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
- Add social impact RAG example for community resource discovery
- fix(core): preserve exception propagation in run_async_tasks with show_progress=True
- [Bug]: similarity() returns nan for zero-norm embeddings, corrupting top-k selection
- fix(core): return 0.0 similarity for zero-norm embeddings instead of nan
- [Bug]: max_iterations and early_stopping_method passed to .run() are ignored when the Context is reused
- fix(core): apply run-level max_iterations and early_stopping_method on a reused Context
- fix(agent-workflow): honor per-run max_iterations/early_stopping_method on reused Context
- fix(ollama): stop deduping streamed tool calls by name and arguments (#22464)
- fix: honor chunk_lines/chunk_lines_overlap in CodeSplitter
- docs: add Nebius Serverless Endpoint RAG example
- Docs
- not yet supported