Quickstart

// Start of Selection This guide provides a streamlined approach to using the Chunkr API for document processing and analysis. The way you use the API is by creating a task for each document you want to process, and then polling the task until it is completed.

​

Setup

1. Create an Account

   Go to chunkr.ai and create an account. Once logged in, navigate to the API section to obtain your API key.

2. Create a task

   Use the following curl command to create a new task:

    curl -X POST https://api.chunkr.ai/api/v1/task \
        -H "Content-Type: multipart/form-data" \
        -H "Authorization: ${YOUR_API_KEY}" \
        -F "file=@/path/to/your/file" \
        -F "model=HighQuality" \
        -F "target_chunk_length=512" \
        -F "ocr_strategy=Auto" \
        -F 'json_schema={
        "title": "Basket",
        "type": "object",
        "properties": [
        {
            "name": "black holes observed",
            "title": "Black Holes Observed",
            "type": "list",
            "description": "A list of black holes observed",
            "default": null
        },
        {
            "name": "implications of data",
            "title": "Implications of Data",
            "type": "string",
            "description": "The implications of the observed data",
            "default": null
        }
        ]
        };type=application/json'
   

   Note: The json_schema parameter is optional. When provided, it should be a list of properties for structured extraction. If you do not require structured data extraction, you can omit this field.

   This command will return the task object containing the task_id needed for polling the task.

3. Get the task

   Use the following curl command to check the status of your task:

   curl -X GET https://api.chunkr.ai/api/v1/task/${TASK_ID} \
     -H "Authorization: ${YOUR_API_KEY}"
   

   Keep polling this endpoint until the status field in the response changes to Succeeded. Once successful, the output field in the response will contain the processed data.

4. Interpreting the Response

   Here is an example of what the output might look like. For a full list of fields and explanations of the output, refer to the task response page.

   {
     "configuration": {
       "model": "Fast",
       "ocr_strategy": "Auto",
       "target_chunk_length": 512
     },
     "created_at": "2023-04-15T10:30:00Z",
     "expires_at": "2023-04-22T10:30:00Z",
     "file_name": "document.pdf",
     "finished_at": "2023-04-15T10:31:30Z",
     "input_file_url": "https://storage.chunkr.ai/input/document.pdf",
     "message": "Task completed successfully",
     "output": {
       "chunk_length": 1,
       "segments": [
         {
           "bbox": {
             "left": 10.0,
             "top": 70.0,
             "width": 110.0,
             "height": 20.0
           },
           "content": "This is a sample text segment.",
           "html": "<p>This is a sample text segment.</p>",
           "image": null,
           "markdown": "This is a sample text segment.",
           "ocr": [
             {
               "bbox": {
                 "left": 2.5,
                 "top": 10.0,
                 "width": 107.5,
                 "height": 10.0
               },
               "confidence": 0.97,
               "text": "This is a sample text segment."
             }
           ],
           "page_height": 842.0,
           "page_number": 1,
           "page_width": 595.0,
           "segment_id": "81729b96-086b-49ce-8112-de8e109bfc3c",
           "segment_type": "Text"
         }
       ]
     },
     "page_count": 5,
     "status": "Succeeded",
     "task_id": "65237fe1-d6f1-456b-9238-408b97a1536d",
     "task_url": "https://api.chunkr.ai/api/v1/task/65237fe1-d6f1-456b-9238-408b97a1536d"
   }