Qdrant (Vector Search)
Qdrant is an open-source vector database used by Quark Commerce for AI-powered semantic search and product recommendations. Instead of relying solely on keyword matching, vector search understands the meaning behind search queries and finds semantically similar products using embeddings.
Navigate to Settings → Qdrant.
What Is It For?
Qdrant stores product embeddings — numerical vector representations of product data generated by AI models. This enables:
- Semantic product search — customers can search using natural language (e.g., "comfortable summer dress") and get relevant results even if exact keywords don't match
- Product recommendations — "similar products" and "you might also like" suggestions based on vector similarity
- AI-assisted catalog features — powering intelligent product discovery across the storefront
Connection Status
The top panel shows the current connection health:
- Status — Connected or Disconnected
- Qdrant Version — the running version of the Qdrant instance
- Collections — number of vector collections stored
Click Refresh to reload the connection telemetry.
Configuration
Connection Settings
| Field | Description | Required |
|---|---|---|
| URL | The Qdrant instance URL (e.g., https://localhost:6333 or your Qdrant Cloud URL) | Yes |
| API Key | Authentication key, required for Qdrant Cloud deployments | For Cloud |
| gRPC Port | Port for gRPC communication (1–65535) | No |
Actions
- Save Settings — persist the connection configuration
- Test Connection — verify connectivity and display telemetry details (version, collection count)
tip
For local development, Qdrant typically runs on http://localhost:6333 with no API key. For production Qdrant Cloud deployments, you'll need the cluster URL and an API key from your Qdrant Cloud dashboard.