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
- langchain-anthropic: `cache_control` on a `tool_use` content block is silently dropped when a matching `tool_calls` item exists
- ChatMistralAI incompatible token output format for LangSmith traceability
- Add Xquik tool pattern for public X data workflows
- Add OpenRouterEmbeddings to langchain-openrouter
- Bug: SummarizationMiddleware._find_safe_cutoff_point preserves orphan ToolMessages -> provider 400 on next call
- create_agent: model_to_tools router can return "model" but path_map omits it -> KeyError('model')
- create_sql_query_chain allows Indirect Prompt Injection via DB sample rows, Direct Prompt Injection via unsanitized question, and emits multi-statement SQL without validation`
- test_mset_chmod fails on Windows due to unsupported chmod permission bits
- Inconsistent `generations` shape in chat model streaming `on_llm_error` callbacks: emits `[[]]` and `[[chunk], []]` where every other path emits `[]`
- Stale `xfail` markers in `langchain-core` tests: `test_convert_to_openai_function_nested_v2` and `test_sync_in_sync_lambdas` pass but are marked expected-to-fail
- Docs
- Python not yet supported