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): avoid mutating retriever results during fusion
- [Bug]: `SummaryIndexLLMRetriever.aretrieve` blocks the event loop (no async path; calls sync llm.predict)
- fix(core): add `async _aretrieve` to `SummaryIndexLLMRetriever`
- [Bug]: AG-UI router: system_prompt is emitted in MESSAGES_SNAPSHOT and grows by one copy every run
- fix(ag-ui): keep the server system_prompt out of MESSAGES_SNAPSHOT
- [Bug]: AG-UI router: frontend tool parameters lose their types and enums (everything becomes str)
- fix(ag-ui): keep the client's JSON Schema for dynamic frontend tools
- [Bug]: AG-UI router: RunAgentInput.context is never passed to the LLM
- fix(ag-ui): pass RunAgentInput.context to the LLM
- [Bug]: AG-UI router: prior tool calls are sent to the LLM as <tool_call> text, so models stop making native tool calls
- Docs
- not yet supported