LEANN open-source vector index shrinks a 60M-chunk RAG index to 6 GB
Original title: Meet LEANN: An Open-Source Vector Index that Shrinks a 60M-Chunk RAG Index from 201 GB to 6 GB
The only stated figure is a drop from 201 GB to 6 GB; no method or benchmark details were in the feed.
LEANN is presented as an open-source vector index that compresses a retrieval-augmented generation index of 60 million chunks from 201 GB to 6 GB. The supplied page text is a cookie notice and does not describe the index design, authors, or evaluation.
Unconfirmed: The size claim appears only in the headline; the article body was not included, so the result is unverified here.
- The claimed corpus is a 60 million chunk RAG index.
- The stated footprint falls from 201 GB to 6 GB.
- Products
- LEANN
From the original article
14 min read at marktechpost.comUC Berkeley’s LEANN vector index stores a pruned graph and recomputes embeddings at query time. It matches HNSW accuracy at 90% recall using 4 GB instead of 188 GB, at the cost of seconds-level search. The post Meet LEANN: An Open-Source Vector Index that Shrinks a 60M-Chunk RAG Index from 201 GB to 6 GB appeared first on MarkTechPost.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.