Releases: explosion/spacy-llm
Releases · explosion/spacy-llm
v0.4.3: LLama 2, Claude 2, fixes for Falcon & readme
✨ New features and improvements
🔴 Bug fixes
- Corrects how runtime arguments are passed to Falcon (#222)
- Fixes incorrect capitalization in example in readme (#227)
📖 Documentation and examples
We've moved most of our documentation to the main spaCy docs:
- Usage pages: https://spacy.io/usage/large-language-models
- API pages: https://spacy.io/api/large-language-models
👥 Contributors
@honnibal, @ines, @koaning, @rmitsch, @svlandeg, @victorialslocum
v0.4.2: Guard REL against entity index errors, warn instead of error for REST auth verification
v0.4.1: Authenticate models at init time, fix incorrect model names
✨ New features and improvements
- Verify authentication details at init (instead of at run) time for Anthropic and Cohere models (#206)
🔴 Bug fixes
- Update OpenLLaMA model names after updates on HuggingFace (#209)
- Fix incorrectly spelled model names for OpenAI models in migration guide (#210)
👥 Contributors
v0.4.0: Falcon, sentiment analysis, summarization, backend refactoring
✨ New features and improvements
- NEW: Refactored to transition from backend- to model-centric architecture. Note: this is breaking, you'll need to adjust your configs (#176)
- NEW: Support for Falcon via HuggingFace (#179)
- NEW: Extract prompt examples from component initialization (#163)
- NEW: Summary task
spacy.Summary.v1
(#181) - NEW: Sentiment analysis task
spacy.Sentiment.v1
(#200) - More thorough check for label inconsistencies in span-related tasks NER, REL, SpanCat, TextCat (#183)
- Update
langchain
pin (#196) - Make fewshot file reader more robust w.r.t. file formats (#184)
⚠️ Backwards incompatibilities
- Built-in support for MiniChain was dropped (#176)
- The switch from a backend- to a model-centric architecture (#176) requires light adjustments in your config. Check out the migration guide to see how to update your config
👥 Contributors
@bdura, @honnibal, @ines, @kabirkhan, @koaning, @rmitsch, @shadeMe, @svlandeg, @vin-ivar
v0.3.2: Fixes for `nlp.pipe(..., as_tuples=True)` and caching of docs with LLM output
v0.3.1: Make type validation optional, fix `pipe_labels()`
v0.3.0: Cohere, Anthropic, OpenLLaMa, StableLM + prompt & response logging + streamlit demo + lemmatization
✨ New features and improvements
- NEW: Optional storing of prompts and responses in
Doc
objects (#127) - NEW: Optional logging of prompts and responses (#80)
- NEW: Streamlit demo (#102)
- NEW: Support for Cohere in backend
spacy.REST.v1
(#165) - NEW: Support for Anthropic in backend
spacy.REST.v1
(#157) - NEW: Support for OpenLLaMA via HuggingFace with the backend
spacy.OpenLLaMa_HF.v1
(#151) - NEW: Support for StableLM via HuggingFace with the backend
spacy.StableLM_HF.v1
(#141) - NEW: Lemmatization task
spacy.Lemma.v1
(#164)
🔴 Bug fixes
- Fix bug with sending empty prompts if all
Doc
objects are cached (#166) - Fix issue with
LangChain
model creation due to updated argument name (#162)
👥 Contributors
@adrianeboyd, @bdura, @honnibal, @ines, @kabirkhan, @ljvmiranda921, @rmitsch, @svlandeg, @victorialslocum, @vin-ivar
v0.2.1: Scoring support & bug fixes
✨ New features and improvements
- NEW:
llm
component supports scoring, like other spaCy components (#135) - Labels for
spacy.NER.v2
,spacy.REL.v1
,spacy.SpanCat.v2
,spacy.TextCat.v2
can be specified as list (#137)
🔴 Bug fixes
- Fix type comparison in type checks failing on some platforms (#158)
- Fix example 3 in readme failing (#137)
👥 Contributors
@adrianeboyd, @bdura, @honnibal, @ines, @kabirkhan, @KennethEnevoldsen, @rmitsch, @svlandeg, @vin-ivar
v0.2.0: New tasks for REL and spancat, reading prompt templates from file, and various improvements and bug fixes
✨ New features and improvements
- NEW: New relation extraction task
spacy.REL.v1
(#114) - NEW: New spancat task
spacy.SpanCat.v1
for entity recognition with overlapping spans (#101) - NEW: Set prompt templates as string or read them from files (e. g. Jinja templates) using
spacy.FileReader.v1
(#95) - Improved prompt for NER task
spacy.NER.v2
(#99) - Ability to describe labels in tasks
spacy.NER.v2
,spacy.SpanCat.v1
(#84) - Improved error handling and retry mechanics in REST backend
spacy.REST.v1
(#110) spacy-llm
can now (#119) be installed with all dependencies for- MiniChain and LangChain with
spacy-llm[minichain]
orspacy-llm[langchain]
respectively
for locally running models on GPU withspacy-llm[transformers]
- Improved type checking to ensure tasks and backend play nice with each other (#83)
- MiniChain and LangChain with
- Use Task abstraction instead of previously two functions template and parse to make the config easier to read (#91)
🔴 Bug fixes
📖 Documentation and examples
- Updated the readme with information about the caching mechanism.
- New usage examples:
👥 Contributors
@adrianeboyd, @bdura, @honnibal, @ines, @kabirkhan, @ljvmiranda921, @rmitsch, @svlandeg
v0.1.2: Bugfix for binary textcat task
- Fix processing of LLM response for binary textcat