> For the complete documentation index, see [llms.txt](https://olddocs.frenzy.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://olddocs.frenzy.ai/response/response-object.md).

# Response Object

## Response Object

| Key                | Type     | Value                                                                                                                                                               |
| ------------------ | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Request Identifier | `string` | JSON object where the key is the attribute (e.g. color) of the product, and value is a JSON object which contains the description and confidence of the prediction. |

### Predicted Attributes

The predicted attributes will be JSON object of the following format

| Key         | Type         | Value                             |
| ----------- | ------------ | --------------------------------- |
| description | `JSON Array` | Array of all the predicted values |
| prob        | `String`     | Confidence of prediction          |

### Example 

CASE 1: Multiple-Object Image without Webhook endpoint

```python
{
  "123": {
    "Products": [
      {
        "bounding_box": [76.27632141113281,152.2967987060547,859.9697875976562,1097.4202880859375],
        "category": {"description": ["dresses"],"prob": "0.67"},
        "style": {"description": ["slip dress"],"prob": "0.87"},
        "color": {"description": ["brown"],"prob": "0.25"},
        ...
      },
      {
        "bounding_box": [[124.05464935302734,585.519775390625,376.329345703125,824.7747802734375]],
        "category": {"description": ["bags"],"prob": "0.95"},
        "style": {"description": ["clutches"],"prob": "0.87"},
        "color": {"description": ["black"],"prob": "0.25"},
        ...
      }
    ]
  }
}
```

CASE 2: Multiple-Object Image with Webhook endpoint

{% tabs %}
{% tab title="Response" %}

```python
{
  "txn_id": "282ae119-10a2-45e1-99c1-a6a87d11bc5e",
  "message": "Started working on the request."
}
```

{% endtab %}

{% tab title="Webhook Request" %}

```
curl --location --request POST 'https://webhook_endpoint' \
--header 'Content-Type: application/json' \
--header 'X-Frenzy-Transaction-ID: 282ae119-10a2-45e1-99c1-a6a87d11bc5e
' \
--data-raw '{
  "123": {
    "Products": [
      {
        "bounding_box": [76.27632141113281,152.2967987060547,859.9697875976562,1097.4202880859375],
        "category": {"description": ["dresses"],"prob": "0.67"},
        "style": {"description": ["slip dress"],"prob": "0.87"},
        "color": {"description": ["brown"],"prob": "0.25"},
        ...
      },
      {
        "bounding_box": [[124.05464935302734,585.519775390625,376.329345703125,824.7747802734375]],
        "category": {"description": ["bags"],"prob": "0.95"},
        "style": {"description": ["clutches"],"prob": "0.87"},
        "color": {"description": ["black"],"prob": "0.25"},
        ...
      }
    ]
  }
}'
```

{% endtab %}
{% endtabs %}

CASE 3: Single-Object Image without Webhook endpoint

```python
{
  "123": {
    "Products": [
      {
        "bounding_box": [76.27632141113281,152.2967987060547,859.9697875976562,1097.4202880859375],
        "category": {"description": ["dresses"],"prob": "0.67"},
        "style": {"description": ["slip dress"],"prob": "0.87"},
        "color": {"description": ["brown"],"prob": "0.25"},
        ...
      }
    ]
  }
}
```

CASE 4: Single-Object Image with Webhook endpoint

{% tabs %}
{% tab title="Response" %}

```python
{
  "txn_id": "282ae119-10a2-45e1-99c1-a6a87d11bc5e",
  "message": "Started working on the request."
}
```

{% endtab %}

{% tab title="Webhook Request" %}

```
curl --location --request POST 'https://webhook_endpoint' \
--header 'Content-Type: application/json' \
--header 'X-Frenzy-Transaction-ID: 282ae119-10a2-45e1-99c1-a6a87d11bc5e
' \
--data-raw '{
  "123": {
    "Products": [
      {
        "bounding_box": [76.27632141113281,152.2967987060547,859.9697875976562,1097.4202880859375],
        "category": {"description": ["dresses"],"prob": "0.67"},
        "style": {"description": ["slip dress"],"prob": "0.87"},
        "color": {"description": ["brown"],"prob": "0.25"},
        ...
      }
    ]
  }
}'
```

{% endtab %}
{% endtabs %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://olddocs.frenzy.ai/response/response-object.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.