Qdrant

Qdrant is a vector similarity search engine and vector database for AI applications. It stores, searches, and manages points made of vectors plus payload data, supporting semantic matching, faceted search, recommendations, discovery, and other neural-search workloads.

It supports dense vectors, sparse vectors, and multivector search, with JSON payload filtering for keyword matching, full-text, numeric ranges, geo-locations, and boolean clauses. Hybrid search combines multiple vectors in one query with fusion strategies such as RRF and DBSF. Qdrant also includes quantization, on-disk storage, sharding, replication, REST and gRPC APIs, and a Web UI.

Qdrant is written in Rust and has official clients for Go, Rust, JavaScript/TypeScript, Python, .NET/C#, and Java. It can run locally in a container, is available as Qdrant Cloud with a free tier, and has Qdrant Edge for running inside an application process with local storage, local queries, and sync to a Qdrant server.