Qdrant
Qdrant (read: quadrant) is a vector similarity search engine and vector database. It provides a production-ready service with a convenient API to store, search, and manage points—vectors with an additional payload Qdrant is tailored to extended filtering support.
Cost / License
- Free
- Open Source (Apache-2.0)
EUPlatforms
- Mac
- Windows
- Linux
- Self-Hosted
- Cloudron
Qdrant News & Activities
Recent activities
- fanpino commented on Qdrant
We use Qdrant as the vector store behind Research File Manager's RAG search. Easy to run in Docker alongside the rest of our stack, and the payload filtering saves us building a separate metadata index for scoping search results per user.
- fanpino liked Qdrant
totanvix added Qdrant as alternative to Elasticvix
alexandreoliveira added Qdrant as alternative to Viglet Turing- Natterjack565 updated Qdrant
- Arkath liked Qdrant
Qdrant information
Developed by
Qdrant Licensing
Open Source (Apache-2.0) and Free product.Written in
Alternatives
63 alternatives listedSupported Languages
- English
AlternativeTo Category
DevelopmentGitHub repository
- 34,177 Stars
- 2,610 Forks
- 703 Open Issues
- Updated
What is Qdrant?
Qdrant (read: quadrant) is a vector similarity search engine and vector database. It provides a production-ready service with a convenient API to store, search, and manage points—vectors with an additional payload Qdrant is tailored to extended filtering support. It makes it useful for all sorts of neural-network or semantic-based matching, faceted search, and other applications.
Qdrant is written in Rust, which makes it fast and reliable even under high load.
With Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and much more!
Qdrant is also available as a fully managed Qdrant Cloud including a free tier.
Comments and Reviews
We use Qdrant as the vector store behind Research File Manager's RAG search. Easy to run in Docker alongside the rest of our stack, and the payload filtering saves us building a separate metadata index for scoping search results per user.