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
- chore(deps): bump the uv group across 3 directories with 1 update
- chore(deps): bump the uv group across 2 directories with 9 updates
- fix(core): preserve prompt attributes in `LLMQuestionGenerator._update_prompts` and handle single-object JSON in `SubQuestionOutputParser`
- fix(memory): avoid mutating messages when attaching session metadata
- fix(memory): deduplicate and cap condensed facts
- fix(core): preserve original nodes during metadata replacement
- fix(core): reject duplicate sub-question tool names
- fix(memory): reject negative oldest-message counts
- fix(core): skip missing schema keys when formatting output prompts
- fix(tools): offload synchronous on-demand retrieval setup
- Docs
- not yet supported