Qdrant

Qdrant is a vector database: embeddings go into a collection with a JSON payload stored beside each one, and a search endpoint returns the nearest neighbours of a query vector.

Authentication

• API key

Actions

Generic API request. Call any Qdrant API endpoint on this connection, for the case where no shipped action covers it yet. The connection supplies the base URL, the authentication and the egress route, so only the path, query and body are yours to fill.

• Delete pointsDestructiveRemove specific vectors from a Qdrant collection by their point ids — the way to retract documents from a vector index without rebuilding the collection.
• Get collectionRetrieve a collection's status and configuration (GET /collections/{collection}).
• Get pointRead one vector from a Qdrant collection by its point id — use it to inspect the payload metadata stored alongside a vector, or to confirm an upsert landed.
• List collectionsList all collections in the Qdrant instance (GET /collections).
• Scroll pointsDestructivePage through points in a collection without a query vector (POST /collections/{collection}/points/scroll).
• Search pointsFind the nearest points to a query vector in a collection (POST /collections/{collection}/points/search).
• Upsert pointsDestructiveInsert or update points (vectors + payloads) in a collection (PUT /collections/{collection}/points).

Product names, logos and brands are the property of their respective owners and are used here for identification only. Their use does not imply endorsement by, or affiliation with, those owners.