This tutorial provides a step-by-step guide on how to use the Extracta.ai API for extracting data from documents.

Step 1: Setting Up Your Environment

Before you begin, ensure you have access to a REST client or a tool like Postman, or set up an environment in your preferred programming language to make HTTP requests.

Step 2: Obtaining API Access

• Register or log in to your account on RapidAPI.
• Subscribe to the Extracta.ai API.

Step 3: Preparing Your Request

• Identify the document you want to extract data from.
• Prepare the extractionDetails JSON structure with the required fields (name, language, fields).
• Convert your document to a base64String or have the URL ready if the document is hosted online.

Step 4: Making the API Request

• Endpoint URL: https://contract-parsing-api.p.rapidapi.com/processDocument
• Method: POST
• Headers: Ensure to include your API key for authentication.
• Body: Structure your request body as shown in the API documentation.

Example request body:

{
  "extractionDetails": {
    "name": "Your Extraction Name",
    "language": "English",
    "fields": [
      {
        "key": "name",
        "description": "Person's name",
        "example": "Jane Doe"
      }
      // Add other fields as required
    ]
  },
  "file": "Your Document in base64String or URL"
}

Step 5: Handling the Response

• On successful extraction, the API will return structured data in JSON format.
• If there are errors (e.g., invalid language or missing fields), you will receive an error message.

Step 6: Post-Processing (Optional)

• Once you receive the data, you can integrate it into your application or use it for analysis.

Additional Tips

• Test with different document types to understand how the API handles various formats.
• Refer to the ‘Supported Languages’ section to ensure accurate language specification.