explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-14 18:22:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

add NER.v3 example to README

Browse Source
This commit is contained in:
Kabir Khan 2023-08-01 10:52:24 -07:00
parent a0a195688f
commit ffd18613d1
1 changed files with 158 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

169
website/docs/usage/large-language-models.mdx
View File

@ -119,9 +119,13 @@ from spacy_llm.util import assemble
nlp = assemble("config.cfg") nlp = assemble("config.cfg")
doc = nlp("You look gorgeous!") doc = nlp("You look gorgeous!")
print(doc.cats) print(doc.cats)
# {"COMPLIMENT": 1.0, "INSULT": 0.0}
``` ```
### Example 2: Add NER using an open-source model through Hugging Face {id="example-2"}
### Example 2: Add a text classifier using an open-source model through HuggingFace {id="example-2"}
The same TextCat task can also be used with an open source model from HuggingFace.
To run this example, ensure that you have a GPU enabled, and `transformers`, To run this example, ensure that you have a GPU enabled, and `transformers`,
`torch` and CUDA installed. For more background information, see the `torch` and CUDA installed. For more background information, see the
@ -129,7 +133,7 @@ To run this example, ensure that you have a GPU enabled, and `transformers`,
Create a config file `config.cfg` containing at least the following (or see the Create a config file `config.cfg` containing at least the following (or see the
full example full example
[here](https://github.com/explosion/spacy-llm/tree/main/usage_examples/ner_dolly)): [here](https://github.com/explosion/spacy-llm/tree/main/usage_examples/textcat_dolly)):
```ini ```ini
[nlp] [nlp]
@ -142,9 +146,10 @@ pipeline = ["llm"]
factory = "llm" factory = "llm"
[components.llm.task] [components.llm.task]
@llm_tasks = "spacy.NER.v2" @llm_tasks = "spacy.TextCat.v2"
labels = ["PERSON", "ORGANISATION", "LOCATION"] labels = ["COMPLIMENT", "INSULT"]
# Use a local Dolly model instead of an API
[components.llm.model] [components.llm.model]
@llm_models = "spacy.Dolly.v1" @llm_models = "spacy.Dolly.v1"
# For better performance, use dolly-v2-12b instead # For better performance, use dolly-v2-12b instead
@ -157,8 +162,9 @@ Now run:
from spacy_llm.util import assemble from spacy_llm.util import assemble
nlp = assemble("config.cfg") nlp = assemble("config.cfg")
doc = nlp("Jack and Jill rode up the hill in Les Deux Alpes") doc = nlp("You look gorgeous!")
print([(ent.text, ent.label_) for ent in doc.ents]) print(doc.cats)
# {"COMPLIMENT": 1.0, "INSULT": 0.0}
``` ```
Note that Hugging Face will download the `"databricks/dolly-v2-3b"` model the Note that Hugging Face will download the `"databricks/dolly-v2-3b"` model the
@ -167,7 +173,126 @@ first time you use it. You can
by setting the environmental variable `HF_HOME`. Also, you can upgrade the model by setting the environmental variable `HF_HOME`. Also, you can upgrade the model
to be `"databricks/dolly-v2-12b"` for better performance. to be `"databricks/dolly-v2-12b"` for better performance.
### Example 3: Create the component directly in Python {id="example-3"}
### Example 3: Add NER using a GPT-3 model from OpenAI {id="example-3"}
In previous versions of the `spacy-llm` `NER` and `SpanCat` tasks, you could configure
a zero-shot pipeline without any examples. The new `v3` (`spacy.NER.v3` and `spacy.SpanCat.v3`)
tasks use few-shot learning exclusively require at least 1 prompt example to be configured.
The old zero-shot prompt we were using really didn't work that well from our evaluations on
well known NER datasets (# TODO: link to evaluation results?)
The new v3 task prompts are based on the [PromptNER](https://arxiv.org/abs/2305.15444) paper and use
chain-of-thought reasoning to improve model quality. The accuracy of this prompt should be much better
for most NER cases but it does require a little bit more work upfront.
```
@misc{ashok2023promptner,
title={PromptNER: Prompting For Named Entity Recognition},
author={Dhananjay Ashok and Zachary C. Lipton},
year={2023},
eprint={2305.15444},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
Create a config file `config.cfg` containing at least the following (or see the
full example
[here](https://github.com/explosion/spacy-llm/tree/main/usage_examples/ner_openai)):
```ini
[nlp]
lang = "en"
pipeline = ["llm"]
[components]
[components.llm]
factory = "llm"
[components.llm.task]
@llm_tasks = "spacy.NER.v3"
labels = ["DISH", "INGREDIENT", "EQUIPMENT"]
description = Entities are the names food dishes,
ingredients, and any kind of cooking equipment.
Adjectives, verbs, adverbs are not entities.
Pronouns are not entities.
[components.llm.task.label_definitions]
DISH = "Known food dishes, e.g. Lobster Ravioli, garlic bread"
INGREDIENT = "Individual parts of a food dish, including herbs and spices."
EQUIPMENT = "Any kind of cooking equipment. e.g. oven, cooking pot, grill"
[components.llm.task.examples]
@misc = "spacy.FewShotReader.v1"
path = "ner_examples.json"
[components.llm.model]
@llm_models = "spacy.GPT-3-5.v1"
```
```json
# ner_examples.json
[
{
"text": "You can't get a great chocolate flavor with carob.",
"spans": [
{
"text": "chocolate",
"is_entity": false,
"label": "==NONE==",
"reason": "is a flavor in this context, not an ingredient"
},
{
"text": "carob",
"is_entity": true,
"label": "INGREDIENT",
"reason": "is an ingredient to add chocolate flavor"
}
]
},
{
"text": "You can probably sand-blast it if it's an anodized aluminum pan",
"spans": [
{
"text": "sand-blast",
"is_entity": false,
"label": "==NONE==",
"reason": "is a cleaning technique, not some kind of equipment"
},
{
"text": "anodized aluminum pan",
"is_entity": true,
"label": "EQUIPMENT",
"reason": "is a piece of cooking equipment, anodized is included since it describes the type of pan"
},
]
}
]
```
Now run:
```python
from spacy_llm.util import assemble
nlp = assemble("config.cfg")
doc = nlp(
"Sriracha sauce goes really well with hoisin stir fry, "
"but you should add it after you use the wok."
)
print([(ent.text, ent.label_) for ent in doc.ents])
# [('Sriracha sauce', 'INGREDIENT'),
# ('hoisin stir fry', 'DISH'),
# ('wok', 'EQUIPMENT')]
```
### Example 4: Create the component directly in Python {id="example-4"}
The `llm` component behaves as any other component does, so adding it to an The `llm` component behaves as any other component does, so adding it to an
existing pipeline follows the same pattern: existing pipeline follows the same pattern:
@ -180,16 +305,38 @@ nlp.add_pipe(
"llm", "llm",
config={ config={
"task": { "task": {
"@llm_tasks": "spacy.NER.v2", "@llm_tasks": "spacy.NER.v3",
"labels": ["PERSON", "ORGANISATION", "LOCATION"] "labels": ["DISH", "INGREDIENT", "EQUIPMENT"]
"examples": [
{
"text": "You can't get a great chocolate flavor with carob.",
"spans": [
{
"text": "chocolate",
"is_entity": False,
"label": "==NONE==",
"reason": "is a flavor in this context, not an ingredient"
},
{
"text": "carob",
"is_entity": True,
"label": "INGREDIENT",
"reason": "is an ingredient to add chocolate flavor"
}
]
},
]
}, },
"model": { "model": {
"@llm_models": "spacy.gpt-3.5.v1", "@llm_models": "spacy.GPT-3.5.v1"
}, },
}, },
) )
nlp.initialize() nlp.initialize()
doc = nlp("Jack and Jill rode up the hill in Les Deux Alpes") doc = nlp(
"Sriracha sauce goes really well with hoisin stir fry, "
"but you should add it after you use the wok."
)
print([(ent.text, ent.label_) for ent in doc.ents]) print([(ent.text, ent.label_) for ent in doc.ents])
``` ```