Qdrant
High-performance open-source vector search engine
Qdrant is a Rust-based vector search engine optimized for speed and efficiency. It delivers the fastest query performance among open-source vector databases and supports advanced filtering with payload indexing.
Editor rating is our overall editorial judgment of the tool, out of 5. It is not a test score and not a user-review average. Ratings have not been re-scored since the tool was listed here. The reasons are in Best for and Pros & cons below.
Requires some technical comfort with API keys, command line, or coding. If you're new to AI, start with a chat-based tool first.
Best for
Pros & cons
✓ Pros
✗ What this won't do
Use cases
Real-time recommendation systems
Filtered semantic search
Lightweight edge AI deployments
High-throughput RAG systems
Start Qdrant with Docker
Docker runs apps in sealed boxes called containers. Run docker pull qdrant/qdrant, then start it with the quickstart's run command, which opens ports 6333 and 6334.
Create a collection
With the Python client, create a collection called test_collection for vectors of size 4 using the DOT distance. A collection is a named group of vectors.
Add points and search
Upsert six points, each with a vector and a city in its payload. Query with the vector [0.2, 0.1, 0.9, 0.7] and a limit of 3, and Qdrant returns the closest points with scores.
Look at the dashboard
Open localhost:6333/dashboard in your browser to see your collections and points. If it does not load, check that the Docker container is still running.
Compare alternatives
| Tool | Category | Editor rating | Pricing |
|---|---|---|---|
| Qdrant (current) | Vector DB | 4.5 | Free (open-source) / cloud from $25 mo |
| Pinecone | Vector DB | 4.6 | Free tier / from $20 mo |
| Weaviate | Vector DB | 4.5 | Free (open-source) / cloud from $45 mo |
| LangChain | Agent Framework | 4.6 | Free (open-source) / LangSmith from $39 mo |