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
- core: `InMemoryRecordManager.list_keys(limit=0)` returns all keys instead of an empty list
- feat(typesafe): experimental classifier based `SkillsMiddleware`
- core: `finalize_tool_call_chunk` coerces `id=None` to `""`, collapsing parallel id-less tool calls
- feat(typesafe): agent middleware powered by TypeSafe classifiers
- refactor(typesafe): mirror SDK request and client configuration
- core: `AsyncBaseTracer` drops `name` in `on_tool_start` and `response` in `on_llm_error`, diverging from `BaseTracer`
- core: `InMemoryVectorStore` raises `NotImplementedError` for relevance-score search and the `similarity_score_threshold` retriever
- MCP ResourceLink/EmbeddedResource metadata dropped when converting to LangChain content blocks (langchain.mcp)
- langchain: preserve result-level MCP `_meta` in tool results
- langchain 1.4.0: any after_model middleware using documented `jump_to="tools"` bypasses the HITL pending_tool_calls gate and re-executes rejected tool calls
- Docs
- Python not yet supported