Hybrid Search

Example

export MILVUS_URI="localhost:19530"

curl --location --request POST "http://${MILVUS_URI}/v2/vectordb/entities/search" \
--header "Content-Type: application/json" \
--data-raw '{
    "collectionName": "quick_setup",
    "data": [
        [0.3580376395471989, -0.6023495712049978, 0.18414012509913835, -0.26286205330961354, 0.9029438446296592]
    ],
    "annsField": "vector",
    "limit": 3,
    "outputFields": [
        "color"
    ]
}'

Possible response is similar to the following.

{
    "code": 0,
    "data": [
        {
            "color": "pink_8682",
            "distance": 1,
            "id": 0
        },
        {
            "color": "red_7025",
            "distance": 0.6290165,
            "id": 1
        },
        {
            "color": "red_4794",
            "distance": 0.5975797,
            "id": 4
        }
    ]
}

Request

Parameters

• Header parameters

  Parameter	Description
  Request-Timeout	integer The timeout duration for this operation. Setting this to None indicates that this operation timeouts when any response arrives or any error occurs.
  Authorization	string The authentication token.

• No query parameters required

• No path parameters required

Request Body

{
    "dbName": "string",
    "collectionName": "string",
    "partitionNames": [],
    "search": [
        {
            "data": [],
            "annsField": "string",
            "filter": "string",
            "groupingField": "string",
            "metricType": "string",
            "limit": "integer",
            "offset": "integer",
            "ignoreGrowing": "boolean",
            "params": {
                "radius": "integer",
                "range_filter": "integer"
            }
        }
    ],
    "rerank": "string",
    "limit": "integer",
    "outputFields": []
}

Parameter	Description
dbName	string The name of the database.
collectionName *	string The name of the collection to which this operation applies.
partitionNames	array The name of the partitions to which this operation applies.
partitionNames[]	string PartitionName
search	array
search[]	object The parameter settings specific to this operation.
search[][].data	array A list of vector embeddings.MilvusZilliz Cloud searches for the most similar vector embeddings to the specified ones.
search[][].data[]	number A vector embedding
search[].annsField	string
search[].filter	string
search[].groupingField	string
search[].metricType	string The name of the metric type that applies to the current search. The value should be the same as the metric type of the target collection. The value defaults to COSINE
search[].limit	integer
search[].offset	integer
search[].ignoreGrowing	boolean
search[].params	object Extra search parameters.
search[].params.radius	integer Determines the threshold of least similarity. When setting metric_type to L2, ensure that this value is greater than that of range_filter. Otherwise, this value should be lower than that of range_filter.
search[].params.range_filter	integer Refines the search to vectors within a specific similarity range. When setting metric_type to IP or COSINE, ensure that this value is greater than that of radius. Otherwise, this value should be lower than that of radius.
rerank *	string
limit	integer The total number of entities to return. You can use this parameter in combination with offset in param to enable pagination. The sum of this value and offset in param should be less than 16,384.
outputFields	array An array of fields to return along with the search results.
outputFields[]	string A field name

Response

Returns the search results.

Response Bodies

• Response body if we process your request successfully

{
    "code": "integer",
    "data": [
        {}
    ]
}

• Response body if we failed to process your request

{
    "code": integer,
    "message": string
}

Properties

The properties in the returned response are listed in the following table.

Property	Description
code	integer Indicates whether the request succeeds. 200: The request succeeds. Others: Some error occurs.
message	string Indicates the possible reason for the reported error.
data	array
data[]	object