> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getcatalog.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Agentic Search Mini

> Fast synchronous search returning up to 10 products. Optional AI-powered attribute enrichment.

<Tip>
  **When to use:** Ideal for autocomplete, quick previews, or when you need fast AI-enriched results with a small result set. For larger result sets with customer profile personalization, use [`POST /v2/agentic-search`](/v2/api-reference/endpoints/search/agentic-search).
</Tip>

## Request

<ParamField header="x-api-key" type="string" required>
  Your API key for authentication.
</ParamField>

### Request Body

<ParamField body="query" type="string" required>
  Natural language search query for product discovery

  **Examples:**

  * `"sustainable midi dresses"`
  * `"luxury minimalist handbags"`
  * `"versatile blazers for work"`
</ParamField>

<ParamField body="enable_enrichment" type="boolean" default="true">
  Enable AI-powered product attribute enrichment for enhanced product data analysis. Set to `false` for faster response times if detailed attributes are not needed.

  **When to disable enrichment:**

  * You need the fastest possible response times
  * You only need basic product information (title, price, URL)
  * You're building a real-time autocomplete feature

  **When to enable enrichment (default):**

  * You need detailed product attributes (color, material, features)
  * You're building product comparison tools
  * You need rich product data for AI-powered recommendations
</ParamField>

## Response

<ResponseField name="data" type="array">
  Array of discovered products with enriched data (up to 10 results).

  <Expandable title="Product Object" defaultOpen>
    <ResponseField name="url" type="string">
      Product URL (normalized and cleaned)
    </ResponseField>

    <ResponseField name="product" type="object">
      Product details

      <Expandable title="Product Properties" defaultOpen>
        <ResponseField name="title" type="string">
          Product title
        </ResponseField>

        <ResponseField name="price" type="object">
          Price information

          <Expandable title="Price Properties">
            <ResponseField name="current_value" type="number">
              Current product price as a number (e.g., 99.99)
            </ResponseField>

            <ResponseField name="compare_at_value" type="number | null">
              Original/compare-at price if on sale, otherwise `null`
            </ResponseField>

            <ResponseField name="currency" type="string">
              Currency code (e.g., `"USD"`)
            </ResponseField>
          </Expandable>
        </ResponseField>

        <ResponseField name="description" type="string">
          Product description
        </ResponseField>

        <ResponseField name="images" type="array">
          Array of product image URLs
        </ResponseField>

        <ResponseField name="attributes" type="object">
          Product attributes when AI enrichment is enabled.
        </ResponseField>

        <Expandable title="Attributes object">
          Key-value object from AI enrichment. Structure is product-dependent; no fixed schema. May include semantic attributes (e.g. style, material, occasion) and other enriched fields.
        </Expandable>
      </Expandable>
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="pagination" type="object">
  Pagination metadata for the results

  <Expandable title="Pagination Properties">
    <ResponseField name="page" type="number">
      Current page number (always 1 for this endpoint)
    </ResponseField>

    <ResponseField name="page_size" type="number">
      Number of items per page (equals the number of products returned)
    </ResponseField>

    <ResponseField name="total_items" type="number">
      Total number of products returned (may be less than 10 if some products couldn't be processed)
    </ResponseField>

    <ResponseField name="total_pages" type="number">
      Total number of pages (always 1 for this endpoint)
    </ResponseField>

    <ResponseField name="has_next" type="boolean">
      Whether there is a next page (always false for this endpoint)
    </ResponseField>

    <ResponseField name="has_prev" type="boolean">
      Whether there is a previous page (always false for this endpoint)
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="meta" type="object">
  Response metadata

  <Expandable title="Meta Properties">
    <ResponseField name="request_id" type="string" optional>
      Unique request identifier for support purposes. Also available in the `Request-ID` response header.
    </ResponseField>
  </Expandable>
</ResponseField>

## Response Schema and Enable Flags

The `/v2/agentic-search-mini` endpoint maintains a consistent response schema regardless of `enable_*` flag values. All fields are always present in product objects returned in the `data` array, but will be `null` when the corresponding flag is `false`.

**Field Mappings:**

| Flag                | Affected Fields                                                                            | Behavior When `false` |
| :------------------ | :----------------------------------------------------------------------------------------- | :-------------------- |
| `enable_enrichment` | `attributes`, `product_type`, `google_product_category_id`, `google_product_category_path` |                       |

<RequestExample dropdown>
  ```powershell cURL theme={null}
  curl -X POST https://api.getcatalog.ai/v2/agentic-search-mini \
    -H "Content-Type: application/json" \
    -H "x-api-key: $CATALOG_API_KEY" \
    -d '{
      "query": "sustainable midi dresses",
      "enable_enrichment": true
    }'
  ```

  ```javascript JavaScript theme={null}
  const response = await fetch('https://api.getcatalog.ai/v2/agentic-search-mini', {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'x-api-key': 'YOUR_API_KEY'
    },
    body: JSON.stringify({
      query: 'sustainable midi dresses',
      enable_enrichment: true
    })
  });

  const data = await response.json();
  console.log(`Found ${data.data.length} products`);
  ```

  ```python Python theme={null}
  import requests

  response = requests.post(
      'https://api.getcatalog.ai/v2/agentic-search-mini',
      headers={
          'Content-Type': 'application/json',
          'x-api-key': 'YOUR_API_KEY'
      },
      json={
          'query': 'sustainable midi dresses',
          'enable_enrichment': True
      }
  )

  data = response.json()
  print(f"Found {len(data['data'])} products")
  ```
</RequestExample>

<ResponseExample>
  ```json Success Response theme={null}
  {
    "data": [
      {
        "url": "https://bysonqo.com/products/floral-crochet-organic-cotton-dress-sustainable-party-top",
        "product": {
          "title": "Organic Cotton Floral Crochet Dress",
          "price": {
            "current_value": 733.6,
            "compare_at_value": null,
            "currency": "USD"
          },
          "description": "",
          "images": [
            [
              "https://encrypted-tbn2.gstatic.com/shopping?q=tbn:ANd9GcQPlPfCKoRew2h3A9Xi54Wm1xfod5UhOVbLvgHtCW7m02kRkqYKg_IgyVrZ_-AZyT-AFivJYE3I0fMKhzQ3zDZCExx1K1UVxJ68QLeIqljZ"
            ]
          ],
          "attributes": {
            "product_name": "Floral Crochet Organic Cotton Dress",
            "material": "100% Peruvian Organic Cotton",
            "certifications": "GOTS, USDA",
            "origin": "Handmade in Peru",
            "design": "Crochet midi dress",
            "measurements": "Hips: 36.22 inches (92 cm), Length: 40.55 inches (103 cm)",
            "available_sizes": "S, M",
            "available_colors": "Ivory, Black, Pink, Red, Orange, Gray, Light Blue, Light Green, Light Violet",
            "care_instructions": "Hand wash with shampoo",
            "production_time": "4-6 days"
          }
        }
      },
      ...
    ],
    "pagination": {
      "page": 1,
      "page_size": 10,
      "total_items": 10,
      "total_pages": 1,
      "has_next": false,
      "has_prev": false
    },
    "meta": {}
  }
  ```
</ResponseExample>