qdrant.tech

Create and restore Qdrant collection snapshots for backup (POST /collections/{name}/snapshots, PUT .../snapshots/recover)

Delete Qdrant points by IDs or by filter (POST /collections/{name}/points/delete) and delete a whole collection (DELETE /collections/{name})

Get similar-item recommendations from Qdrant using the recommend query type with positive/negative examples

Run a Qdrant hybrid search combining dense and sparse vectors with prefetch + RRF fusion via the Query API

Filter Qdrant vector search results by payload conditions (must/should/must_not, match/range) inside a Query API request

Run nearest-neighbor vector search in Qdrant with the universal Query API (POST /collections/{collection_name}/points/query)

Retrieve Qdrant points by ID and scroll/paginate all points (POST /collections/{name}/points, POST /collections/{name}/points/scroll)

Secure a Qdrant instance with API-key authentication (service.api_key config/env, api-key header, read-only key)

Create a Qdrant payload index to speed up filtered search via PUT /collections/{collection_name}/index

Upsert points with vectors and payloads into Qdrant via PUT /collections/{collection_name}/points

Create a Qdrant collection with a given vector size and distance metric via PUT /collections/{collection_name}

Run a local Qdrant instance for development with Docker (ports 6333 REST / 6334 gRPC, persistent volume, health check)