What is Qdrant?

Qdrant is an open-source vector search engine and database written in Rust. It is engineered for high-performance, full-featured vector similarity search at any scale, with advanced features like metadata filtering, hybrid search, and multi-vector support. Qdrant can be deployed in various models including cloud, hybrid, private, and edge environments.

How to use Qdrant?

Start with the free tier in Qdrant Cloud to spin up a cluster in seconds. Use the intuitive REST, gRPC, or official client APIs (Python, JavaScript, etc.) to index vectors and perform similarity searches. Explore the built-in Web UI to test queries and inspect results. For production, scale to a Standard Tier or deploy on your own infrastructure with Hybrid or Private Cloud options.

Core features of Qdrant

High-performance vector search engine built in Rust with SIMD and custom storage engine (Gridstore)
Expansive metadata filters (nested, text, geo, has_vector)
Native hybrid search (dense + sparse) with BM25, SPLADE++, miniCOIL support
Built-in multi-vector support
Efficient one-stage filtering during HNSW traversal
Full-spectrum reranking (ColBERT, MMR, score boosting)
Real-time indexing and memory-efficient storage with quantization (up to 64x reduction)
Enterprise-grade security (SSO, RBAC, SOC2, HIPAA compliant)