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
- [Bug]: TokenCounter counts every native tool call twice (ToolCallBlock and additional_kwargs["tool_calls"])
- [Bug]: TokenCountingHandler counts a tool-call completion as "assistant: None" when usage is missing
- fix(core): stop double-counting native tool calls in TokenCounter
- fix(core): preserve TreeIndex children during root consolidation
- Count generated tool calls in the token-counting usage-less fallback
- fix(core): strip the JSONPath prefix before custom output processors run in JSONQueryEngine
- fix(core): stop chat-to-completion converters from mutating the source message kwargs
- [Bug]: Regression: as_query_engine(llm=..., response_mode="no_text" / "context_only") ignores the supplied LLM again
- [Bug]: Agent run(memory=..., ctx=...) stops writing to the supplied memory once the Context is reused
- chore(deps): bump github/codeql-action from 4.37.9 to 4.39.2
- Docs
- not yet supported