Skip to main content

Quick Start using API

In this tutorial, we will show you step-by-step how to send documents to a DocumentPro using our Rest API

Prerequisites​

  1. You need a DocumentPro account. If you haven't signed up yet, create an account here.
  2. Basic knowledge of making HTTP requests (we'll use Python in our examples).
  3. A document you want to send to the Workflow (we'll use an invoice as an example).

Step 1: Create a Workflow on DocumentPro​

Initially you need to create a Workflow on DocumentPro web so that you can get access to your API Key. Once you have your Account API Key you can create additional Workflows using the Rest API.

  1. Log in to your DocumentPro account.
  2. Navigate to the https://app.documentpro.ai/new-workflow.
  3. Set your Workflow Name.
  4. In the Document Parsing section set the document type.
  5. Next, click on Configure Parser and add the fields you want to extract from your Document. Save Configurations.
  6. Click on Create Workflow. You will be redirected to your Workflow.

Step 1: Get Your API Key​

Before you can make API calls, you need your API key.

  1. On your Workflow Page, click on the Import section in Workflow tab.
  2. You will see an API section with the ability to Create API Key. Click is to get a new API Key. This API key will be the same across all your Workflows.
  3. Copy your API key.

API Key Location

Important: Keep your API key secure and don't share it publicly.

Step 2: Upload a Document​

First, we'll upload a document to DocumentPro using the API.

import requests

url = "https://api.documentpro.ai/v1/documents"
files = [
  ('file', ('invoice.pdf', open('/path/to/your/invoice.pdf', 'rb'), 'application/pdf'))
]
headers = {
  'x-api-key': 'YOUR_API_KEY_HERE'
}

response = requests.post(url, headers=headers, files=files)
print(response.text)

Replace 'YOUR_API_KEY_HERE' with your actual API key, and update the file path to point to your document.

This API call will return a response containing the document_id. Save this ID as you'll need it for the next step.

Step 3: Send your Document to a Workflow​

Now that we've uploaded a document, we can send it to the Workflow you created before. Note the workflow_id in the Workflow tab of the Workflow page.

Template ID Location

Here's how to send the document to the Workflow:

import requests

document_id = "YOUR_DOCUMENT_ID_HERE"
template_id = "YOUR_WORKFLOW_ID_HERE"

url = f"https://api.documentpro.ai/v1/documents/{document_id}/run_parser"

headers = {
  'x-api-key': 'YOUR_API_KEY_HERE',
  'Accept': 'application/json'
}

params = {
    'template_id': template_id,
    'use_ocr': True, # Optional, defaults to Workflow setting
    'query_model': 'gpt-4o', # Optional, defaults to Workflow setting
    'detect_layout': True, # Optional, defaults to Workflow setting
    'detect_tables': True, # Optional, defaults to Workflow setting
    'page_ranges': '1-3' # Optional, defaults to Workflow setting
}

response = requests.get(url, headers=headers, params=params)
print(response.text)

Replace 'YOUR_DOCUMENT_ID_HERE', 'YOUR_TEMPLATE_ID_HERE', and 'YOUR_API_KEY_HERE' with your actual values.

This API call will return a request_id. Save this ID for the final step.

Step 4: Retrieve the Results​

Finally, we can retrieve the parsed results using the request_id from the previous step:

import requests

request_id = "YOUR_REQUEST_ID_HERE"

url = "https://api.documentpro.ai/files"

headers = {
  'x-api-key': 'YOUR_API_KEY_HERE',
  'Accept': 'application/json'
}

params = {
  'request_id': request_id
}

response = requests.get(url, headers=headers, params=params)
print(response.text)

Replace 'YOUR_REQUEST_ID_HERE' and 'YOUR_API_KEY_HERE' with your actual values.

This API call will return the parsed data from your document.

Conclusion​

Congratulations! You've successfully used the DocumentPro API to upload a document, run a parser on it, and retrieve the results.

Here's a quick recap of what we did:

  1. Created a Workflow on DocumentPro
  2. Retrieved the API key from the DocumentPro dashboard.
  3. Uploaded a document using the /v1/documents endpoint.
  4. Sent the document to the Workflow using the /v1/documents/{document_id}/run_parser endpoint.
  5. Retrieved the parsed results using the /files endpoint.

What's Next?​