# Image Recognizer

This component is powered by [Microsoft Azure](https://blogs.microsoft.com/ai/azure-image-captioning/). You can get your own server URL and subscription key for Microsoft Azure [here](https://azure.microsoft.com/en-us/free/). You can add these details to your app in the [Project Settings panel](/snap-to-place/projects/settings.md#api-keys), which you can access by clicking on your app icon.

{% embed url="<https://youtu.be/yG9mdhn70w4>" %}

## Blocks

### Upload

![](/files/-MYdUWtPSMmZq_8MFWND)

#### Inputs

| Name  | Data Type |
| ----- | --------- |
| image | Image     |

#### Outputs

| Name            | Data Type | Data                                                                                  |
| --------------- | --------- | ------------------------------------------------------------------------------------- |
| tags            | List      | Tags used to categorize the image                                                     |
| description     | Text      | Description of the image                                                              |
| confidenceLevel | Decimal   | Value between 0 and 1 describing confidence that the description and tags are correct |
| error           | Text      | If error, returns error; else returns `null`                                          |


---

# 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.thunkable.com/snap-to-place/image-recognizer.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.