Loading page
Loading page
Database tools · Pinecone alternative
Store embeddings and run fast similarity search with filters, for semantic search, RAG and recommendations.
Qdrant is a vector database and similarity search engine written in Rust. You store points, which are vectors with an attached JSON payload. Then you search for the nearest vectors and filter on the payload in the same query.
It supports dense vectors for meaning, sparse vectors for keyword-style search, and several vectors per object. Hybrid search mixes them. You talk to it over REST or gRPC, or through an official client library.
Qdrant suits developers building AI features: retrieval for chatbots, semantic search, recommendations and deduplication. It also suits teams that want one search service that can filter by business fields, not only by similarity.
Managed vector databases usually charge by stored vectors or by usage. A self-hosted Qdrant runs on your own service, and your embeddings stay with your other data.
The trade-off is that you size and run it. Large collections need memory and disk, so plan for growth. You look after updates, snapshots and backups. The template uses the latest image, so read the release notes before you redeploy. Read the Qdrant security guide before you put real data in it.
Containers: qdrant/qdrant:latest
Step 1
Choose the Starter plan. It costs $20 a month and runs up to 3 apps.
Step 2
Open App templates in the dashboard, choose Qdrant, and click Deploy. We set up the containers, secrets and domain.
Step 3
Wait a few minutes for the first deploy, then open your new URL and finish the Qdrant setup screen.