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
- fix(core): avoid mutating caller handlers list in CallbackManager
- perf(evaluation): reuse QA query engine and batch async QA in DatasetGenerator
- fix(readers-web): keep RSS user agents local to each reader
- Example proposal: physics/bounds validation as a workflow event handler (deterministic)
- fix(core): avoid `defaultdict` mutation and plain-dict `KeyError` in `LlamaDebugHandler`
- Open-source MCP runtime behavior security tools - RFC 9334 aligned
- fix(core): scope property graph node deduplication by identity
- perf(memory): precompute message token counts and avoid slice reversals in Memory._manage_queue
- fix(core): preserve negative scores in graph vector retrieval
- [Bug]: TreeIndex insertion erases the children of new root summaries, making inserted nodes unreachable
- Docs
- not yet supported