qdrant

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdran

What is qdrant?

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

Overview of qdrant

What it is

Qdrant (read: quadrant) is a vector similarity search engine and vector database written in Rust. It provides a production-ready service with an API to store, search, and manage points—vectors with an additional JSON payload. Qdrant is designed for extended filtering support and is used for neural-network or semantic-based matching, faceted search, and other applications. The software is available as an open-source project and also as a fully managed Qdrant Cloud service with a free tier.

Key features

  • Dense, sparse, and multi vector search
  • Filtering on payload using keyword matching, full-text, numeric ranges, geo-locations, and combined should, must, must_not clauses
  • Hybrid search combining multiple vectors with fusion strategies like Reciprocal Rank Fusion (RRF) and Distribution-Based Score Fusion (DBSF)
  • Vector quantization and on-disk storage (cuts RAM usage by up to 97%)
  • Distributed deployment with sharding and replication
  • Built-in Web UI for visual interaction and monitoring
  • GPU support for accelerated indexing (NVIDIA and AMD GPUs)

Use cases

Qdrant can be used for semantic text search, similar image search (e.g., food discovery), and e-commerce product categorization. It supports recommendation systems (using positive and negative examples), discovery (constraining search to a specific region of vector space), and multitenancy for multi-user environments. Qdrant Edge provides a lightweight version for edge devices and resource-constrained environments, synchronizing data with a Qdrant server.

Getting started

To run Qdrant locally using Docker:bashdocker run -p 6333:6333 qdrant/qdrantThis starts an insecure deployment without authentication. After starting, connect with a Python client:pythonfrom qdrant_client import QdrantClientclient = QdrantClient(url=”http://localhost:6333”)For Qdrant Edge, initialize an EdgeShard instance. See the repository README for full details.

License and pricing

Qdrant is open-source under the Apache-2.0 license. The repository does not state pricing for the open-source version; Qdrant Cloud offers a paid managed service with a free tier.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/qdrantqdrant.svg)](https://yunodb.com/tools/qdrantqdrant?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/qdrantqdrant?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/qdrantqdrant.svg" alt="Featured on YunoDB" height="20"></a>