Qdrant
High-Performance Vector Search Engine for Production-Grade AI Search
Qdrant is an open-source vector search engine written in Rust, designed for fast and scalable similarity search at any scale. It supports hybrid search (dense + sparse vectors), metadata filtering, multitenancy, quantization, and real-time indexing. It can be self-hosted or deployed via Qdrant Cloud, integrating with popular AI frameworks for use cases like RAG, semantic search, and recommendation systems.
Qdrant stores vectors alongside metadata in a custom Rust-based storage engine with HNSW indexing, enabling sub-millisecond similarity search with advanced filtering, hybrid search, and quantization via REST or gRPC APIs.
AI engineers and developers building production-grade search and retrieval systems
Background.
- Status
- launched
- Business model
- freemium
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.