qdrant/qdrant
VECTOR DATABASE AND SEARCH ENGINE
Qdrant is a vector database and semantic search engine written in Rust. Stores vectors with payload, supports filtering, and works in both client-server and embedded modes.
// KEY FEATURES
- Written in Rust for high performance under load
- Supports extended filtering on vector payload fields
- Includes embedded Qdrant Edge mode for edge devices
- Official clients for Python, Go, Rust, JS, Java, .NET
// DEEP DIVE: HOW IT WORKS
Qdrant works as a vector search engine: accepts embeddings with metadata (payload), indexes them via HNSW, and answers k-NN queries with filtering on payload fields. Runs as a Docker container on port 6333, providing gRPC and REST APIs. Data is stored on disk in collections with configurable vector parameters and distance metrics.
Written in Rust, giving speed and memory safety without GC pauses. Distinguished by embedded Qdrant Edge mode — a library running inside the application process without a separate server, with local storage and ability to sync with a cloud cluster. Cloud version Qdrant Cloud available with a free tier. Supports hybrid search, quantization, sharding, and multi-tenancy via Agent Skills.
Production requires authentication and TLS setup (container runs unsecured by default). Minimum hardware requirements not specified, but Edge version targets constrained resources. Needs Docker or ability to compile Rust binary. Client libraries cover major backend languages.
// USE CASES
Best for: For ML engineers and backend developers building semantic search and RAG
- Create semantic text search with metadata filtering
- Run vector search on edge devices offline via Qdrant Edge
- Integrate vector database into RAG pipeline with any of 6 official clients
// QUICK START
docker run -p 6333:6333 qdrant/qdrant
from qdrant_client import QdrantClient
client = QdrantClient(url="http://localhost:6333")Commands are taken from the repository README — check the current version on GitHub before running.
New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram