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]: Tool-call tokens not counted by Memory, leading to "prompt is too long" (400) errors with AgentWorkflow
- docs: clarify LlamaCloud embedding auth errors
- docs(memory): add RecollectMemory notebook (standalone PyPI integration)
- fix(google-genai): handle MaaS role alias and models.get failure
- fix(sambanova): resolve sambanova_url from the sambanova_url kwarg, not the API key
- fix(github-reader): add asyncio_mode=auto to unblock async tests in CI
- fix(vertexai-search): use asyncio.to_thread in _aretrieve to avoid blocking event loop
- fix(vertexai-search): populate id_ and metadata in structured data store results
- VertexAISearchRetriever drops document id/name and metadata for structured data store results
- VertexAISearchRetriever.aretrieve blocks asyncio event loop by calling synchronous _retrieve
- Docs
- not yet supported