Skip to main content
POST
/
api
/
v1
/
custom-processor
Run Custom Processor
import requests

url = "https://www.datalab.to/api/v1/custom-processor"

files = { "file.0": ("example-file", open("example-file", "rb")) }
payload = {
    "pipeline_id": "<string>",
    "file_url": "<string>",
    "version": "123",
    "run_eval": "false",
    "mode": "fast",
    "max_pages": "123",
    "page_range": "<string>",
    "output_format": "<string>",
    "paginate": "false",
    "add_block_ids": "false",
    "include_markdown_in_chunks": "false",
    "disable_image_extraction": "false",
    "disable_image_captions": "false",
    "skip_cache": "false",
    "webhook_url": "<string>",
    "workflowstepdata_id": "123",
    "file": "<string>"
}
headers = {"X-API-Key": "<api-key>"}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)
{
  "request_id": "<string>",
  "request_check_url": "<string>",
  "success": true,
  "error": "<string>",
  "versions": {}
}

Authorizations

​
X-API-Key
string
header
required

Cookies

​
wos-session
string
​
datalab_active_team
string

Body

multipart/form-data
​
pipeline_id
string
required

The custom pipeline ID or template ID to execute. Must be a completed pipeline created via the custom pipeline API, or a valid template slug.

​
file_url
string | null

Optional file URL (http/https). If provided, the server will download and process it.

​
version
integer | null

Optional version number to use. If not provided, the active version of the pipeline will be used.

​
run_eval
boolean
default:false

Run evaluation rules defined for this custom pipeline.

​
mode
string
default:fast

Output mode for the underlying parsing step.

​
max_pages
integer | null

The maximum number of pages to process.

​
page_range
string | null

The page range to process, comma separated like 0,5-10,20.

​
output_format
string | null

The output format. Can be 'json', 'html', 'markdown', or 'chunks'. Defaults to 'markdown'.

​
paginate
boolean
default:false

Whether to paginate the output. If set to True, each page of the output will be separated by a horizontal rule that contains the page number.

​
add_block_ids
boolean
default:false

Add data-block-id attributes to HTML elements for citation tracking. Only applies when output_format includes 'html'.

​
include_markdown_in_chunks
boolean
default:false

Include markdown field in chunks and JSON output. When enabled, each chunk will have a 'markdown' field with the markdown representation of that block. Only applies when output_format includes 'json' or 'chunks'.

​
disable_image_extraction
boolean
default:false

Disable image extraction from the PDF. Defaults to False.

​
disable_image_captions
boolean
default:false

Disable synthetic image captions/descriptions in output. Images will be rendered as plain img tags without alt text. Defaults to False.

​
skip_cache
boolean
default:false

Skip the cache and re-run.

​
webhook_url
string | null

Optional webhook URL to call when the request is complete.

​
workflowstepdata_id
integer | null

Optional workflow step data ID to associate with this request.

​
file
file | null

Input PDF, word document, powerpoint, or image file, uploaded as multipart form data. Images must be png, jpg, or webp format.

Response

Successful Response

​
request_id
string
required

The ID of the request. This ID can be used to check the status of the request.

​
request_check_url
string
required

The URL to check the status of the request and get results.

​
success
boolean
default:true

Whether the request was successful.

​
error
string | null

If the request was not successful, this will contain an error message.

​
versions

A dictionary of the versions of the libraries used in the request.