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): allow custom kwargs to override defaults in as_retriever
- fix(core): keep related nodes when deleting from SimplePropertyGraphStore (#23988)
- [Bug]: A multi-parameter fan-in step reached through a `@catch_error` handler is rejected by validation, though the workflow runs correctly
- [Bug]: A typed state that subclasses `DictState` comes back as a plain `DictState` from `ctx.to_dict()` / `Context.from_dict`, and its declared fields are lost
- [Bug]: Streaming structured prediction returns empty objects when the model wraps JSON in a ```json fence
- fix(core): implement async DocumentSummaryIndex node deletion
- fix(core): infer_torch_device() returns xpu for Intel GPUs (#23667)
- perf(core): avoid set allocations in sparse_similarity and parallelize aget_agg_embedding_from_queries
- [Bug]: non-streaming calls send 12 requests to a rate-limited provider — the retry decorator and the OpenAI client both retry
- fix(llms-openai): keep a single retry layer for non-streaming calls
- Docs
- not yet supported