v17

latestOpenAPI 3.0.1Apache 2.0raw.githubusercontent.com2026-05-2575397522.8 KB

Search points

Retrieve closest points based on vector similarity and given filtering conditions

post/collections/{collection_name}/points/search

Path parameters

collection_namestring required

Name of the collection to search in

Query parameters

integer

'majority' | 'quorum' | 'all'

majority - send N/2+1 random request and return points, which present on all of them
quorum - send requests to all nodes and return points which present on majority of nodes
all - send requests to all nodes and return points which present on all nodes

Define read consistency guarantees for the operation

timeoutinteger

If set, overrides global timeout for this request. Unit is seconds.

Request body

limitinteger required

Max number of result to return

offsetinteger nullable

Offset of the first result to return. May be used to paginate results. Note: large offset values may cause performance issues.

score_thresholdnumber float nullable

Define a minimal score threshold for the result. If defined, less similar results will not be returned. Score of the returned result might be higher or smaller than the threshold depending on the Distance function used. E.g. for cosine similarity only higher scores will be returned.

Response

successful operation

timenumber float

Time spent to process this request

statusstring

Example response

{
  "time": 0.002,
  "status": "ok",
  "result": [
    {
      "id": 42,
      "version": 3,
      "score": 0.75,
      "payload": {
        "city": "London",
        "color": "green"
      },
      "vector": [
        0.875,
        0.140625,
        0.897599995136261
      ],
      "shard_key": "region_1",
      "order_value": 42
    }
  ]
}