Qdrant - BoostGPT Documentation

Collections, points and vector search. The same job as Pinecone, self-hosted.

Connecting

In the dashboard, open Connectors, find Qdrant and press Connect. The key you enter is checked against Qdrant before anything is saved, so a key that is refused never becomes a connection that fails later.

What you will need

Field	What it is
API Key	Your Qdrant API key
Qdrant URL	Your Qdrant instance URL

Getting the credential

Qdrant Cloud: Sign up and create a cluster at Qdrant Cloud
Self-hosted: Deploy Qdrant using Docker or Kubernetes
Get your cluster URL and API key (if authentication enabled)
Test connection with a simple collection creation

What an agent can do with it

Tool	What it does
`get_collections`	List all collections
`create_collection`	Create a new collection
`get_collection_info`	Get collection information
`delete_collection`	Delete a collection
`upsert_points`	Insert or update points in a collection
`search_points`	Search for similar points
`get_points`	Retrieve points by IDs
`delete_points`	Delete points from collection
`set_payload`	Set payload for points
`create_index`	Create payload index for faster filtering

Useful resources

Qdrant documentation