Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs-docflow.textin.ai/llms.txt

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

The document extraction feature identifies key field information in a document based on the fields configured for its file category.Each field includes a key-value pair and position coordinate information.

​
Field Structure

Field information is located in result.files[].data.fields[], with each field containing the following attributes:
  • key: Field name (such as “Invoice Code”, “Invoice Date”, etc.)
  • value: Field value (recognized text content)
  • position[]: Position coordinate information of the field in the document; fields may span pages or lines, so an array is used

​
Position Coordinate Structure

{
  "page": 0,           // Page number where the field is located
  "vertices": [        // Coordinates of four vertices [x1,y1,x2,y2,x3,y3,x4,y4]
    100, 200,          // Top-left corner
    300, 200,          // Top-right corner
    300, 250,          // Bottom-right corner
    100, 250           // Bottom-left corner
  ]
}
For detailed coordinate descriptions, please refer to the Coordinate System documentation.

​
Example Code

import requests
import json

def extract_fields(workspace_id, batch_number, app_id, secret_code):
    """Extract field information from documents"""
    
    host = "https://docflow.textin.ai"
    url = "/api/app-api/sip/platform/v2/file/fetch"
    
    resp = requests.get(
        f"{host}{url}",
        params={
            "workspace_id": workspace_id, 
            "batch_number": batch_number
        },
        headers={
            "x-ti-app-id": app_id, 
            "x-ti-secret-code": secret_code
        },
        timeout=60,
    )
    
    if resp.status_code != 200:
        print(f"Request failed: {resp.status_code}")
        return None
    
    data = resp.json()
    
    for file in data.get("result", {}).get("files", []):
        print(f"File name: {file.get('name')}")
        print(f"Recognition status: {file.get('recognition_status')}")
        
        # Extract field information
        fields = file.get("data", {}).get("fields", [])
        if fields:
            print("\n=== Field Information ===")
            for field in fields:
                key = field.get("key", "")
                value = field.get("value", "")
                positions = field.get("position", [])
                
                print(f"Field: {key}")
                print(f"Value: {value}")
                
                # Display position information
                for i, pos in enumerate(positions):
                    page = pos.get("page", 0)
                    vertices = pos.get("vertices", [])
                    print(f"  Position {i+1} (Page {page+1}): {vertices}")
                print("-" * 30)
        else:
            print("No field information found")
    
    return data

# Usage example
if __name__ == "__main__":
    workspace_id = "<your-workspace-id>"
    batch_number = "<your-batch-number>"
    app_id = "<your-app-id>"
    secret_code = "<your-secret-code>"
    
    result = extract_fields(workspace_id, batch_number, app_id, secret_code)

​
Return Data Example

{
  "code": 200,
  "result": {
    "files": [
      {
        "id": "202412190001",
        "name": "invoice.pdf",
        "recognition_status": 1,
        "data": {
          "fields": [
            {
              "key": "Invoice Code",
              "value": "3100231130",
              "position": [
                {
                  "page": 0,
                  "vertices": [100, 150, 200, 150, 200, 180, 100, 180]
                }
              ]
            },
            {
              "key": "Invoice Number",
              "value": "12345678",
              "position": [
                {
                  "page": 0,
                  "vertices": [250, 150, 320, 150, 320, 180, 250, 180]
                }
              ]
            },
            {
              "key": "Invoice Date",
              "value": "December 19, 2024",
              "position": [
                {
                  "page": 0,
                  "vertices": [400, 150, 500, 150, 500, 180, 400, 180]
                }
              ]
            },
            {
              "key": "Buyer Name",
              "value": "Shanghai XX Technology Co., Ltd.",
              "position": [
                {
                  "page": 0,
                  "vertices": [100, 250, 400, 250, 400, 280, 100, 280]
                }
              ]
            },
            {
              "key": "Amount",
              "value": "1000.00",
              "position": [
                {
                  "page": 0,
                  "vertices": [500, 350, 600, 350, 600, 380, 500, 380]
                }
              ]
            }
          ]
        }
      }
    ]
  }
}