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
- [Bug]: PIINodePostprocessor.mask_pii() crashes with raw IndexError/JSONDecodeError on malformed LLM output
- fix(postprocessor): raise clear ValueError for malformed LLM output in PIINodePostprocessor
- feat(readers-notion): support a configurable `base_url`
- fix(core): make similarity_top_k=0 return no results instead of all
- [Bug]: Memory trims multimodal chat history with a flat 256 token estimate, contradicting the blocks' own token estimators
- Skip empty or whitespace-only documents in SemanticDoubleMergingSplitterNodeParser
- chore(deps): bump the uv group across 44 directories with 2 updates
- chore(deps): bump the uv group across 5 directories with 2 updates
- fix(core): include docstring param descriptions in FunctionTool schema
- fix(core): preserve fenced PGVector SQL queries
- Docs
- not yet supported