Favorite
Discover
Collections

No collections

Log in
CollectionsDiscoverLibraryLog in
Discover/qdrant/qdrant: Qdrant - High-performance, massive-scale Vecto…
|Link
Open original
qdrant/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/
↗Link
Ggithub.com

qdrant/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/

  • Qdrant is a Rust-based vector database and similarity search engine for AI applications.
  • It stores and searches vectors along with additional JSON payloads, with strong support for filtering.
  • It is designed for semantic matching, faceted search, recommendations, and other neural-network-based use cases.
  • Qdrant offers a production-ready service with REST and gRPC APIs.
  • It supports dense, sparse, and multivector search, including late-interaction models like ColBERT.
  • Hybrid search combines semantic and keyword signals using fusion strategies such as RRF and DBSF.
  • Built-in vector quantization can reduce RAM usage by up to 97% while trading off speed and precision.
  • Qdrant supports distributed deployment with sharding, replication, and zero-downtime collection resizing.
  • Qdrant Cloud provides a fully managed version of the database, including a free tier.
  • Qdrant Edge runs inside the application process for low-latency, offline, resource-constrained environments.

Your notes

Save this item to your library to add private notes.

AI Summary

Qdrant is a Rust vector DB for semantic, hybrid, dense/sparse/multivector search with payload filtering, APIs, quantization, and cloud/edge support.

Collection

Ask about this item

Tags

#hybrid-search#ai-applications#distributed-systems#machine-learning-infrastructure#semantic-search#search-engines#vector-databases#cloud-services#embeddings#data-indexing
✦5 left