A high performance open source vector similarity search engine and database, with a built in dashboard.
Qdrant is a high performance open source vector similarity search engine and vector database, written in Rust for speed and reliability under heavy load. It stores points made of a vector and a JSON payload, indexes them with HNSW, and answers nearest neighbour, filtered and hybrid search queries in milliseconds through a clean REST and gRPC API, with official client libraries for Python, JavaScript, Rust, Go and more.
It suits any team building semantic search, recommendations, retrieval augmented generation or anomaly detection that wants a fast vector database they run and own inside their own cloud account rather than a hosted service.
The cloudimg image installs Qdrant from the official release behind an nginx reverse proxy that binds the engine to loopback and terminates TLS, so the REST and gRPC API and the built in dashboard are reachable securely within minutes. Security is enforced from the first request: a unique API key is generated on each virtual machine's first boot and written to a root only file, and the service is configured to refuse to start without one, so there is no open unauthenticated API and no shared credential in the image. Vector data lives on a dedicated data disk. The paired deployment guide covers reading your key, creating a collection, upserting vectors, running your first search and enabling a real TLS certificate, and every deployment carries 24/7 support.
Real screenshots taken while testing this image against its deployment guide.