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 supported41 Subscribers
Add a CodeTriage badge to langchain
Help out
- Issues
- ToolStrategy retries structured-output validation failures without any cap
- text-splitters: `RecursiveJsonSplitter` sizes chunks against escaped JSON, so `ensure_ascii=False` chunks come back far below `max_chunk_size`
- SummarizationMiddleware sends unredacted conversation history to the summary model, bypassing PIIMiddleware including strategy=block
- langchain-typesafe: allow supplying a classifier to experimental middleware
- langchain-typesafe: recursive `State` alias leaves input schema unresolvable
- langchain-typesafe: ModelRouterMiddleware exposes ignored model_route in input schema
- xai: `ChatXAI` builds two `openai.OpenAI` clients per instance — `client` is not a view onto `root_client`
- ChatAnthropic.bind_tools() raises ValueError on Anthropic's documented browser_toolset_20260801
- core: empty `group_ids` bypasses validation and filtering in `InMemoryRecordManager`
- langchain-typesafe: AutoModeMiddleware classifies a tool call that inner middleware can replace before execution
- Docs
- Python not yet supported