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): ignore non-query brackets in the FLARE output parser
- [Bug]: PII postprocessors reintroduce raw metadata into LLM context
- fix: [Bug]: MultiModalVectorStoreIndex.delete_ref_doc raises KeyError with store_nodes_override=True and leaves the docstore partially deleted
- fix(openai): do not force tool_choice when pydantic_program_mode is LLM
- fix(pii): prevent raw metadata from reappearing in LLM input
- fix: retain tokenizer cache for spawned ingestion workers
- perf(core): avoid O(N) embedding_dict scan in SimpleVectorStore.delete_nodes when node_ids is provided
- fix(core): handle fenced JSON in structured streaming
- fix(core): return no nodes from SimplePropertyGraphStore.get for empty ids
- fix(core): allow custom kwargs to override defaults in remaining as_retriever methods
- Docs
- not yet supported