# Vision AI

## Benefits

* **Accelerate Time-to-Value:** Effortlessly construct, deploy, and oversee computer vision applications tailored to your distinct business requirements. Leverage pre-trained APIs, AutoML, and custom models to streamline development and reduce complexity.
* **Versatility for Diverse Needs:** Address a range of applications and skill levels. Choose between plug-and-play analytics through APIs, custom machine learning models, or comprehensive end-to-end development environments, all available within our vision portfolio.
* **Assured quality from the leader in vision of:** Benefit from investments in vision across our portfolio. Vision offerings have received the highest ratings from several analyst firms.

## Detect Text In Images (`text_detection)`

## Text Detection (Image)

<mark style="color:green;">`POST`</mark> `https://api.autogon.ai/api/v1/services/vision-ai/`

`TEXT_DETECTION` detects and **extracts text from any image**. For example, a photograph might contain a street sign or traffic sign. The JSON includes the entire extracted string, as well as individual words, and their bounding boxes.

#### Headers

| Name                                           | Type   | Description         |
| ---------------------------------------------- | ------ | ------------------- |
| Content-Type<mark style="color:red;">\*</mark> | String | multipart/form-data |

#### Request Body

| Name                                        | Type   | Description                                 |
| ------------------------------------------- | ------ | ------------------------------------------- |
| operation<mark style="color:red;">\*</mark> | String | operation to be performed: `text_detection` |
| image<mark style="color:red;">\*</mark>     | File   | image file to be processed                  |

{% tabs %}
{% tab title="200: OK " %}

```javascript
{
    // Response
}
```

{% endtab %}
{% endtabs %}

## Detect Text In Documents (`document_text_detection`)&#x20;

## Text Detection (Documents)

<mark style="color:green;">`POST`</mark> `https://api.autogon.ai/api/v1/services/vision-ai/`

`DOCUMENT_TEXT_DETECTION` also extracts text from an image, but the response is **optimized for dense text and documents**. The JSON includes page, block, paragraph, word, and break information.

#### Headers

| Name                                           | Type   | Description         |
| ---------------------------------------------- | ------ | ------------------- |
| Content-Type<mark style="color:red;">\*</mark> | String | multipart/form-data |

#### Request Body

| Name      | Type   | Description                                          |
| --------- | ------ | ---------------------------------------------------- |
| operation | String | operation to be performed: `document_text_detection` |
| image     | File   | image to be processed                                |

{% tabs %}
{% tab title="200: OK " %}

```javascript
{
    // Response
}
```

{% endtab %}
{% endtabs %}

## Detect Labels In Images (`label_detection)`

## Label Detection

<mark style="color:green;">`POST`</mark> `https://api.autogon.ai/api/v1/services/vision-ai/`

`LABEL_DETECTION` can identify general objects, locations, activities, animal species, products, and more.

#### Headers

| Name         | Type   | Description         |
| ------------ | ------ | ------------------- |
| Content-Type | String | multipart/form-data |

#### Request Body

| Name                                        | Type   | Description                                  |
| ------------------------------------------- | ------ | -------------------------------------------- |
| image<mark style="color:red;">\*</mark>     | File   | image to be processed                        |
| operation<mark style="color:red;">\*</mark> | String | operation to be performed: `label_detection` |

{% tabs %}
{% tab title="200: OK " %}

```json
{
    "success": true,
    "data": {
        "labelAnnotations": [
            {
                "mid": "/m/01m3v",
                "description": "Computer",
                "score": 0.9151083,
                "topicality": 0.9151083,
                "locale": "",
                "confidence": 0,
                "locations": [],
                "properties": []
            },
            {
                "mid": "/m/01jwgf",
                "description": "Product",
                "score": 0.90773267,
                "topicality": 0.90773267,
                "locale": "",
                "confidence": 0,
                "locations": [],
                "properties": []
            },
            {
                "mid": "/m/0j62f",
                "description": "Rectangle",
                "score": 0.8904041,
                "topicality": 0.8904041,
                "locale": "",
                "confidence": 0,
                "locations": [],
                "properties": []
            },
            {
                "mid": "/m/03gq5hm",
                "description": "Font",
                "score": 0.853358,
                "topicality": 0.853358,
                "locale": "",
                "confidence": 0,
                "locations": [],
                "properties": []
            },
            {
                "mid": "/m/05khh",
                "description": "Operating system",
                "score": 0.8318895,
                "topicality": 0.8318895,
                "locale": "",
                "confidence": 0,
                "locations": [],
                "properties": []
            },
            {
                "mid": "/m/0643t",
                "description": "Personal computer",
                "score": 0.8156862,
                "topicality": 0.8156862,
                "locale": "",
                "confidence": 0,
                "locations": [],
                "properties": []
            },
            {
                "mid": "/m/01mf0",
                "description": "Software",
                "score": 0.80540884,
                "topicality": 0.80540884,
                "locale": "",
                "confidence": 0,
                "locations": [],
                "properties": []
            },
            {
                "mid": "/m/01zbnw",
                "description": "Screenshot",
                "score": 0.80162287,
                "topicality": 0.80162287,
                "locale": "",
                "confidence": 0,
                "locations": [],
                "properties": []
            },
            {
                "mid": "/m/07c1v",
                "description": "Technology",
                "score": 0.77332705,
                "topicality": 0.77332705,
                "locale": "",
                "confidence": 0,
                "locations": [],
                "properties": []
            },
            {
                "mid": "/m/0541p",
                "description": "Multimedia",
                "score": 0.7660149,
                "topicality": 0.7660149,
                "locale": "",
                "confidence": 0,
                "locations": [],
                "properties": []
            }
        ],
        "faceAnnotations": [],
        "landmarkAnnotations": [],
        "logoAnnotations": [],
        "localizedObjectAnnotations": [],
        "textAnnotations": []
    }
}
```

{% endtab %}
{% endtabs %}

## Detect Landmarks In Images (`landmark_detection)`

## Landmark Detection

<mark style="color:green;">`POST`</mark> `https://api.autogon.ai/api/v1/services/vision-ai/`

`LANDMARK_DETECTION` detects popular natural and human-made structures within an image.

#### Headers

| Name                                           | Type   | Description         |
| ---------------------------------------------- | ------ | ------------------- |
| Content-Type<mark style="color:red;">\*</mark> | String | multipart/form-data |

#### Request Body

| Name                                        | Type   | Description                                     |
| ------------------------------------------- | ------ | ----------------------------------------------- |
| image<mark style="color:red;">\*</mark>     | File   | image to be processed                           |
| operation<mark style="color:red;">\*</mark> | String | operation to be performed: `landmark_detection` |

{% tabs %}
{% tab title="200: OK " %}

```json
{
    "success": true,
    "data": {
        "landmarkAnnotations": [
            {
                "mid": "/m/02_2j2l",
                "description": "Charleston Park",
                "score": 0.45514682,
                "boundingPoly": {
                    "vertices": [
                        {
                            "x": 0,
                            "y": 0
                        },
                        {
                            "x": 3024,
                            "y": 0
                        },
                        {
                            "x": 3024,
                            "y": 2212
                        },
                        {
                            "y": 2212,
                            "x": 0
                        }
                    ],
                    "normalizedVertices": []
                },
                "locations": [
                    {
                        "latLng": {
                            "latitude": 37.42209959999999,
                            "longitude": -122.0819686
                        }
                    }
                ],
                "locale": "",
                "confidence": 0,
                "topicality": 0,
                "properties": []
            },
            {
                "mid": "/m/07mj0b",
                "description": "Shoreline Amphitheatre",
                "score": 0.42295343,
                "boundingPoly": {
                    "vertices": [
                        {
                            "x": 0,
                            "y": 0
                        },
                        {
                            "x": 3024,
                            "y": 0
                        },
                        {
                            "x": 3024,
                            "y": 2212
                        },
                        {
                            "y": 2212,
                            "x": 0
                        }
                    ],
                    "normalizedVertices": []
                },
                "locations": [
                    {
                        "latLng": {
                            "latitude": 37.4268342,
                            "longitude": -122.08070230000001
                        }
                    }
                ],
                "locale": "",
                "confidence": 0,
                "topicality": 0,
                "properties": []
            },
            {
                "mid": "/g/11b73jyz5y",
                "description": "Google Android Statues Square",
                "score": 0.42287928,
                "boundingPoly": {
                    "vertices": [
                        {
                            "x": 0,
                            "y": 0
                        },
                        {
                            "x": 3024,
                            "y": 0
                        },
                        {
                            "x": 3024,
                            "y": 2212
                        },
                        {
                            "y": 2212,
                            "x": 0
                        }
                    ],
                    "normalizedVertices": []
                },
                "locations": [
                    {
                        "latLng": {
                            "latitude": 37.4184266,
                            "longitude": -122.08802519999999
                        }
                    }
                ],
                "locale": "",
                "confidence": 0,
                "topicality": 0,
                "properties": []
            }
        ],
        "faceAnnotations": [],
        "logoAnnotations": [],
        "labelAnnotations": [],
        "localizedObjectAnnotations": [],
        "textAnnotations": []
    }
}
```

{% endtab %}
{% endtabs %}

## Detect Logo In Image (`logo_detection)`&#x20;

## Logo Detection

<mark style="color:green;">`POST`</mark> `https://api.autogon.ai/api/v1/services/vision-ai/`

`LOGO_DETECTION`detects popular product logos within an image.

#### Headers

| Name                                           | Type   | Description         |
| ---------------------------------------------- | ------ | ------------------- |
| Content-Type<mark style="color:red;">\*</mark> | String | multipart/form-data |

#### Request Body

| Name                                        | Type   | Description                                 |
| ------------------------------------------- | ------ | ------------------------------------------- |
| image<mark style="color:red;">\*</mark>     | File   | image to be processed                       |
| operation<mark style="color:red;">\*</mark> | String | operation to be performed: `logo_detection` |

{% tabs %}
{% tab title="200: OK " %}

```json
{
    "success": true,
    "data": {
        "logoAnnotations": [
            {
                "mid": "/m/045c7b",
                "description": "Google",
                "score": 0.9447075,
                "boundingPoly": {
                    "vertices": [
                        {
                            "x": 969,
                            "y": 677
                        },
                        {
                            "x": 1536,
                            "y": 677
                        },
                        {
                            "x": 1536,
                            "y": 1072
                        },
                        {
                            "x": 969,
                            "y": 1072
                        }
                    ],
                    "normalizedVertices": []
                },
                "locale": "",
                "confidence": 0,
                "topicality": 0,
                "locations": [],
                "properties": []
            }
        ],
        "faceAnnotations": [],
        "landmarkAnnotations": [],
        "labelAnnotations": [],
        "localizedObjectAnnotations": [],
        "textAnnotations": []
    }
}
```

{% endtab %}
{% endtabs %}

## Detect Web entities and pages (`web_detection`)  (Deprecated)

## Web Detection

<mark style="color:green;">`POST`</mark> `https://api.autogon.ai/api/v1/services/vision-ai/`

`WEB_DETECTION` detects the most likely owners of faces in an image and also Web references to an image.

#### Headers

| Name                                           | Type   | Description         |
| ---------------------------------------------- | ------ | ------------------- |
| Content-Type<mark style="color:red;">\*</mark> | String | multipart/form-data |

#### Request Body

| Name                                        | Type   | Description                                |
| ------------------------------------------- | ------ | ------------------------------------------ |
| image<mark style="color:red;">\*</mark>     | File   | image to be processed                      |
| operation<mark style="color:red;">\*</mark> | String | operation to be performed: `web_detection` |

{% tabs %}
{% tab title="200: OK " %}

```json
{
    "success": true,
    "data": {
        "webDetection": {
            "webEntities": [
                {
                    "entityId": "/g/11f53qsk8f",
                    "score": 12.1215,
                    "description": "Juice WRLD"
                },
                {
                    "entityId": "/t/24gkcc11n6yx7",
                    "score": 0.7112,
                    "description": ""
                },
                {
                    "entityId": "/g/11c2k2k6gm",
                    "score": 0.7112,
                    "description": "SoundCloud"
                },
                {
                    "entityId": "/m/04zxmr8",
                    "score": 0.7041,
                    "description": "SoundCloud"
                },
                {
                    "entityId": "/m/0glt670",
                    "score": 0.6141,
                    "description": "Hip hop music"
                },
                {
                    "entityId": "/g/11pws4_dzr",
                    "score": 0.6012,
                    "description": ""
                },
                {
                    "entityId": "/m/0rz017g",
                    "score": 0.562,
                    "description": ""
                },
                {
                    "entityId": "/m/04yhd6c",
                    "score": 0.562,
                    "description": "Spotify"
                },
                {
                    "entityId": "/m/09jcvs",
                    "score": 0.5599,
                    "description": "YouTube"
                },
                {
                    "entityId": "/m/0svml3_",
                    "score": 0.5599,
                    "description": ""
                }
            ],
            "fullMatchingImages": [
                {
                    "url": "https://oboi-download.ru/files/wallpapers/881/23989.jpg",
                    "score": 0
                },
                {
                    "url": "https://images.hdqwalls.com/download/juice-wrld-a4-3840x2160.jpg",
                    "score": 0
                },
                {
                    "url": "https://preview.redd.it/tvhbb8mo3ps71.jpg?auto=webp&s=e2af382fe56ca3ea74a1fc8783fa879c9977a0d0",
                    "score": 0
                },
                {
                    "url": "https://i.redd.it/tvhbb8mo3ps71.jpg",
                    "score": 0
                },
                {
                    "url": "https://www.pixel4k.com/preview.php?src=https://www.pixel4k.com/wp-content/uploads/2020/12/juice-wrld-4k_1607632977.jpg&w=2560&h=1440",
                    "score": 0
                },
                {
                    "url": "https://images.hdqwalls.com/download/juice-wrld-a4-2560x1440.jpg",
                    "score": 0
                },
                {
                    "url": "https://images.hdqwalls.com/download/juice-wrld-a4-2560x1080.jpg",
                    "score": 0
                },
                {
                    "url": "https://www.pixel4k.com/preview.php?src=https://www.pixel4k.com/wp-content/uploads/2020/12/juice-wrld-4k_1607632977.jpg&w=2560&h=1024",
                    "score": 0
                },
                {
                    "url": "https://wallpaperaccess.com/full/4484535.jpg",
                    "score": 0
                },
                {
                    "url": "https://images.hdqwalls.com/download/juice-wrld-a4-2048x1152.jpg",
                    "score": 0
                }
            ],
            "partialMatchingImages": [
                {
                    "url": "https://i.ytimg.com/vi/3yOXPCvZSWw/maxresdefault.jpg",
                    "score": 0
                },
                {
                    "url": "https://stream.kick.com/thumbnails/livestream/598072/thumb614/video_thumbnail/conversion/thumb614-video_thumbnail.webp",
                    "score": 0
                },
                {
                    "url": "https://cutewallpaper.org/23/american-mountain-android-cell-phone-wallpaper/3025832262.jpg",
                    "score": 0
                },
                {
                    "url": "https://www.hdwallpapers.in/download/american_rapper_juice_wrld_on_motor_bike_in_mountains_background_wearing_black_dress_4k_hd_juice_wrld-2560x1440.jpg",
                    "score": 0
                },
                {
                    "url": "https://wallpaperfordesktop.com/wp-content/uploads/2021/09/Juice-WRLD-Wallpaper-2.jpg",
                    "score": 0
                },
                {
                    "url": "https://www.hdwallpapers.in/download/american_rapper_juice_wrld_on_motor_bike_in_mountains_background_wearing_black_dress_4k_hd_juice_wrld-3840x2160.jpg",
                    "score": 0
                },
                {
                    "url": "https://www.hdwallpapers.in/download/american_rapper_juice_wrld_on_motor_bike_in_mountains_background_wearing_black_dress_4k_hd_juice_wrld-1600x900.jpg",
                    "score": 0
                },
                {
                    "url": "https://wallpapersflix.com/wp-content/uploads/2020/07/Juice-Wrld-Desktop-Wallpaper-1-1024x576.jpg",
                    "score": 0
                },
                {
                    "url": "https://wallsbazar.com/wp-content/uploads/2021/10/Juice-WRLD-Computer-Wallpaper-HD.jpg",
                    "score": 0
                },
                {
                    "url": "https://i.ytimg.com/vi/os6Q8F0_o-Y/maxresdefault.jpg",
                    "score": 0
                }
            ],
            "pagesWithMatchingImages": [
                {
                    "url": "https://www.youtube.com/watch?v=ba7wi64igHk",
                    "pageTitle": "<b>Juice WRLD</b> - Walk This Way (Music Video) - YouTube",
                    "partialMatchingImages": [
                        {
                            "url": "https://i.ytimg.com/vi/iAve0MvJISI/hqdefault.jpg?sqp=-oaymwEiCKgBEF5IWvKriqkDFQgBFQAAAAAYASUAAMhCPQCAokN4AQ==&rs=AOn4CLAXqmrlYXZDXzg35ghHOHdhB8hQlA",
                            "score": 0
                        }
                    ],
                    "score": 0,
                    "fullMatchingImages": []
                },
                {
                    "url": "https://www.youtube.com/watch?v=YrBJie_A3rI",
                    "pageTitle": "<b>Juice WRLD</b> - My Flaws (Unreleased)[Prod. Red Limits] - YouTube",
                    "partialMatchingImages": [
                        {
                            "url": "https://i.ytimg.com/vi/mLDQH7tBjNU/hqdefault.jpg?sqp=-oaymwE8CKgBEF5IWvKriqkDLwgBFQAAAAAYASUAAMhCPQCAokN4AfABAfgB_gmAAtAFigIMCAAQARhOIGUoYjAP&rs=AOn4CLBsT6hWH6tYoKmxHAa1A2CsLM_MEw",
                            "score": 0
                        }
                    ],
                    "score": 0,
                    "fullMatchingImages": []
                },
                {
                    "url": "https://www.youtube.com/watch?v=V74ZFKJIT9Y",
                    "pageTitle": "<b>Juice WRLD</b> - Draco on me (Unreleased) - YouTube",
                    "partialMatchingImages": [
                        {
                            "url": "https://i.ytimg.com/vi/iAve0MvJISI/hqdefault.jpg?sqp=-oaymwEiCKgBEF5IWvKriqkDFQgBFQAAAAAYASUAAMhCPQCAokN4AQ==&rs=AOn4CLAXqmrlYXZDXzg35ghHOHdhB8hQlA",
                            "score": 0
                        }
                    ],
                    "score": 0,
                    "fullMatchingImages": []
                },
                {
                    "url": "https://www.youtube.com/watch?v=os6Q8F0_o-Y",
                    "pageTitle": "<b>Juice WRLD</b> - Lonely ft. Polo G &amp; Machine Gun Kelly ... - YouTube",
                    "partialMatchingImages": [
                        {
                            "url": "https://i.ytimg.com/vi/os6Q8F0_o-Y/mqdefault.jpg",
                            "score": 0
                        },
                        {
                            "url": "https://i.ytimg.com/vi/os6Q8F0_o-Y/hqdefault.jpg?sqp=-oaymwEWCKgBEF5IWvKriqkDCQgBFQAAiEIYAQ==&rs=AOn4CLDIp1n01hbom8qjv_wh56lhLrPUxQ",
                            "score": 0
                        },
                        {
                            "url": "https://i.ytimg.com/vi/os6Q8F0_o-Y/maxresdefault.jpg",
                            "score": 0
                        }
                    ],
                    "score": 0,
                    "fullMatchingImages": []
                },
                {
                    "url": "https://soundcloud.com/user-411448275/sets/juice-wrld-studio-sessions",
                    "pageTitle": "<b>Juice Wrld</b> STUDIO SESSIONS - SoundCloud",
                    "partialMatchingImages": [
                        {
                            "url": "https://i1.sndcdn.com/artworks-PMJJQUNEBOrwDuFw-XTwXZw-t240x240.jpg",
                            "score": 0
                        }
                    ],
                    "score": 0,
                    "fullMatchingImages": []
                },
                {
                    "url": "https://open.spotify.com/playlist/0jLiasxMwWiZEDOw14Hh9j",
                    "pageTitle": "<b>Juice WRLD</b> Type Songs - playlist by @trabbey - Spotify",
                    "partialMatchingImages": [
                        {
                            "url": "https://i.scdn.co/image/ab67706c0000da848e325f487918c4e6f28c8489",
                            "score": 0
                        }
                    ],
                    "score": 0,
                    "fullMatchingImages": []
                },
                {
                    "url": "https://soundcloud.com/strmynghts2/shoot-back-w-juice-wrld",
                    "pageTitle": "Shoot Back (w/ <b>Juice WRLD</b>) - Strmy Nghts - SoundCloud",
                    "partialMatchingImages": [
                        {
                            "url": "https://i1.sndcdn.com/artworks-UnU9o0LxyhhYhxpK-GcWj9Q-t240x240.jpg",
                            "score": 0
                        }
                    ],
                    "score": 0,
                    "fullMatchingImages": []
                },
                {
                    "url": "https://soundcloud.com/user-231868378/murder-rate-1",
                    "pageTitle": "Murder Rate (Skip to :58) - <b>Juice WRLD</b> - SoundCloud",
                    "partialMatchingImages": [
                        {
                            "url": "https://i1.sndcdn.com/avatars-IMUohpyWZoigVIqx-pqiyog-t240x240.jpg",
                            "score": 0
                        }
                    ],
                    "score": 0,
                    "fullMatchingImages": []
                },
                {
                    "url": "https://unsplash.com/s/photos/juice-wrld",
                    "pageTitle": "750+ <b>Juice Wrld</b> Pictures | Download Free Images on Unsplash",
                    "partialMatchingImages": [
                        {
                            "url": "https://images.unsplash.com/photo-1575918679350-bf26b1b4da71?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxzZWFyY2h8M3x8anVpY2UlMjB3cmxkfGVufDB8fDB8fA%3D%3D&w=1000&q=80",
                            "score": 0
                        }
                    ],
                    "score": 0,
                    "fullMatchingImages": []
                },
                {
                    "url": "https://soundcloud.com/vendettawrld_039/cowboy-hunt-juice-wrld-1",
                    "pageTitle": "COWBOY HUNT • <b>Juice WRLD</b> - SoundCloud",
                    "partialMatchingImages": [
                        {
                            "url": "https://i1.sndcdn.com/artworks-UnU9o0LxyhhYhxpK-GcWj9Q-t240x240.jpg",
                            "score": 0
                        }
                    ],
                    "score": 0,
                    "fullMatchingImages": []
                }
            ],
            "visuallySimilarImages": [
                {
                    "url": "https://w0.peakpx.com/wallpaper/342/806/HD-wallpaper-american-rapper-juice-wrld-on-motor-bike-in-mountains-background-wearing-black-dress-juice-wrld.jpg",
                    "score": 0
                },
                {
                    "url": "https://i.ytimg.com/vi/ICDeevqrMIs/maxresdefault.jpg",
                    "score": 0
                },
                {
                    "url": "https://i.pinimg.com/736x/2a/16/81/2a16815d3e6219a4954801cf3fc522b6.jpg",
                    "score": 0
                },
                {
                    "url": "https://images.hdqwalls.com/download/juice-wrld-5k-85-1366x768.jpg",
                    "score": 0
                },
                {
                    "url": "https://img.youtube.com/vi/xaCvFsCM3GU/0.jpg",
                    "score": 0
                },
                {
                    "url": "https://i.guim.co.uk/img/media/ecef4c321a2f47ca1788a25443a820f7ec45c012/1802_511_5069_3041/500.jpg?quality=85&auto=format&fit=max&s=fc43386beae4af2d0c91e62f78ce94f3",
                    "score": 0
                },
                {
                    "url": "https://i.redd.it/h1r304b7pkr51.jpg",
                    "score": 0
                },
                {
                    "url": "https://4kwallpapers.com/images/wallpapers/juice-wrld-fighting-2560x1440-9496.jpeg",
                    "score": 0
                },
                {
                    "url": "https://images.unsplash.com/photo-1575918620264-7f672ce5b7f6?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxzZWFyY2h8Nnx8anVpY2UlMjB3cmxkfGVufDB8fDB8fA%3D%3D&w=1000&q=80",
                    "score": 0
                },
                {
                    "url": "https://e1.pxfuel.com/desktop-wallpaper/414/728/desktop-wallpaper-juice-wrld-gherbo-shares-the-stage-at-isu-g-herbo-and-juice-wrld-thumbnail.jpg",
                    "score": 0
                }
            ],
            "bestGuessLabels": [
                {
                    "label": "juice wrld",
                    "languageCode": "en"
                }
            ]
        },
        "faceAnnotations": [],
        "landmarkAnnotations": [],
        "logoAnnotations": [],
        "labelAnnotations": [],
        "localizedObjectAnnotations": [],
        "textAnnotations": []
    }
}


```

{% endtab %}
{% endtabs %}

## Detect Objects in Images (object\_detection)

<mark style="color:green;">`POST`</mark> `https://api.autogon.ai/api/v1/services/vision-ai/`

#### Headers

| Name                                           | Type   | Description         |
| ---------------------------------------------- | ------ | ------------------- |
| Content-Type<mark style="color:red;">\*</mark> | String | multipart/form-data |

#### Request Body

| Name                                        | Type   | Description                                   |
| ------------------------------------------- | ------ | --------------------------------------------- |
| image<mark style="color:red;">\*</mark>     | File   | image to be processed                         |
| operation<mark style="color:red;">\*</mark> | String | Operation to be performed (object\_detection) |

{% tabs %}
{% tab title="200: OK " %}

```json
{
    "success": true,
    "data": {
        "localizedObjectAnnotations": [
            {
                "mid": "/m/01bqk0",
                "name": "Bicycle wheel",
                "score": 0.9002501,
                "boundingPoly": {
                    "normalizedVertices": [
                        {
                            "x": 0.31731018,
                            "y": 0.7903423
                        },
                        {
                            "x": 0.44589233,
                            "y": 0.7903423
                        },
                        {
                            "x": 0.44589233,
                            "y": 0.97311586
                        },
                        {
                            "x": 0.31731018,
                            "y": 0.97311586
                        }
                    ],
                    "vertices": []
                },
                "languageCode": ""
            },
            {
                "mid": "/m/0h9mv",
                "name": "Tire",
                "score": 0.8839195,
                "boundingPoly": {
                    "normalizedVertices": [
                        {
                            "x": 0.5012414,
                            "y": 0.76509905
                        },
                        {
                            "x": 0.62809473,
                            "y": 0.76509905
                        },
                        {
                            "x": 0.62809473,
                            "y": 0.94585633
                        },
                        {
                            "x": 0.5012414,
                            "y": 0.94585633
                        }
                    ],
                    "vertices": []
                },
                "languageCode": ""
            },
            {
                "mid": "/m/0199g",
                "name": "Bicycle",
                "score": 0.7687283,
                "boundingPoly": {
                    "normalizedVertices": [
                        {
                            "x": 0.3199663,
                            "y": 0.66994625
                        },
                        {
                            "x": 0.63588053,
                            "y": 0.66994625
                        },
                        {
                            "x": 0.63588053,
                            "y": 0.9711194
                        },
                        {
                            "x": 0.3199663,
                            "y": 0.9711194
                        }
                    ],
                    "vertices": []
                },
                "languageCode": ""
            },
            {
                "mid": "/m/06z37_",
                "name": "Picture frame",
                "score": 0.64136606,
                "boundingPoly": {
                    "normalizedVertices": [
                        {
                            "x": 0.78812456,
                            "y": 0.15784176
                        },
                        {
                            "x": 0.9710552,
                            "y": 0.15784176
                        },
                        {
                            "x": 0.9710552,
                            "y": 0.31219316
                        },
                        {
                            "x": 0.78812456,
                            "y": 0.31219316
                        }
                    ],
                    "vertices": []
                },
                "languageCode": ""
            }
        ],
        "faceAnnotations": [],
        "landmarkAnnotations": [],
        "logoAnnotations": [],
        "labelAnnotations": [],
        "textAnnotations": []
    }
}
```

{% endtab %}
{% endtabs %}

## Image Generation

## Creates an image given a prompt.

<mark style="color:green;">`POST`</mark> `http://api.autogon.ai/services/image-generation/`

Given a prompt and/or an input image, this endpoint will generate a new image.

#### Headers

| Name                                           | Type   | Description      |
| ---------------------------------------------- | ------ | ---------------- |
| Content-Type<mark style="color:red;">\*</mark> | String | application/json |

#### Request Body

| Name                                     | Type   | Description                                                                                                 |
| ---------------------------------------- | ------ | ----------------------------------------------------------------------------------------------------------- |
| prompt<mark style="color:red;">\*</mark> | String | A text description of the desired image(s). The maximum length is 1000 characters.                          |
| output\_size                             | String | The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024, defaults to 512x512.` |

{% tabs %}
{% tab title="200: OK " %}

```json
{
    "image_url": "https://example-image-url.com",
    "date_created": "2023-04-15 10:30:49.882687"
}
```

{% endtab %}
{% endtabs %}

## License Plate Detector

Detects license plate in a given image

<mark style="color:green;">`POST`</mark> `http://api.autogon.ai/services/license-plate-detection/`

#### Headers

| Name                                           | Type   | Description      |
| ---------------------------------------------- | ------ | ---------------- |
| Content-Type<mark style="color:red;">\*</mark> | String | application/json |

#### Request Body&#x20;

| Name                                          | Type  | Description                                          |
| --------------------------------------------- | ----- | ---------------------------------------------------- |
| image\_urls<mark style="color:red;">\*</mark> | Array | An array of image urls with images of license plates |
| <p></p><p>confidence\_thresh</p>              | Float | Default: 0.5                                         |
| overlap\_thresh                               | Float | Default: 0.5                                         |

{% tabs %}
{% tab title="200: OK " %}

```json
{
  "https://storage.autogon.ai/45c16e3a-924f-4db0-8db7-0b043598f093.jpg": [
    {
      "lbl_id": 0,
      "lbl": "LP",
      "bbx": {
        "x": 59.0321159362793,
        "y": 434.32745361328125,
        "w": 267.5981750488281,
        "h": 140.85491943359375
      },
      "conf": 0.9056000113487244
    },
    {
      "lbl_id": 0,
      "lbl": "LP",
      "bbx": {
        "x": 543.1251220703125,
        "y": 363.24102783203125,
        "w": 179.230224609375,
        "h": 43.1021728515625
      },
      "conf": 0.7953004240989685
    }
  ]
}
```

{% endtab %}
{% endtabs %}

## Motion Detection

Provides real time, accurate motion tracking for video streams

<mark style="color:green;">`POST`</mark> `http://api.autogon.ai/services/motion-detection/`

#### Headers

| Name                                           | Type   | Description      |
| ---------------------------------------------- | ------ | ---------------- |
| Content-Type<mark style="color:red;">\*</mark> | String | application/json |

#### Request Body&#x20;

| Name                                    | Type | Description                 |
| --------------------------------------- | ---- | --------------------------- |
| video<mark style="color:red;">\*</mark> | File | video file to detect motion |

{% tabs %}
{% tab title="200: OK " %}

```json
{
  "fps": 12.0,
  "annotations": {
    "5": [
      {
        "bbx": {
          "x": 0,
          "y": 568,
          "w": 576,
          "h": 276
        }
      }
    ],
    "6": [
      {
        "bbx": {
          "x": 34,
          "y": 708,
          "w": 110,
          "h": 86
        }
      },
      {
        "bbx": {
          "x": 0,
          "y": 671,
          "w": 576,
          "h": 249
        }
      },
      {
        "bbx": {
          "x": 0,
          "y": 663,
          "w": 120,
          "h": 15
        }
      }
    ],
  }
}
```

{% endtab %}
{% endtabs %}

## Stable Diffusion (Deprecated)

Generate Images from Text

<mark style="color:green;">`POST`</mark> `https://api.autogon.ai/api/v1/services/stable-diffusion/`

#### Headers

| Name                                           | Type | Description      |
| ---------------------------------------------- | ---- | ---------------- |
| Content-Type<mark style="color:red;">\*</mark> |      | application/json |

#### Request Body

| Name                                   | Type   | Description                                |
| -------------------------------------- | ------ | ------------------------------------------ |
| text<mark style="color:red;">\*</mark> | String | Short description of image to be generated |

{% tabs %}
{% tab title="200: OK " %}

```json
{
    "status": true,
    "image": "https://test-image.png"
}
```

{% endtab %}
{% endtabs %}

## Image Captioning (Deprecated)

Analyzes an image and generates captions for images

<mark style="color:green;">`POST`</mark> `https://api.autogon.ai/api/v1/services/image-captioning/`

#### Headers

| Name                                           | Type   | Description         |
| ---------------------------------------------- | ------ | ------------------- |
| Content-Type<mark style="color:red;">\*</mark> | String | multipart/form-data |

#### Request Body

| Name                                         | Type   | Description                                               |
| -------------------------------------------- | ------ | --------------------------------------------------------- |
| image<mark style="color:red;">\*</mark>      | File   | image to be captioned                                     |
| image\_url<mark style="color:red;">\*</mark> | String | url of the image to be captioned (should be downloadable) |

{% tabs %}
{% tab title="200: OK " %}

```json
{
    "status": true,
    "message": "a ball with a yellow ball inside of it "
}
```

{% endtab %}
{% endtabs %}

## Document Question and Answering (Deprecated)

Leverage AI models capable of answering questions based on the content of a given document.

<mark style="color:green;">`POST`</mark> `https://api.autogon.ai/api/v1/services/document-qa/`

#### Headers

| Name                                           | Type   | Description         |
| ---------------------------------------------- | ------ | ------------------- |
| Content-Type<mark style="color:red;">\*</mark> | String | multipart/form-data |

#### Request Body

| Name                                       | Type   | Description |
| ------------------------------------------ | ------ | ----------- |
| question<mark style="color:red;">\*</mark> | String |             |
| document\_url                              | String |             |
| document                                   | File   |             |

{% tabs %}
{% tab title="200: OK " %}

```json
{
    "status": True, 
    "message": answer
}
```

{% endtab %}

{% tab title="400: Bad Request " %}

```json
{
    "status": False, 
    "message": error message
}
```

{% endtab %}
{% endtabs %}

## Visual Question and Answering (Deprecated)

Generate accurate answers about an image based on the visual content of the image

<mark style="color:green;">`POST`</mark> `https://api.autogon.ai/api/v1/services/vilt-vq/`

#### Headers

| Name                                           | Type   | Description         |
| ---------------------------------------------- | ------ | ------------------- |
| Content-Type<mark style="color:red;">\*</mark> | String | multipart/form-data |

#### Request Body

| Name                                   | Type   | Description |
| -------------------------------------- | ------ | ----------- |
| text<mark style="color:red;">\*</mark> | String |             |
| image                                  | File   |             |
| image\_url                             | String |             |

{% tabs %}
{% tab title="200: OK " %}

```json
{
    "status": true,
    "message": "very"
}
```

{% endtab %}
{% endtabs %}


---

# Agent Instructions: 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://docs.autogon.ai/autogon-qore/vision-ai.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.