NAME
    gcloud beta vector-search collections data-objects batch-search - batch
        search data objects from a Vector Search collection

SYNOPSIS
    gcloud beta vector-search collections data-objects batch-search
        --collection=COLLECTION --location=LOCATION
        --searches-from-file=SEARCHES_FROM_FILE
        [[--rrf-weights=[WEIGHT,...]
          : --combine-output-data-fields=[DATA_OUTPUT_FIELD,...]
          --combine-output-metadata-fields=[METADATA_OUTPUT_FIELD,...]
          --combine-output-vector-fields=[VECTOR_OUTPUT_FIELD,...]
          --combine-top-k=COMBINE_TOP_K]] [GCLOUD_WIDE_FLAG ...]

DESCRIPTION
    (BETA) Batch search data objects from a Vector Search collection. Searches
    can be specified in a JSON file via --searches-from-file.

EXAMPLES
    To batch search data objects from collection my-collection in location
    us-central1 using searches defined in searches.json, run:

        $ gcloud beta vector-search collections data-objects batch-search \
            --collection=my-collection --location=us-central1 \
            --searches-from-file=searches.json

    Example searches.json:

        [
          {
            "semanticSearch": {
              "searchText": "sci-fi movie",
              "searchField": "vector1",
              "topK": 10
            }
          },
          {
            "vectorSearch": {
              "searchField": "vector2",
              "topK": 5,
              "vector": { "values": [0.1, 0.2, 0.3] }
            }
          }
        ]

REQUIRED FLAGS
     --collection=COLLECTION
        The collection to batch search data objects from.

     --location=LOCATION
        Location of the collection.

     --searches-from-file=SEARCHES_FROM_FILE
        Path to a JSON file containing a list of searches. Each element in list
        should be a JSON object representing a Search message, e.g.,
        {"semanticSearch": {"searchText": "...", "searchField": "..."}}. Keys
        must be camelCase as in API definition. Example file content:

            [
              {
                "vectorSearch": {
                  "vector": {
                    "values": [
                      1,
                      2,
                      3,
                      4
                    ]
                  },
                  "searchField": "genre_embedding",
                  "topK": 10,
                  "outputFields": {
                    "dataFields": [
                      "director",
                      "genre",
                      "title",
                      "year"
                    ]
                  }
                }
              },
              {
                "semanticSearch": {
                  "searchText": "sci-fi movie",
                  "searchField": "plot_embedding",
                  "taskType": "SEMANTIC_SIMILARITY",
                  "topK": 10
                }
              },
              {
                "textSearch": {
                  "searchText": "movie 1",
                  "dataFieldNames": ["title"],
                  "topK": 10
                }
              }
            ]

OPTIONAL FLAGS
     Combine Results Options

     Ranker

     This must be specified.

       RRF Ranker

       --rrf-weights=[WEIGHT,...]
          RRF weights for combining results.

     --combine-output-data-fields=[DATA_OUTPUT_FIELD,...]
        List of data fields to include in combined output.

     --combine-output-metadata-fields=[METADATA_OUTPUT_FIELD,...]
        List of metadata fields to include in combined output.

     --combine-output-vector-fields=[VECTOR_OUTPUT_FIELD,...]
        List of vector fields to include in combined output.

     --combine-top-k=COMBINE_TOP_K
        Top K results to return when combining results.

GCLOUD WIDE FLAGS
    These flags are available to all commands: --access-token-file, --account,
    --billing-project, --configuration, --flags-file, --flatten, --format,
    --help, --impersonate-service-account, --log-http, --project, --quiet,
    --trace-token, --user-output-enabled, --verbosity.

    Run $ gcloud help for details.

NOTES
    This command is currently in beta and might change without notice. This
    variant is also available:

        $ gcloud vector-search collections data-objects batch-search

