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(benchmarks): fix file handle leak and missing timeout in HotpotQA download
- fix(core): `retriever_weights` not applied in `QueryFusionRetriever` reciprocal_rerank mode
- fix(embeddings): do not clutter stdout when turning off embeddings
- [Feature Request]: Token-efficient serialization for agent pipelines to reduce context window overhead
- Allow to pass GCP credentials on Anthropic initialization
- docs: add Sulci Cache — context-aware semantic LLM cache integration
- fix: async HTTP for DocumentBlock URL resolution in async chat paths
- [Bug]: @retry_decorator on async generator _conversion_stream_with_retry is silently inert
- [Bug]: OpenAILike / FunctionAgent: Kimi-K2.5 sometimes returns final answer in reasoning_content
- [Bug]: ElasticsearchStore sync methods use run_until_complete — breaks in ASGI with pooled clients
- Docs
- not yet supported