Home/Vector DBs/Qdrant
Vector DBs
qdrant

Qdrant

TypeScriptPythonOpen-sourceVector DBRust

High-performance vector database written in Rust. Qdrant delivers exceptional speed and memory efficiency for large-scale vector search with a clean REST and gRPC API.

License

Apache-2.0

Language

TypeScript / Python / Rust

88
Trust
Strong

Why Qdrant?

Performance-critical vector search at scale

You want the fastest self-hostable vector DB

Memory-efficient workloads with millions of vectors

Signal Breakdown

What drives the Trust Score

npm downloads
180k / wk
Commits (90d)
200 commits
GitHub stars
21k ★
Stack Overflow
2k q's
Community
Growing fast
Weighted Trust Score88 / 100

Download Trend

Last 12 months

Tradeoffs & Caveats

Know before you commit

You need a fully managed cloud-first solution

Your team doesn't have Rust/systems experience for tuning

Simple RAG use case where Pinecone is simpler

Pricing

Free tier & paid plans

Free tier

Free open-source + 1GB free cloud

Paid

Cloud from $0.08/GB/mo

Best performance per dollar for self-hosted

Alternative Tools

Other options worth considering

pinecone
Pinecone64Fair

Managed vector database purpose-built for AI applications. Fully hosted with serverless scaling and a free tier (100k vectors). The fastest way to add semantic search or RAG to production.

weaviate
Weaviate90Excellent

Open-source vector database with built-in ML model integration. Weaviate supports hybrid search (vector + BM25), multi-tenancy, and can run fully self-hosted or managed.

elasticsearch
Elasticsearch98Excellent

The leading distributed search and analytics engine. Elasticsearch powers full-text search, log aggregation (ELK stack), and complex analytics queries at scale. Powerful but operationally complex to self-host.

Often Used Together

Complementary tools that pair well with Qdrant

langchain

LangChain

AI Orchestration

96Excellent
View
LL

LlamaIndex

AI Orchestration

82Strong
View
openai-api

OpenAI API

LLM APIs

87Strong
View
fastapi

FastAPI

Backend Frameworks

97Excellent
View
docker

Docker

DevOps & Infra

93Excellent
View

Learning Resources

Docs, videos, tutorials, and courses

Get Started

Repository and installation options

View on GitHub

github.com/qdrant/qdrant

npmnpm install @qdrant/js-client-rest
pippip install qdrant-client

Quick Start

Copy and adapt to get going fast

import { QdrantClient } from '@qdrant/js-client-rest';

const client = new QdrantClient({ url: process.env.QDRANT_URL, apiKey: process.env.QDRANT_API_KEY });

const results = await client.search('my_collection', {
  vector: [0.1, 0.2, 0.3],
  limit: 5,
});
console.log(results);

Code Examples

Common usage patterns

Create collection and upsert

Set up a collection and add vectors

await client.createCollection('docs', {
  vectors: { size: 1536, distance: 'Cosine' },
});

await client.upsert('docs', {
  points: [{ id: 1, vector: embeddings[0], payload: { text: 'Hello world' } }],
});

Filtered search

Search with metadata filters

const results = await client.search('docs', {
  vector: queryEmbedding,
  filter: { must: [{ key: 'category', match: { value: 'tech' } }] },
  limit: 10,
});

Community Notes

Real experiences from developers who've used this tool