{
  "opencollection": "1.0.0",
  "info": {
    "name": "API Reference agentic-search > agenticSearch search-metadata-filter API",
    "version": "1.0.0"
  },
  "items": [
    {
      "info": {
        "name": "search-metadata-filter",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Audio Sound (with Metadata Filters)",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://api.coactive.ai/api/v0/search/metadata-filters/audio-sound",
            "headers": [
              {
                "name": "Authorization",
                "value": ""
              }
            ],
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Triggers an asynchronous search for video segments containing the specified `audio_class` (e.g., 'Music', 'Dog', 'Explosion') within the specified dataset (`dataset_id`), restricted to videos whose metadata matches every entry in `metadata_filters` (e.g., `genre = documentary`). Audio chunks are scored using the Audio Spectrogram Transformer (AST) model, which predicts confidence scores for 527 AudioSet sound classes across fixed-length audio segments extracted from ingested videos; no text embe"
        },
        {
          "info": {
            "name": "Job Result",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://api.coactive.ai/api/v0/search/metadata-filters/job/result/:run_id",
            "headers": [
              {
                "name": "Authorization",
                "value": ""
              }
            ],
            "params": [
              {
                "name": "run_id",
                "value": "",
                "type": "path"
              },
              {
                "name": "dataset_id",
                "value": "",
                "type": "query"
              }
            ]
          },
          "docs": "Job Result"
        },
        {
          "info": {
            "name": "Job Status",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://api.coactive.ai/api/v0/search/metadata-filters/job/status/:run_id",
            "headers": [
              {
                "name": "Authorization",
                "value": ""
              }
            ],
            "params": [
              {
                "name": "run_id",
                "value": "",
                "type": "path"
              },
              {
                "name": "dataset_id",
                "value": "",
                "type": "query"
              }
            ]
          },
          "docs": "Job Status"
        },
        {
          "info": {
            "name": "Text to Image (with Metadata Filters)",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://api.coactive.ai/api/v0/search/metadata-filters/text-to-image",
            "headers": [
              {
                "name": "Authorization",
                "value": ""
              }
            ],
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Triggers an asynchronous text-to-image search within the specified dataset (`dataset_id`), restricted to image assets matching every entry in `metadata_filters` (e.g., `category = sports`, `tag contains outdoor`). The `text_query` is encoded into an embedding using the dataset's configured vision-language encoder (e.g., CLIP, SigLIP, Perception Encoder) and ranked against image embeddings via vector similarity, while the metadata filters are applied as a pre-scoring constraint on the asset metad"
        },
        {
          "info": {
            "name": "Text to Keyframe (with Metadata Filters)",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://api.coactive.ai/api/v0/search/metadata-filters/text-to-keyframe",
            "headers": [
              {
                "name": "Authorization",
                "value": ""
              }
            ],
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Text to Keyframe (with Metadata Filters)"
        },
        {
          "info": {
            "name": "Text to Shot (with Metadata Filters)",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://api.coactive.ai/api/v0/search/metadata-filters/text-to-shot",
            "headers": [
              {
                "name": "Authorization",
                "value": ""
              }
            ],
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Text to Shot (with Metadata Filters)"
        },
        {
          "info": {
            "name": "Text to Transcript (with Metadata Filters)",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://api.coactive.ai/api/v0/search/metadata-filters/text-to-transcript",
            "headers": [
              {
                "name": "Authorization",
                "value": ""
              }
            ],
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Triggers an asynchronous transcript search within the specified dataset (`dataset_id`), restricted to videos whose metadata matches every entry in `metadata_filters` (e.g., `rating = PG`, `genre = documentary`). When `match_mode=\"semantic\"`, the `text_query` is encoded with the dataset's configured audio/transcript encoder (e.g., sentence transformers, Qwen) and ranked against transcript embeddings via vector similarity. When `match_mode=\"exact\"`, no embedding is computed and the raw `text_query"
        },
        {
          "info": {
            "name": "Text to Video (with Metadata Filters)",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://api.coactive.ai/api/v0/search/metadata-filters/text-to-video",
            "headers": [
              {
                "name": "Authorization",
                "value": ""
              }
            ],
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Triggers an asynchronous text-to-video search within the specified dataset (`dataset_id`), restricted to assets matching every entry in `metadata_filters` (e.g., `genre = musical`, `rating != PG`, `headline contains olympics`, `impressions > 1000`). The `text_query` is encoded into an embedding using the dataset's configured vision-language encoder (e.g., CLIP, SigLIP, Perception Encoder) and ranked against video keyframe embeddings via vector similarity, while the metadata filters are applied a"
        }
      ]
    }
  ],
  "bundled": true
}