# Qdrant — High-Performance Vector Database

> Vector database and search engine for AI applications. Handles billion-scale similarity search with filtering, sparse vectors, and multi-tenancy. Rust-powered. 30K+ stars.

## Install

Save in your project root:

## Quick Use

```bash
# Run with Docker
docker run -p 6333:6333 qdrant/qdrant

# Or install Python client
pip install qdrant-client
```

```python
from qdrant_client import QdrantClient
from qdrant_client.models import Distance, VectorParams, PointStruct

client = QdrantClient("localhost", port=6333)
client.create_collection("docs", vectors_config=VectorParams(size=384, distance=Distance.COSINE))

client.upsert("docs", points=[
    PointStruct(id=1, vector=[0.1]*384, payload={"title": "AI Guide"}),
])

results = client.query_points("docs", query=[0.1]*384, limit=5)
```

---

## Intro

Qdrant is a high-performance vector database and similarity search engine built in Rust. Designed for production AI applications — RAG pipelines, semantic search, recommendation systems, and anomaly detection. Supports dense and sparse vectors, payload filtering, multi-tenancy, and horizontal scaling. Available as self-hosted (Docker/binary) or managed cloud. 30,000+ GitHub stars.

**Best for**: Production RAG, semantic search, recommendation engines, and any app needing vector similarity
**Works with**: LangChain, LlamaIndex, Haystack, OpenAI, Cohere, any embedding model

---

## Key Features

### Performance
- **Rust-powered** — written in Rust for maximum speed and memory safety
- **Billion-scale** — handles billions of vectors with quantization and sharding
- **HNSW indexing** — fast approximate nearest neighbor search

### Advanced Search
- **Hybrid search** — combine dense vectors with sparse vectors (BM25-style)
- **Payload filtering** — filter results by metadata alongside vector similarity
- **Multi-vector** — store multiple vectors per point (e.g., title + content embeddings)

### Production Features
- **Multi-tenancy** — isolate data per customer within one collection
- **Snapshots** — backup and restore collections
- **Horizontal scaling** — distributed mode with sharding and replication
- **REST + gRPC** APIs

### Integrations
LangChain, LlamaIndex, Haystack, Spring AI, AutoGen, CrewAI, and 50+ frameworks.

---

### FAQ

**Q: What is Qdrant?**
A: A Rust-powered vector database for AI applications. Handles billion-scale similarity search with filtering, sparse vectors, and multi-tenancy. 30K+ GitHub stars.

**Q: Is Qdrant free?**
A: Open-source under Apache 2.0 for self-hosting. Qdrant Cloud offers a managed service with a free tier (1GB).

---

## Source & Thanks

> Created by [Qdrant](https://github.com/qdrant). Licensed under Apache 2.0.
> [qdrant/qdrant](https://github.com/qdrant/qdrant) — 30,000+ GitHub stars

---
Source: https://tokrepo.com/en/workflows/1566710d-f5ed-46da-af8c-757475a10420
Author: AI Open Source