# Indexing sparse vectors with Turso

DevFeed: [Indexing sparse vectors with Turso](<https://devfeed.tech/articles/indexing-sparse-vectors-with-turso-5976.md>)

Original publisher: [Read original article](<https://turso.tech/blog/indexing-sparse-vectors-with-turso>)

Author: Nikita Sivukhin

Published: 2025-11-05T00:00:00Z

Content type: article

Language: en

Sources: [Turso Blog](<https://devfeed.tech/sources/turso-blog.md>)

Topics: [AI search](<https://devfeed.tech/topics/ai-search.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [database](<https://devfeed.tech/tags/database.md>), [search](<https://devfeed.tech/tags/search.md>), [storage](<https://devfeed.tech/tags/storage.md>), [turso](<https://devfeed.tech/tags/turso.md>), [vector](<https://devfeed.tech/tags/vector.md>)

## AI overview

Turso 0.3.0 introduces sparse-vector storage and specialized indexing for approximate nearest-neighbor search using Weighted Jaccard distance. The article reports 5-50x lower storage use and a 21% approximate-search speedup.

## Source excerpt

Turso 0.3.0 adds sparse vector indexing with Weighted Jaccard distance, delivering 5 to 50x space savings and 21% faster approximate search over dense vectors.