POST
/
api
/
v1
/
document-extractions
/
{workflowName}
curl --request POST \
  --url https://api.repromptai.com/api/v1/document-extractions/{workflowName} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "file_url": "https://example-bucket.s3.amazonaws.com/uploads/document.pdf?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=EXAMPLEKEY%2F20240527%2Fus-west-1%2Fs3%2Faws4_request&X-Amz-Date=20240527T004338Z&X-Amz-Expires=900&X-Amz-Signature=example-signature&X-Amz-SignedHeaders=host",
  "doc_type": "mega_invoice"
}'
{
  "file_id": "file_12345",
  "job_id": "job_12345",
  "file_metadata": "{\"pdf_type\": \"unknown\"}",
  "extraction": "{}"
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

​
workflowName
string
required

Body

application/json
​
file_url
string

The URL of the document to be processed

​
doc_type
string

Optional document type to help with classification, extraction, and validation

Response

200 - application/json
Document submitted successfully
​
file_id
string

The unique identifier of the file

​
job_id
string

The unique identifier of the job

​
file_metadata
string

Metadata of the file

​
extraction
string

Extraction details