Repolode
Submit
qdrant

qdrant/qdrant

Qdrant is a Rust-based vector similarity search engine and vector database with payload filtering, for semantic search and recommendation.

Open-source alternative to:Pinecone

View on GitHubWebsite
Stars
35,152
Forks
2,765
Open issues
778
Last commit
3 hours ago

What is it?

Qdrant is a vector similarity search engine and vector database. It stores points, each made of a vector plus an arbitrary JSON payload, and lets you search them by similarity while filtering on payload fields such as keywords, full text, numeric ranges and geo-locations. It is aimed at neural-network and semantic matching, faceted search, and recommendation applications built on embeddings.

The server runs as a container or as a standalone process and exposes both a REST API with an OpenAPI 3.0 specification and a gRPC interface. Official client libraries cover Go, Rust, JavaScript/TypeScript, Python, .NET and Java. A lightweight variant, Qdrant Edge, runs inside the application process for edge devices and offline use, and can sync with a server.

The engine supports dense, sparse and multivector search, hybrid search with RRF or DBSF fusion, scalar and other quantization to reduce RAM use, on-disk storage, sharding and replication, and a built-in Web UI for exploring collections.

Key features

  • 01Dense, sparse and multivector search in one engine.
  • 02Payload filtering with must, should and must_not conditions.
  • 03Hybrid search with RRF and DBSF score fusion.
  • 04Built-in quantization to reduce RAM usage.
  • 05Sharding, replication and zero-downtime collection updates.
  • 06REST and gRPC APIs with official clients in six languages.

Use cases

  • Building semantic text search over embeddings from a language model.
  • Image or product similarity search in e-commerce.
  • Recommendation features based on positive and negative example points.
  • Running vector search on edge devices with offline support via Qdrant Edge.

Quick start

  1. 1

    Run the Qdrant server with Docker

    docker run -p 6333:6333 qdrant/qdrant
  2. 2

    Connect to the server with the Python client

    from qdrant_client import QdrantClient client = QdrantClient(url="http://localhost:6333")

Things to know

  • The Docker command starts an insecure deployment with no authentication, open to all network interfaces; you must secure it before production use.

Topics

#vector-database#vector-search#semantic-search#embeddings#hnsw#rust#similarity-search#ai-search#ai-search-engine#embeddings-similarity

FAQ

What is qdrant?
Qdrant is a Rust-based vector similarity search engine and vector database with payload filtering, for semantic search and recommendation. Qdrant is a vector similarity search engine and vector database. It stores points, each made of a vector plus an arbitrary JSON payload, and lets you search them by similarity while filtering on payload fields such as keywords, full text, numeric ranges and geo-locations. It is aimed at neural-network and semantic matching, faceted search, and recommendation applications built on embeddings.
Is qdrant free to use? What license does it have?
qdrant is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is qdrant still maintained?
Actively maintained. The last commit to qdrant was on Oct 20, 2026.
What can I use qdrant for?
Building semantic text search over embeddings from a language model. Image or product similarity search in e-commerce. Recommendation features based on positive and negative example points. Running vector search on edge devices with offline support via Qdrant Edge.
How do I install qdrant?
Run the Qdrant server with Docker: docker run -p 6333:6333 qdrant/qdrant Connect to the server with the Python client: from qdrant_client import QdrantClient client = QdrantClient(url="http://localhost:6333")
Where can I get qdrant?
The source code and installation instructions are on GitHub: https://github.com/qdrant/qdrant

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects