DocuDive API documentation

Overview

This documentation provides details on various APIs available in DocuDive, including Information Extractor APIs, Business Insights APIs, Summary APIs, Key Questions and Answers APIs, and Conversational APIs. All APIs accept a PDF document, image, or website link as input and return output in text format with markup language.

API Reference

The DocuDive API is structured around REST principles, offering predictable resource-oriented URLs, accepting JSON-encoded request bodies, returning JSON-encoded responses, and using standard HTTP response codes, authentication, and verbs. It is designed to extract and analyze various types of information from documents, images, and web links.

API Access and Authentication

To use these APIs, customers must obtain an API key provided by DocuDive. Follow these steps to get your API key:

1. Request API Key: Send an email request to [email protected] with your full name and company details. Or send us a message through our contact us page.

2. Add Payment Method: Ensure a valid payment method is added to your DocuDive profile.

3. API Key Delivery: The API key will be delivered to you within 12 hours of request, provided all account and payment information is verified.

Base URL

All API requests should be made to the following base URL:

https://api.docudive.com

Common Request Structure

• Input: File upload (PDF or image) or URL.

• Request Payload: Includes client_id, information_type, content details, and API key.

• Output: JSON with client details (name, ID), timestamp, and the extracted information in text format with markup language.

Error Codes and Types

• HTTP Status Code Summary

  Status code	Summary
  200 OK	Everything worked as expected.
  400 Bad Request	The request was unacceptable, often due to missing a required parameter.
  401 Unauthorized	No valid API key provided.
  402 Request Failed	The parameters were valid, but the request failed.
  403 Forbidden	The API key doesn’t have permissions to perform the request.
  404 Not Found	The requested resource doesn’t exist.
  409 Conflict	The request conflicts with another request (perhaps due to using the same idempotent key).
  429 Too Many Requests	Too many requests hit the API too quickly. We recommend exponential backoff.
  500, 502, 503, 504 Server Errors	Something went wrong on DocuDive’s end (these are rare).

• Error Types

  Error type	Summary
  api_error	General errors related to server issues or unexpected conditions on DocuDive's side.
  payment_error	Occurs when there are insufficient credits in the account for the requested operation.
  invalid_request_error	Arises when the request contains invalid parameters or lacks required information.

API endpoints

• Details

  Purpose: Extracts specified types of information from input content based on the type and sub_type parameter.

  Endpoint: /extract-information

  Method: POST

  Input: File (PDF/image) or URL

  Output: Extracted information with client details and timestamp

  Information Types:

  type	sub_type
  information	topic
  information	time_line
  information	named_entity
  information	citations
  information	info_snippet
  information	cited_examples
  business_insights	educational_information
  business_insights	financial_information
  business_insights	editorial_information
  business_insights	legal_information
  summary	short_summary
  summary	detailed_summary
  qa	qa

• Sample Request Payload

  {
    "api_key": "your_api_key_here",
    "client_id": "client_12345",
    "type": "information"
    "sub_type": "topic"
  }

• Sample Response

  {
    "client_id": "client_12345",
    "client_name": "Company XYZ",
    "timestamp": "2024-07-28T12:34:56Z",
    "type": "information",
    "sub_type": "topic",
    "data": {
      "topics": [
        {
          "topic": "Data Privacy",
          "description": "Discussion on data protection laws and compliance measures."
        },
        {
          "topic": "Artificial Intelligence",
          "description": "Overview of AI applications in various industries."
        }
      ]
    }
  }

• Code Examples

  • cURL

    curl -X POST https://api.docudive.com/v1/extract-information \
    -H "Authorization: Bearer your_api_key_here" \
    -H "Content-Type: application/json" \
    -d '{
      "api_key": "your_api_key_here",
      "client_id": "client_12345",
      "type": "information",
      "sub_type": "topic",
      "file": "base64_encoded_string_of_pdf"
    }'

  • PHP

     'your_api_key_here',
      'client_id' => 'client_12345',
      'type' => 'information',
      'sub_type' => 'topic',
      'file' => 'base64_encoded_string_of_pdf'
    );
    
    $options = array(
      'http' => array(
        'header'  => "Content-type: application/json\r\n",
        'method'  => 'POST',
        'content' => json_encode($data),
      ),
    );
    $context  = stream_context_create($options);
    $result = file_get_contents($url, false, $context);
    echo $result;
    ?>

  • Java

    import java.io.OutputStream;
    import java.net.HttpURLConnection;
    import java.net.URL;
    import java.nio.charset.StandardCharsets;
    
    public class DocuDiveAPI {
        public static void main(String[] args) throws Exception {
            String url = "https://api.docudive.com/v1/extract-information";
            String jsonInputString = "{\"api_key\": \"your_api_key_here\", \"client_id\": \"client_12345\", \"type\": \"information\", \"sub_type\": \"topic\", \"file\": \"base64_encoded_string_of_pdf\"}";
    
            URL obj = new URL(url);
            HttpURLConnection con = (HttpURLConnection) obj.openConnection();
            con.setRequestMethod("POST");
            con.setRequestProperty("Content-Type", "application/json; utf-8");
            con.setRequestProperty("Accept", "application/json");
            con.setDoOutput(true);
    
            try (OutputStream os = con.getOutputStream()) {
                byte[] input = jsonInputString.getBytes(StandardCharsets.UTF_8);
                os.write(input, 0, input.length);
            }
    
            int responseCode = con.getResponseCode();
            System.out.println("POST Response Code :: " + responseCode);
        }
    }

  • Python

    import requests
    import json
    
    url = 'https://api.docudive.com/v1/extract-information'
    data = {
        'api_key': 'your_api_key_here',
        'client_id': 'client_12345',
        'type': 'information',
        'sub_type': 'topic',
        'file': 'base64_encoded_string_of_pdf'
    }
    headers = {
        'Authorization': 'Bearer your_api_key_here',
        'Content-Type': 'application/json'
    }
    
    response = requests.post(url, headers=headers, data=json.dumps(data))
    print(response.json())

  • Node.js

    const fetch = require('node-fetch');
    
    const url = 'https://api.docudive.com/v1/extract-information';
    const data = {
      api_key: 'your_api_key_here',
      client_id: 'client_12345',
      type: 'information',
      sub_type: 'topic',
      file: 'base64_encoded_string_of_pdf'
    };
    
    fetch(url, {
      method: 'POST',
      headers: {
        'Authorization': 'Bearer your_api_key_here',
        'Content-Type': 'application/json'
      },
      body: JSON.stringify(data)
    })
    .then(response => response.json())
    .then(data => console.log(data))
    .catch(error => console.error('Error:', error));

  • .NET

    using System;
    using System.Net.Http;
    using System.Text;
    using System.Threading.Tasks;
    
    class Program {
        static async Task Main(string[] args) {
            var client = new HttpClient();
            var request = new HttpRequestMessage(HttpMethod.Post, "https://api.docudive.com/v1/extract-information");
    
            var json = "{\"api_key\": \"your_api_key_here\", \"client_id\": \"client_12345\", \"type\": \"information\", \"sub_type\": \"topic\", \"file\": \"base64_encoded_string_of_pdf\"}";
            request.Content = new StringContent(json, Encoding.UTF8, "application/json");
            request.Headers.Add("Authorization", "Bearer your_api_key_here");
    
            var response = await client.SendAsync(request);
            var responseString = await response.Content.ReadAsStringAsync();
    
            Console.WriteLine(responseString);
        }
    }