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(vertex,google-genai): normalize Gemini model IDs and preserve streaming thought/cached token usage
- Docs: pass workflow runtime values to memory blocks
- Integration example proposal: typed bounded retrieval over large MCP tool sets
- [Bug]: Relative score fusion corrupts rankings when cached results share score wrappers
- fix(core): isolate cached scores during relative fusion
- [Bug]: SimpleFileNodeParser ignores custom id_func for supported file types
- fix: forward id_func to SimpleFileNodeParser child parsers
- fix(anthropic): stop forcing tool_choice for Opus 5.5 and Sonnet 5.5
- fix(patentsview): import time used for Retry-After backoff
- [Bug]: RetrieverEvaluator, MultiModalRetrieverEvaluator and ObjectRetriever.aretrieve still call sync postprocess_nodes() in async paths
- Docs
- not yet supported