Skip to content
OpenSourceSoftware.ai
Qdrant logo

Qdrant

qdrant · Databases

GitHub stars

35,279
—Awaiting first sync

Awaiting first sync

No measured star history yet

What is Qdrant?

Qdrant turns embeddings from AI models into searchable data. It is the storage and retrieval layer behind many semantic search, recommendation and retrieval-augmented generation systems, built for speed and reliability under load.

Qdrant is an open-source vector similarity search engine and vector database written in Rust. It stores vectors with payloads, supports extensive filtering for semantic and faceted search, and offers official clients for Python, JavaScript, Go, Rust, Java and .NET. It can be self-hosted or used in Qdrant Cloud.

Core capabilities

  • Store and search embeddings with attached payloads through a convenient API.
  • Combine vector search with rich filtering for semantic and faceted search.
  • Run it from a container, in Qdrant Cloud, or embedded on edge devices with Qdrant Edge.

Clients and deployment options

Official clients cover Go, Rust, JavaScript and TypeScript, Python, .NET and Java. Qdrant runs as a container on your own infrastructure, as the managed Qdrant Cloud with a free tier, or as Qdrant Edge inside resource-constrained devices.

  • Clients
  • Docker
  • Apache-2.0

Where it fits

Use cases

  1. 01

    Give an AI assistant your documents

    Embed a client's documents, store them in Qdrant, and retrieve the most relevant passages for each question in a retrieval-augmented generation pipeline.

  2. 02

    Build semantic product search

    Search a catalogue by meaning rather than exact keywords, and narrow results with filters on price, category or availability.

  3. 03

    Power recommendations

    Find items similar to those a user liked by comparing their vectors, with filters to exclude what they have already seen.