datastores.ai
Qdrant

Qdrant

Open SourceRust

High-performance vector search engine in Rust

Categoryopen-sourceLanguageRustLicenseApache-2.0Websiteqdrant.tech

About Qdrant

Qdrant is an open-source vector database and similarity search engine written in Rust, optimized for high performance and scalability. It provides efficient indexing, filtering, and retrieval of vector embeddings, making it suitable for AI applications such as semantic search, recommendation systems, and retrieval-augmented generation. Qdrant supports both self-hosted and managed cloud deployments and offers strong metadata filtering capabilities alongside vector search. Its Rust-based architecture delivers fast query performance and efficient memory usage, making it a popular choice for production AI workloads.

Key features

Written in Rust for speed
Rich payload filtering
Multiple distance metrics
Quantization support
Distributed deployment
gRPC & REST APIs

Pricing

Open SourceFree
Self-hosted
Cloud (Free)$0
1GB cluster
Cloud (Standard)From ~$15/mo
 
EnterpriseCustom
 

Common use cases

Similarity search
Neural search
Matching engines
RAG applications

Common questions about Qdrant

Is Qdrant free to use?

Yes, Qdrant is open source under the Apache-2.0 license. You can self-host it at no licensing cost, though you'll need to manage infrastructure and operational costs.

Can I get support for Qdrant?

Qdrant has community support through documentation, forums, and GitHub issues. Some open-source databases also offer commercial enterprise support contracts.

What are the main use cases for Qdrant?

Qdrant is commonly used for similarity search, neural search, matching engines, and similar applications requiring semantic similarity search.

Does Qdrant integrate with popular AI tools?

Most vector databases integrate with LangChain, LlamaIndex, and popular embedding providers. Check the Qdrant documentation for specific integration guides and examples.

Comparisons featuring Qdrant

Not sure if Qdrant is right for you?

Compare it side-by-side with other vector databases to find the best fit for your project.