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): unescape doubled braces in SafeFormatter so prompts render valid JSON examples
- fix(core): honor supplied LLM in no-text and context-only modes
- fix(core): honor memory passed to run() when the Context is reused
- fix(core): pass callback_manager to response synthesizer in RetrieverQueryEngine.from_args
- perf(core): avoid re-tokenizing popped splits in TokenTextSplitter._merge
- fix(readers-web): preserve callback-owned page metadata
- fix(chroma): allow metadata-only node deletion in ChromaVectorStore
- [Bug]: Chat memory from_dict mutates the snapshot and breaks repeated restores
- perf(core): use deque for overlap window in SentenceSplitter._merge
- fix(core): preserve chat memory input snapshots during restore
- Docs
- not yet supported