Skip to content

feat: add LlamaIndex retrievers#355

Closed
raoabinav wants to merge 5 commits into
StarTrail-org:mainfrom
raoabinav:feat/llamaindex-retrievers
Closed

feat: add LlamaIndex retrievers#355
raoabinav wants to merge 5 commits into
StarTrail-org:mainfrom
raoabinav:feat/llamaindex-retrievers

Conversation

@raoabinav

Copy link
Copy Markdown
Contributor

Evaluator Summary

  • Abi added optional LlamaIndex retriever adapters backed by LEANN indexes, supporting both pure vector retrieval and hybrid dense-vector plus BM25 retrieval.
  • The design keeps LlamaIndex as an optional lazy import, preserving lightweight core LEANN installs while enabling users already in the LlamaIndex ecosystem to plug in LEANN retrieval directly.
  • The implementation converts LEANN SearchResult values into LlamaIndex TextNode / NodeWithScore objects while preserving IDs, text, metadata, and scores.
  • Quality bar: tests cover query validation, weighting, scoring, metadata preservation, async retrieval, and lazy integration imports.

# Conflicts:
#	tests/test_readme_examples.py
@raoabinav

Copy link
Copy Markdown
Contributor Author

Parking this PR for now to keep the review queue focused on #347. I’ll revisit/reopen this work later as a smaller clean PR once the content-hash PR lands.

@raoabinav raoabinav closed this Jun 6, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant