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 handling additional properties in mcp tool schema
- [Bug]: VectorMemoryBlock writes the session filter into query_kwargs, pinning every later session to the first session's id
- fix(core): FunctionTool.call() returns an un-awaited coroutine as a successful result when fn and async_fn are both async
- split_text_keep_separator puts the separator at the start of each split, not the end as documented
- [Bug]: Dispatcher.__init__() uses mutable default arguments ([])
- [Bug]: UPSERTS_AND_DELETE never deletes documents that share a content hash
- llamaindex-openeval-adapter: convert core.evaluation evaluators/results to/from EvalPort (standalone package, not a PR)
- fix: replace mutable default args [] with None in Dispatcher.__init__
- fix(core): keep separators at end of text splits
- fix(core): build the VectorMemoryBlock session filter per call instead of mutating query_kwargs
- Docs
- not yet supported