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 supported40 Subscribers
Add a CodeTriage badge to langchain
Help out
- Issues
- fix(core): strip injected args before validation for strict schemas
- Improve `pretty_print`
- feat(core,model-profiles): add model profile augmentation for code execution support
- fix(langchain): Explicitly disable callbacks in `LLMToolSelectorMiddleware`
- Empty `AIMessage` when using `astream()` with Anthropic programmatic tool calling
- Python 3.14 support
- Structured output and tool invocation
- When using OpenAI Responses API in streaming mode, there is no chunk from langchain that contains the entire function_call definition including arguments.
- SummarizationMiddleware breaks Anthropic extended thinking by removing thinking blocks during active assistant turns
- fix(core): resolve tools losing optional runnable config
- Docs
- Python not yet supported