# Run Form Recognizer

This activity allows users to extract data from documents by using [Azure Form Recognizer](https://docs.microsoft.com/en-us/azure/applied-ai-services/form-recognizer/overview?tabs=v3-0). User should have created a Form Recognizer resource in their Azure Portal to use this activity.

## Input

* **Document:** [`String Argument`](https://docs.visualyze.ai/getting-started/rpa-studio/arguments#types-of-arguments) \*\*\*\* <mark style="color:red;">`Required`</mark>\
  Specifies the path of the document to recognize. Supported file formats are pdf, jpg, bmp, tiff or png.
* **End Point:** [`String Argument`](https://docs.visualyze.ai/getting-started/rpa-studio/arguments#types-of-arguments) \*\*\*\* <mark style="color:red;">`Required`</mark>\
  Specifies the endpoint of the Form Recognizer resource.
* **API Key:** [`String Argument`](https://docs.visualyze.ai/getting-started/rpa-studio/arguments#types-of-arguments) \*\*\*\* <mark style="color:red;">`Required`</mark>\
  Specifies the API Key of the Form Recognizer resource.

## Options

* **Form Type:**\
  Specifies type of form model to apply on the document. Following form types are available:
  * `General`- Key value pair extraction.
  * `Invoice` - Standard Invoice model.
  * `Receipt` - Standard Receipt model.
  * `BusinessCard` - Standard Business Card model.
  * `Id` - Standard ID Document model
* **Output Types:**

  Specifies types of data to be included in the output. One or more of the following types can be selected at the same time:

  * `Document`- Extracted key value pairs for `General` model and recognized fields for others.
  * `Table`- Extracted tables.
  * `Text`- Text extracted using OCR.
* **Use Cache:**

  Specifies whether to use the cached result from previous run if available:

  * `True`
  * `False`

## Output

* **Result:** [`Variable`](https://docs.visualyze.ai/getting-started/rpa-studio/variables/activity-variables)\
  Specifies the output variable where the extracted result is saved.


---

# 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.visualyze.ai/integrations/azure/run-form-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.