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): keep repacked sub-chunks in order in the Refine loop
- fix: encode ImageBlock streams when Base64 is requested
- fix(memory): preserve system messages through FIFO waterfall eviction
- fix(async): narrow except in run_async_tasks to ImportError only
- fix(schema): use as_posix() for MediaResource path hash — platform-independent hashes
- [Bug]: BaseWorkflowAgent.init_run raises IndexError when chat_history contains no user messages
- [Bug]: Refine response synthesizer refines repacked sub-chunks in reverse order
- fix: stop rendering literal "None" in ChatML prompts for content-less messages
- fix(instrumentation): avoid mutable defaults in Dispatcher.__init__
- fix(core): prevent Memory from silently evicting system messages
- Docs
- not yet supported