-after training.
+- [TextCatBOW.v1](/api/legacy#TextCatBOW_v1) and
+  [TextCatBOW.v2](/api/legacy#TextCatBOW_v2) used an erroneous sparse linear
+  layer that only used a small number of the allocated parameters.
+- [TextCatBOW.v1](/api/legacy#TextCatBOW_v1) and
+  [TextCatBOW.v2](/api/legacy#TextCatBOW_v2) did not have the `length` argument.
 
 </Accordion>
 
+### spacy.TextCatParametricAttention.v1 {id="TextCatParametricAttention"}
+
+> #### Example Config
+>
+> ```ini
+> [model]
+> @architectures = "spacy.TextCatParametricAttention.v1"
+> exclusive_classes = true
+> nO = null
+>
+> [model.tok2vec]
+> @architectures = "spacy.Tok2Vec.v2"
+>
+> [model.tok2vec.embed]
+> @architectures = "spacy.MultiHashEmbed.v2"
+> width = 64
+> rows = [2000, 2000, 1000, 1000, 1000, 1000]
+> attrs = ["ORTH", "LOWER", "PREFIX", "SUFFIX", "SHAPE", "ID"]
+> include_static_vectors = false
+>
+> [model.tok2vec.encode]
+> @architectures = "spacy.MaxoutWindowEncoder.v2"
+> width = ${model.tok2vec.embed.width}
+> window_size = 1
+> maxout_pieces = 3
+> depth = 2
+> ```
+
+A neural network model that is built upon Tok2Vec and uses parametric attention
+to attend to tokens that are relevant to text classification.
+
+| Name                | Description                                                                                                                                                                                    |
+| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `tok2vec`           | The `tok2vec` layer to build the neural network upon. ~~Model[List[Doc], List[Floats2d]]~~                                                                                                     |
+| `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~                                                                                                                                     |
+| `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.TextCatReduce.v1 {id="TextCatReduce"}
+
+> #### Example Config
+>
+> ```ini
+> [model]
+> @architectures = "spacy.TextCatReduce.v1"
+> exclusive_classes = false
+> use_reduce_first = false
+> use_reduce_last = false
+> use_reduce_max = false
+> use_reduce_mean = true
+> nO = null
+>
+> [model.tok2vec]
+> @architectures = "spacy.HashEmbedCNN.v2"
+> pretrained_vectors = null
+> width = 96
+> depth = 4
+> embed_size = 2000
+> window_size = 1
+> maxout_pieces = 3
+> subword_features = true
+> ```
+
+A classifier that pools token hidden representations of each `Doc` using first,
+max or mean reduction and then applies a classification layer. Reductions are
+concatenated when multiple reductions are used.
+
+<Infobox variant="warning" title="Relation to TextCatCNN" id="TextCatCNN">
+
+`TextCatReduce` is a generalization of the older
+[`TextCatCNN`](/api/legacy#TextCatCNN_v2) model. `TextCatCNN` always uses a mean
+reduction, whereas `TextCatReduce` also supports first/max reductions.
+
+</Infobox>
+
+| Name                | Description                                                                                                                                                                                    |
+| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~                                                                                                                                     |
+| `tok2vec`           | The [`tok2vec`](#tok2vec) layer of the model. ~~Model~~                                                                                                                                        |
+| `use_reduce_first`  | Pool by using the hidden representation of the first token of a `Doc`. ~~bool~~                                                                                                                |
+| `use_reduce_last`   | Pool by using the hidden representation of the last token of a `Doc`. ~~bool~~                                                                                                                 |
+| `use_reduce_max`    | Pool by taking the maximum values of the hidden representations of a `Doc`. ~~bool~~                                                                                                           |
+| `use_reduce_mean`   | Pool by taking the mean of all hidden representations of a `Doc`. ~~bool~~                                                                                                                     |
+| `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]~~                                                                                                                               |
+
 ## Span classification architectures {id="spancat",source="spacy/ml/models/spancat.py"}
 
 ### spacy.SpanCategorizer.v1 {id="SpanCategorizer"}

website/docs/api/cli.mdx

@@ -1268,13 +1268,14 @@ 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]
+$ python -m spacy benchmark speed [model] [data_path] [--code] [--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)~~                                                                             |
+| `--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)~~ |
 | `--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)~~                                                                                                                       |
@@ -1296,6 +1297,9 @@ input formats are:
 
 When a directory is provided it is traversed recursively to collect all files.
 
+When loading a .spacy file, any potential annotations stored on the `Doc` that are not overwritten by the pipeline will be preserved.
+If you want to evaluate the pipeline on raw text only, make sure that the .spacy file does not contain any annotations.
+
 ```bash
 $ python -m spacy apply [model] [data-path] [output-file] [--code] [--text-key] [--force-overwrite] [--gpu-id] [--batch-size] [--n-process]
 ```

website/docs/api/curatedtransformer.mdx

@@ -400,6 +400,14 @@ identifiers are grouped by token. Instances of this class are typically assigned
 to the [`Doc._.trf_data`](/api/curatedtransformer#assigned-attributes) extension
 attribute.
 
+> #### Example
+>
+> ```python
+> # Get the last hidden layer output for "is" (token index 1)
+> doc = nlp("This is a text.")
+> tensors = doc._.trf_data.last_hidden_layer_state[1]
+> ```
+
 | Name              | Description                                                                                                                                                                        |
 | ----------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `all_outputs`     | List of `Ragged` tensors that correspends to outputs of the different transformer layers. Each tensor element corresponds to a piece identifier's representation. ~~List[Ragged]~~ |

website/docs/api/large-language-models.mdx

@@ -20,10 +20,9 @@ An LLM component is implemented through the `LLMWrapper` class. It is accessible
 through a generic `llm`
 [component factory](https://spacy.io/usage/processing-pipelines#custom-components-factories)
 as well as through task-specific component factories: `llm_ner`, `llm_spancat`,
-`llm_rel`, `llm_textcat`, `llm_sentiment`, `llm_summarization` and
+`llm_rel`, `llm_textcat`, `llm_sentiment`, `llm_summarization`,
-`llm_entity_linker`.
+`llm_entity_linker`, `llm_raw` and `llm_translation`. For these factories, the
-
+GPT-3-5 model from OpenAI is used by default, but this can be customized.
-### LLMWrapper.\_\_init\_\_ {id="init",tag="method"}
 
 > #### Example
 >
@@ -33,13 +32,18 @@ as well as through task-specific component factories: `llm_ner`, `llm_spancat`,
 > llm = nlp.add_pipe("llm", config=config)
 >
 > # Construction via add_pipe with a task-specific factory and default GPT3.5 model
-> llm = nlp.add_pipe("llm-ner")
+> llm = nlp.add_pipe("llm_ner")
+>
+> # Construction via add_pipe with a task-specific factory and custom model
+> llm = nlp.add_pipe("llm_ner", config={"model": {"@llm_models": "spacy.Dolly.v1", "name": "dolly-v2-12b"}})
 >
 > # Construction from class
 > from spacy_llm.pipeline import LLMWrapper
 > llm = LLMWrapper(vocab=nlp.vocab, task=task, model=model, cache=cache, save_io=True)
 > ```
 
+### LLMWrapper.\_\_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
 [`nlp.add_pipe`](/api/language#add_pipe).
@@ -225,8 +229,8 @@ All tasks are registered in the `llm_tasks` registry.
 dataset across multiple storage units for easier processing and lookups. In
 `spacy-llm` we use this term (synonymously: "mapping") to describe the splitting
 up of prompts if they are too long for a model to handle, and "fusing"
-(synonymously: "reducing") to describe how the model responses for several shards
+(synonymously: "reducing") to describe how the model responses for several
-are merged back together into a single document.
+shards are merged back together into a single document.
 
 Prompts are broken up in a manner that _always_ keeps the prompt in the template
 intact, meaning that the instructions to the LLM will always stay complete. The
@@ -1133,6 +1137,25 @@ supports `.yml`, `.yaml`, `.json` and `.jsonl`.
 path = "textcat_examples.json"
 ```
 
+If you want to perform few-shot learning with a binary classifier (i. e. a text
+either should or should not be assigned to a given class), you can provide
+positive and negative examples with answers of "POS" or "NEG". "POS" means that
+this example should be assigned the class label defined in the configuration,
+"NEG" means it shouldn't. E. g. for spam classification:
+
+```json
+[
+  {
+    "text": "You won the lottery! Wire a fee of 200$ to be able to withdraw your winnings.",
+    "answer": "POS"
+  },
+  {
+    "text": "Your order #123456789 has arrived",
+    "answer": "NEG"
+  }
+]
+```
+
 ### REL {id="rel"}
 
 The REL task extracts relations between named entities.
@@ -1358,13 +1381,14 @@ contain provider-specific keys and values, as it will be passed onwards to the
 provider's API.
 
 | Argument           | Description                                                                                                                                                                    |
-| ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
 | `name`             | Model name, i. e. any supported variant for this particular model. Default depends on the specific model (cf. below) ~~str~~                                                   |
 | `config`           | Further configuration passed on to the model. Default depends on the specific model (cf. below). ~~Dict[Any, Any]~~                                                            |
 | `strict`           | If `True`, raises an error if the LLM API returns a malformed response. Otherwise, return the error responses as is. Defaults to `True`. ~~bool~~                              |
 | `max_tries`        | Max. number of tries for API request. Defaults to `5`. ~~int~~                                                                                                                 |
 | `max_request_time` | Max. time (in seconds) to wait for request to terminate before raising an exception. Defaults to `30.0`. ~~float~~                                                             |
 | `interval`         | Time interval (in seconds) for API retries in seconds. Defaults to `1.0`. ~~float~~                                                                                            |
+| `endpoint`         | Endpoint URL. Defaults to the provider's standard URL, if available (which is not the case for providers with exclusively custom deployments, such as Azure) ~~Optional[str]~~ |
 
 > #### Example config:
 >
@@ -1483,7 +1507,7 @@ These models all take the same parameters:
 > ```ini
 > [components.llm.model]
 > @llm_models = "spacy.Llama2.v1"
-> name = "llama2-7b-hf"
+> name = "Llama-2-7b-hf"
 > ```
 
 Currently, these models are provided as part of the core library:

website/docs/api/legacy.mdx

@@ -162,7 +162,10 @@ network has an internal CNN Tok2Vec layer and uses attention.
 
 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
-yet support that.
+yet support that. `TextCatCNN` has been replaced by the more general
+[`TextCatReduce`](/api/architectures#TextCatReduce) layer. `TextCatCNN` is
+identical to `TextCatReduce` with `use_reduce_mean=true`,
+`use_reduce_first=false`, `reduce_last=false` and `use_reduce_max=false`.
 
 > #### Example Config
 >
@@ -194,11 +197,58 @@ 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.TextCatCNN.v2 {id="TextCatCNN_v2"}
+
+> #### Example Config
+>
+> ```ini
+> [model]
+> @architectures = "spacy.TextCatCNN.v2"
+> exclusive_classes = false
+> nO = null
+>
+> [model.tok2vec]
+> @architectures = "spacy.HashEmbedCNN.v2"
+> pretrained_vectors = null
+> width = 96
+> depth = 4
+> embed_size = 2000
+> window_size = 1
+> maxout_pieces = 3
+> subword_features = true
+> ```
+
+A neural network model where token vectors are calculated using a CNN. The
+vectors are mean pooled and used as features in a feed-forward network. This
+architecture is usually less accurate than the ensemble, but runs faster.
+
+`TextCatCNN` has been replaced by the more general
+[`TextCatReduce`](/api/architectures#TextCatReduce) layer. `TextCatCNN` is
+identical to `TextCatReduce` with `use_reduce_mean=true`,
+`use_reduce_first=false`, `reduce_last=false` and `use_reduce_max=false`.
+
+| Name                | Description                                                                                                                                                                                    |
+| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~                                                                                                                                     |
+| `tok2vec`           | The [`tok2vec`](#tok2vec) layer of the model. ~~Model~~                                                                                                                                        |
+| `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]~~                                                                                                                               |
+
+<Accordion title="spacy.TextCatCNN.v1 definition" spaced>
+
+[TextCatCNN.v1](/api/legacy#TextCatCNN_v1) had the exact same signature, but was
+not yet resizable. Since v2, new labels can be added to this component, even
+after training.
+
+</Accordion>
+
 ### 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
-yet support that.
+yet support that. Versions of this model before `spacy.TextCatBOW.v3` used an
+erroneous sparse linear layer that only used a small number of the allocated
+parameters.
 
 > #### Example Config
 >
@@ -222,6 +272,33 @@ 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.TextCatBOW.v2 {id="TextCatBOW"}
+
+Versions of this model before `spacy.TextCatBOW.v3` used an erroneous sparse
+linear layer that only used a small number of the allocated parameters.
+
+> #### Example Config
+>
+> ```ini
+> [model]
+> @architectures = "spacy.TextCatBOW.v2"
+> exclusive_classes = false
+> ngram_size = 1
+> no_output_layer = false
+> nO = null
+> ```
+
+An n-gram "bag-of-words" model. This architecture should run much faster than
+the others, but may not be as accurate, especially if texts are short.
+
+| Name                | Description                                                                                                                                                                                    |
+| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~                                                                                                                                     |
+| `ngram_size`        | Determines the maximum length of the n-grams in the BOW model. For instance, `ngram_size=3` would give unigram, trigram and bigram features. ~~int~~                                           |
+| `no_output_layer`   | Whether or not to add an output layer to the model (`Softmax` activation if `exclusive_classes` is `True`, else `Logistic`). ~~bool~~                                                          |
+| `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 {id="TransitionBasedParser_v1"}
 
 Identical to

website/docs/api/spancategorizer.mdx

@@ -89,6 +89,21 @@ architectures and their arguments and hyperparameters.
 | `negative_weight` <Tag variant="new">3.5.1</Tag>    | Multiplier for the loss terms. It can be used to downweight the negative samples if there are too many. It is only used when `add_negative_label` is `True`. Defaults to `1.0`. ~~float~~                                                                                                               |
 | `allow_overlap` <Tag variant="new">3.5.1</Tag>      | If `True`, the data is assumed to contain overlapping spans. It is only available when `max_positive` is exactly 1. Defaults to `True`. ~~bool~~                                                                                                                                                        |
 
+<Infobox variant="warning">
+
+If you set a non-default value for `spans_key`, you'll have to update
+`[training.score_weights]` as well so that weights are computed properly. E. g.
+for `spans_key == "myspankey"`, include this in your config:
+
+```ini
+[training.score_weights]
+spans_myspankey_f = 1.0
+spans_myspankey_p = 0.0
+spans_myspankey_r = 0.0
+```
+
+</Infobox>
+
 ```python
 %%GITHUB_SPACY/spacy/pipeline/spancat.py
 ```

website/docs/api/transformer.mdx

@@ -397,6 +397,17 @@ are wrapped into the
 by this class. Instances of this class are typically assigned to the
 [`Doc._.trf_data`](/api/transformer#assigned-attributes) extension attribute.
 
+> #### Example
+>
+> ```python
+> # Get the last hidden layer output for "is" (token index 1)
+> doc = nlp("This is a text.")
+> indices = doc._.trf_data.align[1].data.flatten()
+> last_hidden_state = doc._.trf_data.model_output.last_hidden_state
+> dim = last_hidden_state.shape[-1]
+> tensors = last_hidden_state.reshape(-1, dim)[indices]
+> ```
+
 | Name           | Description                                                                                                                                                                                                                                                                                                                          |
 | -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
 | `tokens`       | A slice of the tokens data produced by the tokenizer. This may have several fields, including the token IDs, the texts and the attention mask. See the [`transformers.BatchEncoding`](https://huggingface.co/transformers/main_classes/tokenizer.html#transformers.BatchEncoding) object for details. ~~dict~~                       |

website/docs/api/vocab.mdx

@@ -13,7 +13,7 @@ between `Doc` objects.
 <Infobox variant ="warning">
 
 Note that a `Vocab` instance is not static. It increases in size as texts with
-new tokens are processed.
+new tokens are processed. Some models may have an empty vocab at initialization.
 
 </Infobox>
 
@@ -93,6 +93,7 @@ given string, you need to look it up in
 > #### Example
 >
 > ```python
+> nlp("I'm eating an apple")
 > apple = nlp.vocab.strings["apple"]
 > oov = nlp.vocab.strings["dskfodkfos"]
 > assert apple in nlp.vocab

website/docs/models/index.mdx

@@ -108,12 +108,12 @@ In the `sm`/`md`/`lg` models:
 
 #### CNN/CPU pipelines with floret vectors
 
-The Finnish, Korean and Swedish `md` and `lg` pipelines use
+The Croatian, Finnish, Korean, Slovenian, Swedish and Ukrainian `md` and `lg`
-[floret vectors](/usage/v3-2#vectors) instead of default vectors. If you're
+pipelines use [floret vectors](/usage/v3-2#vectors) instead of default vectors.
-running a trained pipeline on texts and working with [`Doc`](/api/doc) objects,
+If you're running a trained pipeline on texts and working with [`Doc`](/api/doc)
-you shouldn't notice any difference with floret vectors. With floret vectors no
+objects, you shouldn't notice any difference with floret vectors. With floret
-tokens are out-of-vocabulary, so [`Token.is_oov`](/api/token#attributes) will
+vectors no tokens are out-of-vocabulary, so
-return `False` for all tokens.
+[`Token.is_oov`](/api/token#attributes) will return `False` for all tokens.
 
 If you access vectors directly for similarity comparisons, there are a few
 differences because floret vectors don't include a fixed word list like the
@@ -132,10 +132,20 @@ vector keys for default vectors.
 
 ### Transformer pipeline design {id="design-trf"}
 
-In the transformer (`trf`) models, the `tagger`, `parser` and `ner` (if present)
+In the transformer (`trf`) pipelines, the `tagger`, `parser` and `ner` (if
-all listen to the `transformer` component. The `attribute_ruler` and
+present) all listen to the `transformer` component. The `attribute_ruler` and
 `lemmatizer` have the same configuration as in the CNN models.
 
+For spaCy v3.0-v3.6, `trf` pipelines use
+[`spacy-transformers`](https://github.com/explosion/spacy-transformers) and the
+transformer output in `doc._.trf_data` is a
+[`TransformerData`](/api/transformer#transformerdata) object.
+
+For spaCy v3.7+, `trf` pipelines use
+[`spacy-curated-transformers`](https://github.com/explosion/spacy-curated-transformers)
+and `doc._.trf_data` is a
+[`DocTransformerOutput`](/api/curatedtransformer#doctransformeroutput) object.
+
 ### Modifying the default pipeline {id="design-modify"}
 
 For faster processing, you may only want to run a subset of the components in a

website/docs/usage/101/_named-entities.mdx

@@ -31,8 +31,6 @@ for ent in doc.ents:
 Using spaCy's built-in [displaCy visualizer](/usage/visualizers), here's what
 our example sentence and its named entities look like:
 
-<Iframe
+<Standalone height={120}>
-  title="displaCy visualization of entities"
+<div style={{lineHeight: 2.5, fontFamily: "-apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol'", fontSize: 18}}><mark style={{ background: '#7aecec', padding: '0.45em 0.6em', margin: '0 0.25em', lineHeight: 1, borderRadius: '0.35em'}}>Apple <span style={{ fontSize: '0.8em', fontWeight: 'bold', lineHeight: 1, borderRadius: '0.35em', marginLeft: '0.5rem'}}>ORG</span></mark> is looking at buying <mark style={{ background: '#feca74', padding: '0.45em 0.6em', margin: '0 0.25em', lineHeight: 1, borderRadius: '0.35em'}}>U.K. <span style={{ fontSize: '0.8em', fontWeight: 'bold', lineHeight: 1, borderRadius: '0.35em', marginLeft: '0.5rem'}}>GPE</span></mark> startup for <mark style={{ background: '#e4e7d2', padding: '0.45em 0.6em', margin: '0 0.25em', lineHeight: 1, borderRadius: '0.35em'}}>$1 billion <span style={{ fontSize: '0.8em', fontWeight: 'bold', lineHeight: 1, borderRadius: '0.35em', marginLeft: '0.5rem'}}>MONEY</span></mark></div>
-  src="/images/displacy-ent1.html"
+</Standalone>
-  height={100}
-/>

website/docs/usage/101/_pos-deps.mdx

@@ -56,8 +56,7 @@ for token in doc:
 Using spaCy's built-in [displaCy visualizer](/usage/visualizers), here's what
 our example sentence and its dependencies look like:
 
-<Iframe
+<ImageScrollable
-  title="displaCy visualization of dependencies and entities"
+  src="/images/displacy-long.svg"
-  src="/images/displacy-long.html"
+  width={1975}
-  height={450}
 />

website/docs/usage/layers-architectures.mdx

@@ -153,8 +153,9 @@ maxout_pieces = 3
 depth = 2
 
 [components.textcat.model.linear_model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
+length = 262144
 ngram_size = 1
 no_output_layer = false
 ```
@@ -170,8 +171,9 @@ factory = "textcat"
 labels = []
 
 [components.textcat.model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
+length = 262144
 ngram_size = 1
 no_output_layer = false
 nO = null

website/docs/usage/linguistic-features.mdx

@@ -290,11 +290,7 @@ for token in doc:
 | toward        | `prep`     | shift     | `NOUN`   | manufacturers           |
 | manufacturers | `pobj`     | toward    | `ADP`    |                         |
 
-<Iframe
+<ImageScrollable src="/images/displacy-long2.svg" width={1275} />
-  title="displaCy visualization of dependencies and entities 2"
-  src="/images/displacy-long2.html"
-  height={450}
-/>
 
 Because the syntactic relations form a tree, every word has **exactly one
 head**. You can therefore iterate over the arcs in the tree by iterating over
@@ -709,11 +705,9 @@ doc = nlp(text)
 displacy.serve(doc, style="ent")
 ```
 
-<Iframe
+<Standalone height={180}>
-  title="displaCy visualizer for entities"
+<div style={{lineHeight: 2.5, fontFamily: "-apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol'", fontSize: 18}}>When <mark style={{ background: '#aa9cfc', padding: '0.45em 0.6em', margin: '0 0.25em', lineHeight: 1, borderRadius: '0.35em'}}>Sebastian Thrun <span style={{ fontSize: '0.8em', fontWeight: 'bold', lineHeight: 1, borderRadius: '0.35em', marginLeft: '0.5rem'}}>PERSON</span></mark> started working on self-driving cars at <mark style={{ background: '#7aecec', padding: '0.45em 0.6em', margin: '0 0.25em', lineHeight: 1, borderRadius: '0.35em'}}>Google <span style={{ fontSize: '0.8em', fontWeight: 'bold', lineHeight: 1, borderRadius: '0.35em', marginLeft: '0.5rem'}}>ORG</span></mark> in <mark style={{ background: '#bfe1d9', padding: '0.45em 0.6em', margin: '0 0.25em', lineHeight: 1, borderRadius: '0.35em'}}>2007 <span style={{ fontSize: '0.8em', fontWeight: 'bold', lineHeight: 1, borderRadius: '0.35em', marginLeft: '0.5rem'}}>DATE</span></mark>, few people outside of the company took him seriously.</div>
-  src="/images/displacy-ent2.html"
+</Standalone>
-  height={180}
-/>
 
 ## Entity Linking {id="entity-linking"}
 
@@ -723,6 +717,10 @@ identifier from a knowledge base (KB). You can create your own
 [`KnowledgeBase`](/api/kb) and [train](/usage/training) a new
 [`EntityLinker`](/api/entitylinker) using that custom knowledge base.
 
+As an example on how to define a KnowledgeBase and train an entity linker model,
+see [`this tutorial`](https://github.com/explosion/projects/blob/v3/tutorials/nel_emerson)
+using [spaCy projects](/usage/projects).
+
 ### Accessing entity identifiers {id="entity-linking-accessing",model="entity linking"}
 
 The annotated KB identifier is accessible as either a hash value or as a string,
@@ -733,6 +731,7 @@ object, or the `ent_kb_id` and `ent_kb_id_` attributes of a
 ```python
 import spacy
 
+# "my_custom_el_pipeline" is assumed to be a custom NLP pipeline that was trained and serialized to disk
 nlp = spacy.load("my_custom_el_pipeline")
 doc = nlp("Ada Lovelace was born in London")
 

website/docs/usage/processing-pipelines.mdx

@@ -1328,8 +1328,9 @@ labels = []
 # This function is created and then passed to the "textcat" component as
 # the argument "model"
 [components.textcat.model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
+length = 262144
 ngram_size = 1
 no_output_layer = false
 

website/docs/usage/rule-based-matching.mdx

@@ -1144,10 +1144,9 @@ relations and tokens we want to match:
 > displacy.serve(doc)
 > ```
 
-<Iframe
+<ImageScrollable
-  title="displaCy visualization of dependencies"
+  src="/images/displacy-dep-founded.svg"
-  src="/images/displacy-dep-founded.html"
+  width={925}
-  height={450}
 />
 
 The relations we're interested in are:

website/docs/usage/saving-loading.mdx

@@ -405,7 +405,7 @@ available to spaCy, all you need to do is install the package in your
 environment:
 
 ```bash
-$ python setup.py develop
+$ python -m pip install .
 ```
 
 spaCy is now able to create the pipeline component `"snek"` – even though you
@@ -586,11 +586,9 @@ After installing the package, the custom colors will be used when visualizing
 text with `displacy`. Whenever the label `SNEK` is assigned, it will be
 displayed in `#3dff74`.
 
-<Iframe
+<Standalone height={100}>
-  title="displaCy visualization of entities"
+<div style={{lineHeight: 2.5, fontFamily: "-apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol'", fontSize: 18}}>🌱🌿 <mark style={{ background: '#3dff74', padding: '0.45em 0.6em', margin: '0 0.25em', lineHeight: 1, borderRadius: '0.35em'}}>🐍 <span style={{ fontSize: '0.8em', fontWeight: 'bold', lineHeight: 1, borderRadius: '0.35em', marginLeft: '0.5rem'}}>SNEK</span></mark> ____ 🌳🌲 ____ <mark style={{ background: '#cfc5ff', padding: '0.45em 0.6em', margin: '0 0.25em', lineHeight: 1, borderRadius: '0.35em'}}>👨‍🌾 <span style={{ fontSize: '0.8em', fontWeight: 'bold', lineHeight: 1, borderRadius: '0.35em', marginLeft: '0.5rem'}}>HUMAN</span></mark> 🏘️</div>
-  src="/images/displacy-ent-snek.html"
+</Standalone>
-  height={100}
-/>
 
 ## Saving, loading and distributing trained pipelines {id="models"}
 
@@ -675,7 +673,7 @@ $ python -m spacy package ./en_example_pipeline ./packages
 ```
 
 This command will create a pipeline package directory and will run
-`python setup.py sdist` in that directory to create a binary `.whl` file or
+`python -m build` in that directory to create a binary `.whl` file or
 `.tar.gz` archive of your package that can be installed using `pip install`.
 Installing the binary wheel is usually more efficient.
 

website/docs/usage/v3-3.mdx

@@ -77,11 +77,9 @@ doc.spans["custom"] = [Span(doc, 3, 6, "ORG"), Span(doc, 5, 6, "GPE")]
 displacy.serve(doc, style="span", options={"spans_key": "custom"})
 ```
 
-<Iframe
+<Standalone height={100}>
-  title="displaCy visualizer for overlapping spans"
+<div style={{ lineHeight: 2.5, direction: 'ltr', fontFamily: "-apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol'", fontSize: 18 }}>Welcome to the <span style={{ fontWeight: 'bold', display: 'inline-block', position: 'relative'}}>Bank<span style={{ background: '#7aecec', top: 40, height: 4, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}></span><span style={{ background: '#7aecec', top: 40, height: 4, borderTopLeftRadius: 3, borderBottomLeftRadius: 3, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}><span style={{ background: '#7aecec', color: '#000', top: '-0.5em', padding: '2px 3px', position: 'absolute', fontSize: '0.6em', fontWeight: 'bold', lineHeight: 1, borderRadius: 3 }}>ORG</span></span></span> <span style={{ fontWeight: 'bold', display: 'inline-block', position: 'relative'}}>of <span style={{ background: '#7aecec', top: 40, height: 4, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}></span></span> <span style={{ fontWeight: 'bold', display: 'inline-block', position: 'relative'}}>China<span style={{ background: '#7aecec', top: 40, height: 4, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}></span><span style={{ background: '#feca74', top: 57, height: 4, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}></span><span style={{ background: '#feca74', top: 57, height: 4, borderTopLeftRadius: 3, borderBottomLeftRadius: 3, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}><span style={{ background: '#feca74', color: '#000', top: '-0.5em', padding: '2px 3px', position: 'absolute', fontSize: '0.6em', fontWeight: 'bold', lineHeight: 1, borderRadius: 3 }}>GPE</span></span></span>.</div>
-  src="/images/displacy-span.html"
+</Standalone>
-  height={180}
-/>
 
 ## Additional features and improvements
 

website/docs/usage/visualizers.mdx

@@ -119,11 +119,9 @@ doc = nlp(text)
 displacy.serve(doc, style="ent")
 ```
 
-<Iframe
+<Standalone height={180}>
-  title="displaCy visualizer for entities"
+<div style={{lineHeight: 2.5, fontFamily: "-apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol'", fontSize: 18}}>When <mark style={{ background: '#aa9cfc', padding: '0.45em 0.6em', margin: '0 0.25em', lineHeight: 1, borderRadius: '0.35em'}}>Sebastian Thrun <span style={{ fontSize: '0.8em', fontWeight: 'bold', lineHeight: 1, borderRadius: '0.35em', marginLeft: '0.5rem'}}>PERSON</span></mark> started working on self-driving cars at <mark style={{ background: '#7aecec', padding: '0.45em 0.6em', margin: '0 0.25em', lineHeight: 1, borderRadius: '0.35em'}}>Google <span style={{ fontSize: '0.8em', fontWeight: 'bold', lineHeight: 1, borderRadius: '0.35em', marginLeft: '0.5rem'}}>ORG</span></mark> in <mark style={{ background: '#bfe1d9', padding: '0.45em 0.6em', margin: '0 0.25em', lineHeight: 1, borderRadius: '0.35em'}}>2007 <span style={{ fontSize: '0.8em', fontWeight: 'bold', lineHeight: 1, borderRadius: '0.35em', marginLeft: '0.5rem'}}>DATE</span></mark>, few people outside of the company took him seriously.</div>
-  src="/images/displacy-ent2.html"
+</Standalone>
-  height={180}
-/>
 
 The entity visualizer lets you customize the following `options`:
 
@@ -148,11 +146,9 @@ use the `colors` setting to add your own colors for them.
 > displacy.serve(doc, style="ent", options=options)
 > ```
 
-<Iframe
+<Standalone height={225}>
-  title="displaCy visualizer for entities (custom styling)"
+<div style={{lineHeight: 2.5, fontFamily: "-apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol'", fontSize: 18}}>But <mark style={{ background: 'linear-gradient(90deg, #aa9cfc, #fc9ce7)', padding: '0.45em 0.6em', margin: '0 0.25em', lineHeight: 1, borderRadius: '0.35em'}}>Google <span style={{ fontSize: '0.8em', fontWeight: 'bold', lineHeight: 1, borderRadius: '0.35em', marginLeft: '0.5rem'}}>ORG</span></mark> is starting from behind. The company made a late push into hardware, and <mark style={{ background: 'linear-gradient(90deg, #aa9cfc, #fc9ce7)', padding: '0.45em 0.6em', margin: '0 0.25em', lineHeight: 1, borderRadius: '0.35em'}}>Apple <span style={{ fontSize: '0.8em', fontWeight: 'bold', lineHeight: 1, borderRadius: '0.35em', marginLeft: '0.5rem'}}>ORG</span></mark>’s Siri, available on iPhones, and <mark style={{ background: 'linear-gradient(90deg, #aa9cfc, #fc9ce7)', padding: '0.45em 0.6em', margin: '0 0.25em', lineHeight: 1, borderRadius: '0.35em'}}>Amazon <span style={{ fontSize: '0.8em', fontWeight: 'bold', lineHeight: 1, borderRadius: '0.35em', marginLeft: '0.5rem'}}>ORG</span></mark>’s Alexa software, which runs on its Echo and Dot devices, have clear leads in consumer adoption.</div>
-  src="/images/displacy-ent-custom.html"
+</Standalone>
-  height={225}
-/>
 
 The above example uses a little trick: Since the background color values are
 added as the `background` style attribute, you can use any
@@ -197,11 +193,9 @@ doc.spans["sc"] = [
 displacy.serve(doc, style="span")
 ```
 
-<Iframe
+<Standalone height={100}>
-  title="displaCy visualizer for overlapping spans"
+<div style={{ lineHeight: 2.5, direction: 'ltr', fontFamily: "-apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol'", fontSize: 18 }}>Welcome to the <span style={{ fontWeight: 'bold', display: 'inline-block', position: 'relative'}}>Bank<span style={{ background: '#7aecec', top: 40, height: 4, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}></span><span style={{ background: '#7aecec', top: 40, height: 4, borderTopLeftRadius: 3, borderBottomLeftRadius: 3, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}><span style={{ background: '#7aecec', color: '#000', top: '-0.5em', padding: '2px 3px', position: 'absolute', fontSize: '0.6em', fontWeight: 'bold', lineHeight: 1, borderRadius: 3 }}>ORG</span></span></span> <span style={{ fontWeight: 'bold', display: 'inline-block', position: 'relative'}}>of <span style={{ background: '#7aecec', top: 40, height: 4, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}></span></span> <span style={{ fontWeight: 'bold', display: 'inline-block', position: 'relative'}}>China<span style={{ background: '#7aecec', top: 40, height: 4, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}></span><span style={{ background: '#feca74', top: 57, height: 4, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}></span><span style={{ background: '#feca74', top: 57, height: 4, borderTopLeftRadius: 3, borderBottomLeftRadius: 3, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}><span style={{ background: '#feca74', color: '#000', top: '-0.5em', padding: '2px 3px', position: 'absolute', fontSize: '0.6em', fontWeight: 'bold', lineHeight: 1, borderRadius: 3 }}>GPE</span></span></span>.</div>
-  src="/images/displacy-span.html"
+</Standalone>
-  height={180}
-/>
 
 The span visualizer lets you customize the following `options`:
 
@@ -223,11 +217,9 @@ specify which one displaCy should use with `spans_key` (`sc` is the default).
 > displacy.serve(doc, style="span", options=options)
 > ```
 
-<Iframe
+<Standalone height={100}>
-  title="displaCy visualizer for spans (custom spans_key)"
+<div style={{ lineHeight: 2.5, direction: 'ltr', fontFamily: "-apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol'", fontSize: 18 }}>Welcome to the <span style={{ fontWeight: 'bold', display: 'inline-block', position: 'relative'}}>Bank<span style={{ background: '#ddd', top: 40, height: 4, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}></span><span style={{ background: '#ddd', top: 40, height: 4, borderTopLeftRadius: 3, borderBottomLeftRadius: 3, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}><span style={{ background: '#ddd', color: '#000', top: '-0.5em', padding: '2px 3px', position: 'absolute', fontSize: '0.6em', fontWeight: 'bold', lineHeight: 1, borderRadius: 3 }}>BANK</span></span></span> <span style={{ fontWeight: 'bold', display: 'inline-block', position: 'relative'}}>of <span style={{ background: '#ddd', top: 40, height: 4, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}></span></span> <span style={{ fontWeight: 'bold', display: 'inline-block', position: 'relative'}}>China<span style={{ background: '#ddd', top: 40, height: 4, left: -1, width: 'calc(100% + 2px)', position: 'absolute' }}></span></span>.</div>
-  src="/images/displacy-span-custom.html"
+</Standalone>
-  height={225}
-/>
 
 ## Using displaCy in Jupyter notebooks {id="jupyter"}
 

website/meta/languages.json

@@ -103,6 +103,10 @@
             "has_examples": true,
             "models": ["fi_core_news_sm", "fi_core_news_md", "fi_core_news_lg"]
         },
+        {
+            "code": "fo",
+            "name": "Faroese"
+        },
         {
             "code": "fr",
             "name": "French",
@@ -290,6 +294,12 @@
             "example": "Dit is een zin.",
             "has_examples": true
         },
+        {
+            "code": "nn",
+            "name": "Norwegian Nynorsk",
+            "example": "Det er ein meir enn i same periode i fjor.",
+            "has_examples": true
+        },
         {
             "code": "pl",
             "name": "Polish",

website/meta/sidebars.json

@@ -9,14 +9,9 @@
                     { "text": "Models & Languages", "url": "/usage/models" },
                     { "text": "Facts & Figures", "url": "/usage/facts-figures" },
                     { "text": "spaCy 101", "url": "/usage/spacy-101" },
-                    { "text": "New in v3.0", "url": "/usage/v3" },
+                    { "text": "New in v3.7", "url": "/usage/v3-7" },
-                    { "text": "New in v3.1", "url": "/usage/v3-1" },
-                    { "text": "New in v3.2", "url": "/usage/v3-2" },
-                    { "text": "New in v3.3", "url": "/usage/v3-3" },
-                    { "text": "New in v3.4", "url": "/usage/v3-4" },
-                    { "text": "New in v3.5", "url": "/usage/v3-5" },
                     { "text": "New in v3.6", "url": "/usage/v3-6" },
-                    { "text": "New in v3.7", "url": "/usage/v3-7" }
+                    { "text": "New in v3.5", "url": "/usage/v3-5" }
                 ]
             },
             {

website/meta/site.json

@@ -66,6 +66,10 @@
                 {
                     "text": "Stack Overflow",
                     "url": "http://stackoverflow.com/questions/tagged/spacy"
+                },
+                {
+                    "text": "Merchandise",
+                    "url": "https://explosion.ai/merch"
                 }
             ]
         },

website/meta/universe.json

@@ -4500,6 +4500,23 @@
                 "website": "https://nlp.unibuc.ro/people/snisioi.html"
             },
             "category": ["pipeline", "training", "models"]
+        },
+        {
+            "id": "redfield-spacy-nodes",
+            "title": "Redfield NLP Nodes for KNIME",
+            "slogan": "Makes the functionality of the spaCy library available in KNIME Analytics Platform.",
+            "description": "This extension provides nodes that make the functionality of the spaCy library available in the [KNIME Analytics Platform](https://www.knime.com/).",
+            "github": "Redfield-AB/Spacy-Nodes",
+            "url": "https://redfield.ai/spacy-redfield/",
+            "thumb": "https://raw.githubusercontent.com/Redfield-AB/Spacy-Nodes/master/resource/redfield_logo_100x100.png",
+            "image": "https://raw.githubusercontent.com/Redfield-AB/Spacy-Nodes/master/resource/screen1.png",
+            "author": "Redfield AB",
+            "author_links": {
+                "twitter": "Redfield_AB",
+                "github": "Redfield-AB",
+                "website": "https://redfield.ai"
+            },
+            "category": ["standalone"]
         }
     ],
 

website/public/images/displacy-ent-custom.html

@@ -1,80 +0,0 @@
-<div
-    class="entities"
-    style="
-        line-height: 2.5;
-        font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif,
-            'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol';
-        font-size: 18px;
-    "
-    >But
-    <mark
-        class="entity"
-        style="
-            background: linear-gradient(90deg, #aa9cfc, #fc9ce7);
-            padding: 0.45em 0.6em;
-            margin: 0 0.25em;
-            line-height: 1;
-            border-radius: 0.35em;
-        "
-        >Google
-        <span
-            style="
-                font-size: 0.8em;
-                font-weight: bold;
-                line-height: 1;
-                border-radius: 0.35em;
-                text-transform: uppercase;
-                vertical-align: middle;
-                margin-left: 0.5rem;
-            "
-            >ORG</span
-        ></mark
-    >is starting from behind. The company made a late push into hardware, and
-    <mark
-        class="entity"
-        style="
-            background: linear-gradient(90deg, #aa9cfc, #fc9ce7);
-            padding: 0.45em 0.6em;
-            margin: 0 0.25em;
-            line-height: 1;
-            border-radius: 0.35em;
-        "
-        >Apple
-        <span
-            style="
-                font-size: 0.8em;
-                font-weight: bold;
-                line-height: 1;
-                border-radius: 0.35em;
-                text-transform: uppercase;
-                vertical-align: middle;
-                margin-left: 0.5rem;
-            "
-            >ORG</span
-        ></mark
-    >’s Siri, available on iPhones, and
-    <mark
-        class="entity"
-        style="
-            background: linear-gradient(90deg, #aa9cfc, #fc9ce7);
-            padding: 0.45em 0.6em;
-            margin: 0 0.25em;
-            line-height: 1;
-            border-radius: 0.35em;
-        "
-        >Amazon
-        <span
-            style="
-                font-size: 0.8em;
-                font-weight: bold;
-                line-height: 1;
-                border-radius: 0.35em;
-                text-transform: uppercase;
-                vertical-align: middle;
-                margin-left: 0.5rem;
-            "
-            >ORG</span
-        ></mark
-    >’s Alexa software, which runs on its Echo and Dot devices, have clear leads in consumer
-    adoption.</div
->

website/public/images/displacy-ent-snek.html

@@ -1,59 +0,0 @@
-<div
-    class="entities"
-    style="
-        line-height: 2.5;
-        font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif,
-            'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol';
-        font-size: 16px;
-    "
->
-    🌱🌿
-    <mark
-        class="entity"
-        style="
-            background: #3dff74;
-            padding: 0.45em 0.6em;
-            margin: 0 0.25em;
-            line-height: 1;
-            border-radius: 0.35em;
-        "
-        >🐍
-        <span
-            style="
-                font-size: 0.8em;
-                font-weight: bold;
-                line-height: 1;
-                border-radius: 0.35em;
-                text-transform: uppercase;
-                vertical-align: middle;
-                margin-left: 0.5rem;
-            "
-            >SNEK</span
-        ></mark
-    >
-    ____ 🌳🌲 ____
-    <mark
-        class="entity"
-        style="
-            background: #cfc5ff;
-            padding: 0.45em 0.6em;
-            margin: 0 0.25em;
-            line-height: 1;
-            border-radius: 0.35em;
-        "
-        >👨‍🌾
-        <span
-            style="
-                font-size: 0.8em;
-                font-weight: bold;
-                line-height: 1;
-                border-radius: 0.35em;
-                text-transform: uppercase;
-                vertical-align: middle;
-                margin-left: 0.5rem;
-            "
-            >HUMAN</span
-        ></mark
-    >
-    🏘️
-</div>

website/public/images/displacy-ent1.html

@@ -1,84 +0,0 @@
-<div
-    class="entities"
-    style="
-        line-height: 2.5;
-        font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif,
-            'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol';
-        font-size: 16px;
-    "
->
-    <mark
-        class="entity"
-        style="
-            background: #7aecec;
-            padding: 0.45em 0.6em;
-            margin: 0 0.25em;
-            line-height: 1;
-            border-radius: 0.35em;
-        "
-    >
-        Apple
-        <span
-            style="
-                font-size: 0.8em;
-                font-weight: bold;
-                line-height: 1;
-                border-radius: 0.35em;
-                text-transform: uppercase;
-                vertical-align: middle;
-                margin-left: 0.5rem;
-            "
-            >ORG</span
-        >
-    </mark>
-    is looking at buying
-    <mark
-        class="entity"
-        style="
-            background: #feca74;
-            padding: 0.45em 0.6em;
-            margin: 0 0.25em;
-            line-height: 1;
-            border-radius: 0.35em;
-        "
-    >
-        U.K.
-        <span
-            style="
-                font-size: 0.8em;
-                font-weight: bold;
-                line-height: 1;
-                border-radius: 0.35em;
-                text-transform: uppercase;
-                vertical-align: middle;
-                margin-left: 0.5rem;
-            "
-            >GPE</span
-        >
-    </mark>
-    startup for
-    <mark
-        class="entity"
-        style="
-            background: #e4e7d2;
-            padding: 0.45em 0.6em;
-            margin: 0 0.25em;
-            line-height: 1;
-            border-radius: 0.35em;
-        "
-    >
-        $1 billion
-        <span
-            style="
-                font-size: 0.8em;
-                font-weight: bold;
-                line-height: 1;
-                border-radius: 0.35em;
-                text-transform: uppercase;
-                vertical-align: middle;
-                margin-left: 0.5rem;
-            "
-            >MONEY</span
-        >
-    </mark>
-</div>

website/public/images/displacy-ent2.html

@@ -1,86 +0,0 @@
-<div
-    class="entities"
-    style="
-        line-height: 2.5;
-        font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif,
-            'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol';
-        font-size: 18px;
-    "
->
-    When
-    <mark
-        class="entity"
-        style="
-            background: #aa9cfc;
-            padding: 0.45em 0.6em;
-            margin: 0 0.25em;
-            line-height: 1;
-            border-radius: 0.35em;
-        "
-    >
-        Sebastian Thrun
-        <span
-            style="
-                font-size: 0.8em;
-                font-weight: bold;
-                line-height: 1;
-                border-radius: 0.35em;
-                text-transform: uppercase;
-                vertical-align: middle;
-                margin-left: 0.5rem;
-            "
-            >PERSON</span
-        >
-    </mark>
-    started working on self-driving cars at
-    <mark
-        class="entity"
-        style="
-            background: #7aecec;
-            padding: 0.45em 0.6em;
-            margin: 0 0.25em;
-            line-height: 1;
-            border-radius: 0.35em;
-        "
-    >
-        Google
-        <span
-            style="
-                font-size: 0.8em;
-                font-weight: bold;
-                line-height: 1;
-                border-radius: 0.35em;
-                text-transform: uppercase;
-                vertical-align: middle;
-                margin-left: 0.5rem;
-            "
-            >ORG</span
-        >
-    </mark>
-    in
-    <mark
-        class="entity"
-        style="
-            background: #bfe1d9;
-            padding: 0.45em 0.6em;
-            margin: 0 0.25em;
-            line-height: 1;
-            border-radius: 0.35em;
-        "
-    >
-        2007
-        <span
-            style="
-                font-size: 0.8em;
-                font-weight: bold;
-                line-height: 1;
-                border-radius: 0.35em;
-                text-transform: uppercase;
-                vertical-align: middle;
-                margin-left: 0.5rem;
-            "
-            >DATE</span
-        >
-    </mark>
-    , few people outside of the company took him seriously.
-</div>

website/public/images/displacy-long2.svg

@@ -0,0 +1,212 @@
+<svg
+    xmlns="http://www.w3.org/2000/svg"
+    xmlns:xlink="http://www.w3.org/1999/xlink"
+    id="0"
+    class="displacy"
+    width="1275"
+    height="399.5"
+    style="
+        max-width: none;
+        height: 399.5px;
+        color: #000000;
+        background: #ffffff;
+        font-family: Arial;
+    "
+>
+    <text class="displacy-token" fill="currentColor" text-anchor="middle" y="309.5">
+        <tspan class="displacy-word" fill="currentColor" x="50">Autonomous</tspan>
+        <tspan class="displacy-tag" dy="2em" fill="currentColor" x="50">ADJ</tspan>
+    </text>
+
+    <text class="displacy-token" fill="currentColor" text-anchor="middle" y="309.5">
+        <tspan class="displacy-word" fill="currentColor" x="225">cars</tspan>
+        <tspan class="displacy-tag" dy="2em" fill="currentColor" x="225">NOUN</tspan>
+    </text>
+
+    <text class="displacy-token" fill="currentColor" text-anchor="middle" y="309.5">
+        <tspan class="displacy-word" fill="currentColor" x="400">shift</tspan>
+        <tspan class="displacy-tag" dy="2em" fill="currentColor" x="400">VERB</tspan>
+    </text>
+
+    <text class="displacy-token" fill="currentColor" text-anchor="middle" y="309.5">
+        <tspan class="displacy-word" fill="currentColor" x="575">insurance</tspan>
+        <tspan class="displacy-tag" dy="2em" fill="currentColor" x="575">NOUN</tspan>
+    </text>
+
+    <text class="displacy-token" fill="currentColor" text-anchor="middle" y="309.5">
+        <tspan class="displacy-word" fill="currentColor" x="750">liability</tspan>
+        <tspan class="displacy-tag" dy="2em" fill="currentColor" x="750">NOUN</tspan>
+    </text>
+
+    <text class="displacy-token" fill="currentColor" text-anchor="middle" y="309.5">
+        <tspan class="displacy-word" fill="currentColor" x="925">toward</tspan>
+        <tspan class="displacy-tag" dy="2em" fill="currentColor" x="925">ADP</tspan>
+    </text>
+
+    <text class="displacy-token" fill="currentColor" text-anchor="middle" y="309.5">
+        <tspan class="displacy-word" fill="currentColor" x="1100">manufacturers</tspan>
+        <tspan class="displacy-tag" dy="2em" fill="currentColor" x="1100">NOUN</tspan>
+    </text>
+
+    <g class="displacy-arrow">
+        <path
+            class="displacy-arc"
+            id="arrow-0-0"
+            stroke-width="2px"
+            d="M70,264.5 C70,177.0 215.0,177.0 215.0,264.5"
+            fill="none"
+            stroke="currentColor"
+        ></path>
+        <text dy="1.25em" style="font-size: 0.8em; letter-spacing: 1px">
+            <textpath
+                xlink:href="#arrow-0-0"
+                class="displacy-label"
+                startOffset="50%"
+                fill="currentColor"
+                text-anchor="middle"
+            >
+                amod
+            </textpath>
+        </text>
+        <path
+            class="displacy-arrowhead"
+            d="M70,266.5 L62,254.5 78,254.5"
+            fill="currentColor"
+        ></path>
+    </g>
+
+    <g class="displacy-arrow">
+        <path
+            class="displacy-arc"
+            id="arrow-0-1"
+            stroke-width="2px"
+            d="M245,264.5 C245,177.0 390.0,177.0 390.0,264.5"
+            fill="none"
+            stroke="currentColor"
+        ></path>
+        <text dy="1.25em" style="font-size: 0.8em; letter-spacing: 1px">
+            <textpath
+                xlink:href="#arrow-0-1"
+                class="displacy-label"
+                startOffset="50%"
+                fill="currentColor"
+                text-anchor="middle"
+            >
+                nsubj
+            </textpath>
+        </text>
+        <path
+            class="displacy-arrowhead"
+            d="M245,266.5 L237,254.5 253,254.5"
+            fill="currentColor"
+        ></path>
+    </g>
+
+    <g class="displacy-arrow">
+        <path
+            class="displacy-arc"
+            id="arrow-0-2"
+            stroke-width="2px"
+            d="M595,264.5 C595,177.0 740.0,177.0 740.0,264.5"
+            fill="none"
+            stroke="currentColor"
+        ></path>
+        <text dy="1.25em" style="font-size: 0.8em; letter-spacing: 1px">
+            <textpath
+                xlink:href="#arrow-0-2"
+                class="displacy-label"
+                startOffset="50%"
+                fill="currentColor"
+                text-anchor="middle"
+            >
+                compound
+            </textpath>
+        </text>
+        <path
+            class="displacy-arrowhead"
+            d="M595,266.5 L587,254.5 603,254.5"
+            fill="currentColor"
+        ></path>
+    </g>
+
+    <g class="displacy-arrow">
+        <path
+            class="displacy-arc"
+            id="arrow-0-3"
+            stroke-width="2px"
+            d="M420,264.5 C420,89.5 745.0,89.5 745.0,264.5"
+            fill="none"
+            stroke="currentColor"
+        ></path>
+        <text dy="1.25em" style="font-size: 0.8em; letter-spacing: 1px">
+            <textpath
+                xlink:href="#arrow-0-3"
+                class="displacy-label"
+                startOffset="50%"
+                fill="currentColor"
+                text-anchor="middle"
+            >
+                dobj
+            </textpath>
+        </text>
+        <path
+            class="displacy-arrowhead"
+            d="M745.0,266.5 L753.0,254.5 737.0,254.5"
+            fill="currentColor"
+        ></path>
+    </g>
+
+    <g class="displacy-arrow">
+        <path
+            class="displacy-arc"
+            id="arrow-0-4"
+            stroke-width="2px"
+            d="M420,264.5 C420,2.0 925.0,2.0 925.0,264.5"
+            fill="none"
+            stroke="currentColor"
+        ></path>
+        <text dy="1.25em" style="font-size: 0.8em; letter-spacing: 1px">
+            <textpath
+                xlink:href="#arrow-0-4"
+                class="displacy-label"
+                startOffset="50%"
+                fill="currentColor"
+                text-anchor="middle"
+            >
+                prep
+            </textpath>
+        </text>
+        <path
+            class="displacy-arrowhead"
+            d="M925.0,266.5 L933.0,254.5 917.0,254.5"
+            fill="currentColor"
+        ></path>
+    </g>
+
+    <g class="displacy-arrow">
+        <path
+            class="displacy-arc"
+            id="arrow-0-5"
+            stroke-width="2px"
+            d="M945,264.5 C945,177.0 1090.0,177.0 1090.0,264.5"
+            fill="none"
+            stroke="currentColor"
+        ></path>
+        <text dy="1.25em" style="font-size: 0.8em; letter-spacing: 1px">
+            <textpath
+                xlink:href="#arrow-0-5"
+                class="displacy-label"
+                startOffset="50%"
+                fill="currentColor"
+                text-anchor="middle"
+            >
+                pobj
+            </textpath>
+        </text>
+        <path
+            class="displacy-arrowhead"
+            d="M1090.0,266.5 L1098.0,254.5 1082.0,254.5"
+            fill="currentColor"
+        ></path>
+    </g>
+</svg>

website/public/images/displacy-span-custom.html

@@ -1,84 +0,0 @@
-<div
-    class="spans"
-    style="
-        line-height: 2.5;
-        font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif,
-            'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol';
-        font-size: 18px;
-        direction: ltr;
-    "
->
-    Welcome to the
-    <span style="font-weight: bold; display: inline-block; position: relative">
-        Bank
-        <span
-            style="
-                background: #ddd;
-                top: 40px;
-                height: 4px;
-                left: -1px;
-                width: calc(100% + 2px);
-                position: absolute;
-            "
-        >
-        </span>
-        <span
-            style="
-                background: #ddd;
-                top: 40px;
-                height: 4px;
-                border-top-left-radius: 3px;
-                border-bottom-left-radius: 3px;
-                left: -1px;
-                width: calc(100% + 2px);
-                position: absolute;
-            "
-        >
-            <span
-                style="
-                    background: #ddd;
-                    color: #000;
-                    top: -0.5em;
-                    padding: 2px 3px;
-                    position: absolute;
-                    font-size: 0.6em;
-                    font-weight: bold;
-                    line-height: 1;
-                    border-radius: 3px;
-                "
-            >
-                BANK
-            </span>
-        </span>
-    </span>
-    <span style="font-weight: bold; display: inline-block; position: relative">
-        of
-        <span
-            style="
-                background: #ddd;
-                top: 40px;
-                height: 4px;
-                left: -1px;
-                width: calc(100% + 2px);
-                position: absolute;
-            "
-        >
-        </span>
-    </span>
-    <span style="font-weight: bold; display: inline-block; position: relative">
-        China
-
-        <span
-            style="
-                background: #ddd;
-                top: 40px;
-                height: 4px;
-                left: -1px;
-                width: calc(100% + 2px);
-                position: absolute;
-            "
-        >
-        </span>
-    </span>
-    .
-</div>

website/public/images/displacy-span.html

@@ -1,123 +0,0 @@
-<div
-    class="spans"
-    style="
-        line-height: 2.5;
-        direction: ltr;
-        font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif,
-            'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol';
-        font-size: 18px;
-    "
->
-    Welcome to the
-    <span style="font-weight: bold; display: inline-block; position: relative">
-        Bank
-        <span
-            style="
-                background: #7aecec;
-                top: 40px;
-                height: 4px;
-                left: -1px;
-                width: calc(100% + 2px);
-                position: absolute;
-            "
-        >
-        </span>
-        <span
-            style="
-                background: #7aecec;
-                top: 40px;
-                height: 4px;
-                border-top-left-radius: 3px;
-                border-bottom-left-radius: 3px;
-                left: -1px;
-                width: calc(100% + 2px);
-                position: absolute;
-            "
-        >
-            <span
-                style="
-                    background: #7aecec;
-                    color: #000;
-                    top: -0.5em;
-                    padding: 2px 3px;
-                    position: absolute;
-                    font-size: 0.6em;
-                    font-weight: bold;
-                    line-height: 1;
-                    border-radius: 3px;
-                "
-            >
-                ORG
-            </span>
-        </span>
-    </span>
-    <span style="font-weight: bold; display: inline-block; position: relative">
-        of
-
-        <span
-            style="
-                background: #7aecec;
-                top: 40px;
-                height: 4px;
-                left: -1px;
-                width: calc(100% + 2px);
-                position: absolute;
-            "
-        >
-        </span>
-    </span>
-    <span style="font-weight: bold; display: inline-block; position: relative">
-        China
-        <span
-            style="
-                background: #7aecec;
-                top: 40px;
-                height: 4px;
-                left: -1px;
-                width: calc(100% + 2px);
-                position: absolute;
-            "
-        >
-        </span>
-        <span
-            style="
-                background: #feca74;
-                top: 57px;
-                height: 4px;
-                left: -1px;
-                width: calc(100% + 2px);
-                position: absolute;
-            "
-        >
-        </span>
-        <span
-            style="
-                background: #feca74;
-                top: 57px;
-                height: 4px;
-                border-top-left-radius: 3px;
-                border-bottom-left-radius: 3px;
-                left: -1px;
-                width: calc(100% + 2px);
-                position: absolute;
-            "
-        >
-            <span
-                style="
-                    background: #feca74;
-                    color: #000;
-                    top: -0.5em;
-                    padding: 2px 3px;
-                    position: absolute;
-                    font-size: 0.6em;
-                    font-weight: bold;
-                    line-height: 1;
-                    border-radius: 3px;
-                "
-            >
-                GPE
-            </span>
-        </span>
-    </span>
-    .
-</div>

website/src/components/embed.js

@@ -107,6 +107,22 @@ const Image = ({ src, alt, title, href, ...props }) => {
     )
 }
 
+const ImageScrollable = ({ src, alt, width, ...props }) => {
+    return (
+        <figure className={classNames(classes.standalone, classes.scrollable)}>
+            <img className={classes['image-scrollable']} src={src} alt={alt} width={width} height="auto" />
+        </figure>
+    )
+}
+
+const Standalone = ({ height, children, ...props }) => {
+    return (
+        <figure className={classes.standalone} style={{ height }}>
+            {children}
+        </figure>
+    )
+}
+
 const ImageFill = ({ image, ...props }) => {
     return (
         <span
@@ -137,4 +153,4 @@ const GoogleSheet = ({ id, link, height, button = 'View full table' }) => {
     )
 }
 
-export { YouTube, SoundCloud, Iframe, Image, ImageFill, GoogleSheet }
+export { YouTube, SoundCloud, Iframe, Image, ImageFill, ImageScrollable, GoogleSheet, Standalone }

website/src/remark.js

@@ -13,7 +13,7 @@ import Aside from './components/aside'
 import Button from './components/button'
 import Tag from './components/tag'
 import Grid from './components/grid'
-import { YouTube, SoundCloud, Iframe, Image, GoogleSheet } from './components/embed'
+import { YouTube, SoundCloud, Iframe, Image, ImageScrollable, GoogleSheet, Standalone } from './components/embed'
 import Project from './widgets/project'
 import { Integration, IntegrationLogo } from './widgets/integration.js'
 import { Logos, Colors, Patterns } from './widgets/styleguide'
@@ -90,6 +90,8 @@ export const remarkComponents = {
      * For regular img elements it is not possible to pass properties
      */
     Image,
+    ImageScrollable,
+    Standalone,
 
     Label,
     Logos,