Qdrant

Qdrant is an open-source vector database and vector search engine designed for high-performance similarity search on embeddings. It enables developers to store, index, and query high-dimensional vector representations produced by machine learning models, making it suitable for semantic search, recommendation, and AI-driven applications. Built in Rust, Qdrant focuses on efficiency, reliability, and scalability for production workloads.

Qdrant offers a powerful API for managing collections, payloads (metadata), and advanced filtering, allowing users to combine vector similarity with structured filtering in a single query. It supports approximate nearest neighbor (ANN) search with various indexing techniques, as well as exact search when needed for higher precision. The engine includes features such as payload indexing, filtering by conditions, sharding, replication, and distributed deployment for large-scale systems. Qdrant also provides integrations with popular machine learning frameworks and embedding providers, as well as client libraries in multiple programming languages.