langchain
https://github.com/langchain-ai/langchain
Python
⚡ Building applications with LLMs through composability ⚡
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported39 Subscribers
Add a CodeTriage badge to langchain
Help out
- Issues
- Request for Guidance: Reasoning Transparency After Migrating from `ZeroShotAgent` to `create_agent`
- feat(standard-tests): validate tool call chunks during streaming
- feat(core): Add OutputFixingParser for LCEL chain retry support
- not requiring uuid-utils for python-3.14 free-threading
- Support recursive tool schemas
- Warn when passing in block types not supported by a model
- create_agent did not remove the reasoning from the message list
- Error in create_agent() when enable "messages" streaming mode: 'Error: is not a valid tool'
- `EvaluationResult.feedback_config` silently drops unknown or partial dict fields without error
- QdrantVectorStore cannot be used in a truly async form, no alternative is provided
- Docs
- Python not yet supported