Skip to main content
POST
/
extract_async
Extract Document Async
curl --request POST \
  --url https://dev.api.runpulse.com/extract_async \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "file-url": "<string>",
  "schema": {},
  "pages": "<string>",
  "chunk_size": 123,
  "extract_figure": false,
  "figure_description": false,
  "return_html": false,
  "schema_prompt": "<string>"
}
'
{
  "job_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "status": "pending",
  "message": "Job queued for processing"
}

​
Large Document Response Structure

For documents exceeding 70 pages, the completed job result includes a URL structure: 
{
  "created_at": "timestamp",
  "job_id": "job-id",
  "result": {
    "is_url": true,
    "url": "https://pulse-studio-api.s3.region.amazonaws.com/results/...",
    "plan-info": {
      "pages_used": 0,
      "tier": "foundation"
    }
  },
  "status": "completed",
  "updated_at": "timestamp"
}

​
Key Points:

  • Documents over 70 pages return a URL containing the complete response
  • URLs automatically expire after 24 hours
  • No changes required to your API request structure
  • For documents under 70 pages, the API continues to return results directly in the result field

​
Implementation Tips:

  1. Check if result contains "is_url": true
  2. If true, fetch the complete document data from the provided URL
  3. Store URLs securely as they contain your processed results

Authorizations

​
x-api-key
string
header
required

API key for authentication

Body

application/json
​
file-url
string<uri>
required

URL of the file to process

​
schema
object

JSON schema for structured data extraction

​
pages
string

Page range to process

​
chunk_size
integer

Custom chunk size in characters

​
extract_figure
boolean
default:false

Extract figures and images

​
figure_description
boolean
default:false

Generate AI descriptions for figures

​
return_html
boolean
default:false

Return HTML instead of markdown

​
schema_prompt
string

Custom prompt for schema extraction

Response

Job created successfully

​
job_id
string<uuid>

Unique job identifier

​
status
enum<string>

Initial job status

Available options:
pending
​
message
string
Example:

"Job queued for processing"