> For the complete documentation index, see [llms.txt](https://docs.skyone.cloud/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.skyone.cloud/english/skyone-studio/integrations/flows/tool-modules/ocr-processing-module.md).

# OCR Processing Module

### Definition

The **OCR Processing** **module** utilizes artificial intelligence to perform optical character recognition on image and PDF files. It extracts and structures document data, returning the content in various formats such as JSON and Markdown.

{% hint style="warning" %}
To use this module, you must enable the Artificial Intelligence feature in **Skyone Studio**. Please contact the sales team at <comercial@skyone.solutions>.
{% endhint %}

### Adding the "OCR Processing” module

The "**OCR Processing**" module appears under the Tools option within the flow editor. After clicking to add it, the initial configuration modal will be displayed.

<figure><img src="https://2493694111-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FQPcfIOA6Tl2Bmk6CdV2O%2Fuploads%2F7NMvLxTPvUcylNkFaYjQ%2FDesign%20sem%20nome.gif?alt=media&amp;token=8856390d-7a27-4708-95cb-541ecec2bd2e" alt=""><figcaption></figcaption></figure>

Complete or select the following items to use the module:

* **File in base64:** Insert the file content (PDF or image) encoded in Base64 format, previously registered as a variable. Refer to the "Variables" section for more details.
* **Model:** Select the AI model to be used for OCR processing.
* **Return type (optional):** Choose the output format for the extracted text. Options include JSON (module default), Markdown, or Raw Text.
* **Prompt:** Enter the instruction to guide the data extraction and reading behavior.
* **Parse type (optional):** Defines how the system should interpret the extracted data:
  * **Auto parsing:** The API attempts to convert the response into JSON. If unsuccessful, it returns the original string.
  * **JSON Schema:** Defines a JSON schema to structure the response consistently.
* **Schema in JSON Schema:** Insert the schema definition (available only when the JSON Schema option is active).
* **Split into pages? (optional):** Enable this option to have the processing handle each page of the document individually.
* **Maintain context? (optional):** If enabled, the AI will use information from previous pages to improve understanding of the content on subsequent pages.

Click "**Next**". You will be redirected to the test screen.

Click "**Test**" to verify the module.&#x20;

<figure><img src="https://2493694111-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FQPcfIOA6Tl2Bmk6CdV2O%2Fuploads%2FgWvisfM1yvOH20dcxnry%2Fdel%20edicao%20de%20imagem%20(7).png?alt=media&amp;token=54ec54aa-7332-41ef-a688-df2b357abf21" alt=""><figcaption></figcaption></figure>

To finish, simply click "**Save**".

{% hint style="info" %}
[Learn more about the Module Header here](https://docs.skyone.cloud/english/skyone-studio/integrations/flows/module-header.md).
{% endhint %}


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.skyone.cloud/english/skyone-studio/integrations/flows/tool-modules/ocr-processing-module.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
