llama_index
https://github.com/run-llama/llama_index
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.
not yet supported1 Subscribers
Add a CodeTriage badge to llama_index
Help out
- Issues
- feat(postprocessor): add ZTDS zero-trust in-memory node postprocessor (IETF draft-02)
- [Bug]: LLMMultiSelector adds the SelectionOutputParser format instructions to the prompt twice
- fix(core): stop LLMMultiSelector from adding output format instructions twice
- from_openai_message_dict raises KeyError on image_url parts missing the optional detail key
- fix(openai): tolerate image_url parts without detail
- fix(core): fully bind function tool arguments
- [Documentation]: The API documentation cannot be used properly and cannot be scrolled to see more content.
- fix(agent): keep state_prompt out of the message stored in memory
- [Bug]: ReActAgent handoff leaves stale current_reasoning in ctx.store, contaminating the next turn's prompt and memory
- fix(core): stop prompt constructors from mutating the caller's metadata dict
- Docs
- not yet supported