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 TokenTextSplitter chunks within budget
- fix(node_parser): prevent TokenTextSplitter chunk token overflow when stripped (fix #22858)
- feat(core): give ChatMessage an optional id and Memory a way to look one up
- Memory waterfall loses flushed messages when a memory block fails
- [Bug]: TokenTextSplitter emits chunks one token over chunk_size because splits are budgeted unstripped
- feat(core): add native async support to PIINodePostprocessor
- fix(core): fall back to plain-text read when nltk 3.10.3+ rejects hardlinked stopwords
- fix(cohere-rerank): catch KeyError when COHERE_API_KEY is missing to raise intended ValueError (#22774)
- [Feature Request]: Query-aware, token-budget web reader for RAG pipelines
- [Feature Request]: List llama-index-tools-sprites in LlamaHub Agent Tools
- Docs
- not yet supported