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]: Ollama: per-call think=False is silently dropped by the "or self.thinking" fallback (request sent without think)
- fix(anthropic): add usage metadata to non-streaming chat() and achat()
- fix(ollama): stop deduping streamed tool calls by name+arguments
- [Bug]: stream_chat/astream_chat drop a tool call when two calls share the same name+arguments
- docs: fix broken MariaDB Vector Overview link
- fix(core): skip empty nodes in JSONNodeParser
- Use UTF-8 for Feedly auth token writes
- fix(sharepoint): prevent path traversal in SharePointReader downloads
- fix: Arbitrary file read via ImageDocument.metadata["file_path"]
- feat(core): add truncate_text_middle helper function to core utils
- Docs
- not yet supported