UC Berkeley releases LEANN, an open-source vector index that recomputes embeddings at query time
Overview
UC Berkeley's Sky Computing Lab has released LEANN, an open-source vector index that stores a pruned graph and recomputes embeddings at query time instead of saving them.
MarkTechPost reports that the project's repository benchmark shows a 60 million chunk Wikipedia index shrinking from 201 GB to 6 GB. On the tested hardware, retrieval takes seconds rather than milliseconds.
The code is MIT licensed and installs with uv pip install leann. The storage figures come from the project's own benchmark, and the report does not describe independent testing.
Written by AI from the articles below · updated Oct 27, 7:45 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- MarkTechPostNewsLEANN open-source vector index cuts a 60M-chunk RAG index from 201 GB to 6 GB
AIUC Berkeley's Sky Computing Lab released LEANN, an open-source vector index that stores a pruned graph and recomputes embeddings at query time instead of saving them. The repo benchmark shows a 60 million chunk Wikipedia index shrinking from 201 GB to 6 GB, with retrieval taking seconds rather than milliseconds on the tested hardware.
Heat Trend
- Current comparable heat
- 7
- Peak comparable heat
- 9Oct 27, 8:00 PM ET
- Change in past 24 hours
- –
The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.