This guide offers a detailed walkthrough on utilizing the Extracta.ai API to pull information from documents.

Step 1: Environment Configuration

Before starting, make sure you have a REST client like Postman at hand, or configure your coding environment for making HTTP requests in the language of your choice.

Step 2: Gaining API Access

• Sign up or sign in on the RapidAPI platform.
• Opt into the Extracta.ai API subscription.

Step 3: Request Preparation

• Select the document from which you wish to extract information.
• Formulate the extractionDetails JSON object including essential attributes (name, language, fields).
• Encode your document into a base64String or ensure its URL is accessible if it’s stored online.

Step 4: Executing the API Request

• Endpoint URL: https://bank-statement-parsing-api.p.rapidapi.com/processDocument
• Method: POST
• Headers: Include your API key to authenticate your request.
• Body: Compose the body of your request as illustrated in the API’s guidelines.

Example request body:

{
  "extractionDetails": {
    "name": "Name of Extraction",
    "language": "English",
    "fields": [
      {
        "key": "name",
        "description": "Name of the person",
        "example": "John Doe"
      }
      // Insert additional fields as needed
    ]
  },
  "file": "Your Document as base64String or URL"
}

Step 5: Response Management

• Upon successful data extraction, the API will send back the data in a structured JSON format.
• Should there be any issues (for instance, incorrect language or incomplete fields), an error notification will be provided.

Step 6: Post-Extraction Processing (Optional)

• After obtaining the data, you may incorporate it into your application or leverage it for further analysis.

Additional Recommendations

• Experiment with various types of documents to gauge the API’s adaptability to different formats.
• Check the ‘Supported Languages’ list to verify your language choice is supported.