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.

To use this module, you must enable the Artificial Intelligence feature in Skyone Studio. Please contact the sales team at [email protected].

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.

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.

To finish, simply click "Save".

Learn more about the Module Header here.