Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.superagentx.ai/llms.txt

Use this file to discover all available pages before exploring further.

The ExtractAIHandler is a utility for document AI extraction. It integrates with an AI-powered backend to process files (e.g., invoices, PDFs, receipts) and extract structured JSON data. It supports Base64 file encoding, asynchronous extraction requests, job polling, and retrieval of processed results. This handler is useful for invoice extraction, document digitization, and structured data retrieval from files.

​
Example

To create the ExtractAIHandler object with your Extract API credentials: 
import os
from superagentx.handler.ai.extract import ExtractAIHandler

extract_handler = ExtractAIHandler(
    prompt_name="invoice_extraction",
    api_token=os.getenv("EXTRACT_API_TOKEN"),
    base_url=os.getenv("BASE_URL"),
    project_id="test_project_123"
)
Get File Base64 Data:
Reads a file from the given path and returns its Base64-encoded content. 
file_data = await extract_handler.get_file_base64_data("invoice.pdf")
print(file_data[:100])  # preview first 100 chars
Extract API:
Initiates a file extraction request and polls until results are available. 
result = await extract_handler.extract_api(
    file_path="invoice.pdf",
    file_data=file_data,
    poll_interval=5,
    retry=10
)
print(result)
Get Invoice JSON Data:
Fetches the extracted JSON data using the reference ID of a completed job. 
invoice_data = await extract_handler.get_invoice_json_data("ref12345")
print(invoice_data)