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
- `ProviderToolSearchMiddleware` defers tools as flat top-level functions instead of wrapping them in a `namespace` — no token savings
- bug: Legacy Qdrant vector store returns raw distances instead of normalized relevance scores
- bug: [chroma] similarity_search_by_vector_with_relevance_scores returns raw distances instead of normalized scores
- core: `BaseChatModel.agenerate` masks a non-`Exception` `BaseException` with `AttributeError`
- TypeError: unsupported operand type(s) for += on dict in _combine_llm_outputs when making multiple LLM calls
- langchain stream_events v3 final response tokens not streamed in real-time, all arrive at once
- Bug: langchain-anthropic file_tool callback never emits args["old_path"] but _handle_rename reads it -> KeyError on every rename
- bug(core): cache implementing `__len__` makes `generate`/`agenerate` raise `KeyError`
- HTMLSemanticPreservingSplitter reorders inline text around tags (e.g. <strong>, <a>, etc.)
- Feature request: Profile-aware prompt router with ML-backed routing and ensemble fallback
- Docs
- Python not yet supported