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: handle None backup separators in TokenTextSplitter
- [Bug]: Mimetype is None for files with uppercase extensions (e.g. IMG_0001.JPG)
- docs: list the Section Anything PDF reader on the integrations page
- fix(core): guess mimetype case-insensitively from file extension
- docs: move HoneyHive to main observability integrations with OpenInference setup
- docs: note that local servers speaking Ollama's API work with the Ollama package
- Require `llama-index-storage-kvstore-postgres` 0.6.x for the Postgres docstore
- [Bug]: `BasicRuntime.restore()` fails with "Invocation ... not found in in_progress" when it replays the journal of a run that was itself restored
- [Bug]: SentenceSplitter does not recognize the Devanagari danda, so Hindi and Marathi chunks are cut mid sentence
- Add InfinityDB zero-LLM memory integration
- Docs
- not yet supported