Optimize Multitenant AI Apps with Flat Indexes for MongoDB Vector Search

This title was summarized by AI from the post below.
View organization page for MongoDB

911,624 followers

Building AI apps where each user has their own private data? HNSW indexes weren't designed for that; they're built for massive shared datasets, not thousands of smaller per-user collections. 💫 Introducing Flat Indexes for MongoDB Vector Search: Optimize multitenant AI apps with one parameter change, "indexingMethod": "flat", that delivers better recall, less memory overhead, and zero cross-tenant noise. Available now in Public Preview on Amazon Web Services (AWS), Google Cloud, and Microsoft Azurehttps://lnkd.in/dJW9kfjs

  • No alternative text description for this image

Trevor nailed it — HNSW at per-user granularity is a memory and recall nightmare. The flat index approach makes a lot of sense for AI apps being built in markets like Malaysia and SEA right now, where the pattern is hundreds of SME clients on a shared SaaS platform, each expecting their own AI that knows only their data. Cross-tenant bleed on vector search in those setups is a real commercial risk, not just a technical inconvenience. Flat indexing with proper partitioning solves that cleanly without rebuilding the entire infra.

Like
Reply

per tenant vector search is a real pain. tried splitting hnsw by user in pgvector and the build cost ate me alive. flat might actually be the move

Like
Reply

Veena C. + Chris Kabat ^ just saw this and thought about our conversation yesterday.

See more comments

To view or add a comment, sign in

Explore content categories