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): align EmbeddingRecencyPostprocessor dedup with sorted node order
- fix(ag-ui): record ToolMessage for frontend tool_call_ids at suspend boundary
- [Bug]: workflow_as_mcp captures a single Workflow instance, sharing self.* state across every MCP client
- fix(llms): default streaming role to ASSISTANT when delta.role is None (zhipuai, konko)
- fix: support workflow factories for MCP apps
- fix(core): unescape "{{"/"}}" in SafeFormatter.format
- [codex] Use CreateSchema for chat store schemas
- fix: refresh shared docstore vector indexes
- fix(protocols/ag-ui): require tool_call_id on tool messages
- fix: initialize multimodal retriever base state
- Docs
- not yet supported