Case Study Deskcasestudydesk.com
AI SoftwareSourced

Case Study: Dust scales to 5,000+ data sources and sub-second queries with Qdrant

Dust Case StudySourced & dated by Case Study Desk
Key facts · TL;DR
Company
Dust
Industry
AI Software
Challenge
Vector infrastructure straining at scale
Headline result
Query latency cut from 5–10s to under a second

Key results

5–10s → <1s
Query latency in large collections
After migrating to Qdrant
5,000+
Data sources supported
4x
Lower RAM usage
From 30+ GB to a quarter of the size

The challenge

Dust, an OS for AI-native companies that lets users build AI agents on company knowledge, initially created a separate vector collection per data source. As data sources grew beyond 5,000 the approach became unsustainable: RAM consumption skyrocketed and search slowed as memory-mapped vectors spilled to disk, while the team managed nearly a thousand collections and over a million vector operations per cycle.

The solution

Dust migrated to Qdrant, consolidating its fragmented architecture into shared, multi-tenant collections with sharding and payload filtering, and adopted scalar quantization to shrink vector storage while keeping original vectors on disk for fallback.

The results, in context

Queries in large collections that once took 5 to 10 seconds now return in under a second. Collections that once consumed over 30 GB of RAM were optimized to run at a quarter of that size, and the platform scaled to support 5,000+ data sources.

Products used

Qdrant Qdrant Vector Database