For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
CommunityAPI StatusAPI PricingSign Up
DocumentationAPI ReferencesCookbookIntegrationDeveloper Tools
DocumentationAPI ReferencesCookbookIntegrationDeveloper Tools
  • API Reference
    • Introduction
    • Authentication
    • Access to Beta APIs
    • Meta Prompt Guide
  • Endpoints
      • POSTCreate Document Intelligence Job
      • POSTGet Document Intelligence Upload URLs
      • POSTStart Document Intelligence Job
      • GETGet Document Intelligence Job Status
      • POSTGet Document Intelligence Download URLs
LogoLogo
CommunityAPI StatusAPI PricingSign Up
EndpointsDocument Intelligence

Start Document Intelligence Job

||View as Markdown|
POST
https://api.sarvam.ai/doc-digitization/job/v1/:job_id/start
POST
/doc-digitization/job/v1/:job_id/start
$curl -X POST https://api.sarvam.ai/doc-digitization/job/v1/job_id/start \
>     -H "api-subscription-key: <apiSubscriptionKey>" \
>     -H "Content-Type: application/json" \
>     -d '{}'
1{
2  "job_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
3  "job_state": "Accepted",
4  "created_at": "2024-01-15T09:30:00Z",
5  "updated_at": "2024-01-15T09:30:00Z",
6  "storage_container_type": "Azure",
7  "total_files": 1,
8  "successful_files_count": 0,
9  "failed_files_count": 0,
10  "error_message": "",
11  "job_details": [
12    {
13      "inputs": [
14        {
15          "file_name": "invoice_2024_01.pdf",
16          "file_id": "file_1234567890abcdef"
17        }
18      ],
19      "outputs": [
20        {
21          "file_name": "invoice_2024_01_output.json",
22          "file_id": "file_abcdef1234567890"
23        }
24      ],
25      "state": "Pending",
26      "total_pages": 5,
27      "pages_processed": 0,
28      "pages_succeeded": 0,
29      "pages_failed": 0,
30      "error_message": "",
31      "error_code": null,
32      "page_errors": []
33    }
34  ]
35}
Validates the uploaded file and starts processing. **Validation Checks:** - File must be uploaded before starting - File size must not exceed 200 MB - PDF must be parseable by the PDF parser - ZIP must contain only JPEG/PNG images - ZIP must be flat (no nested folders beyond one level) - ZIP must contain at least one valid image - Page/image count must not exceed 10 (returns `422` with `max_page_limit_exceeded` if exceeded) - User must have sufficient credits **Processing:** Job runs asynchronously. Poll the status endpoint or use webhook callback for completion notification.
Was this page helpful?
Previous

Get Document Intelligence Job Status

Next
Built with

Validates the uploaded file and starts processing.

Validation Checks:

  • File must be uploaded before starting
  • File size must not exceed 200 MB
  • PDF must be parseable by the PDF parser
  • ZIP must contain only JPEG/PNG images
  • ZIP must be flat (no nested folders beyond one level)
  • ZIP must contain at least one valid image
  • Page/image count must not exceed 10 (returns 422 with max_page_limit_exceeded if exceeded)
  • User must have sufficient credits

Processing: Job runs asynchronously. Poll the status endpoint or use webhook callback for completion notification.

Authentication

api-subscription-keystring
API Key authentication via header

Path parameters

job_idstringRequiredformat: "uuid"
The unique identifier of the job

Response

Successful Response
job_idstringformat: "uuid"

Job identifier (UUID)

job_stateenum
Current job state
created_atstringformat: "date-time"

Job creation timestamp (ISO 8601)

updated_atstringformat: "date-time"

Last update timestamp (ISO 8601)

storage_container_typeenum
Storage backend type
Allowed values:
total_filesintegerDefaults to 0

Total input files (always 1)

successful_files_countintegerDefaults to 0
Files that completed successfully
failed_files_countintegerDefaults to 0
Files that failed
error_messagestringDefaults to

Job-level error message

job_detailslist of objects

Per-file processing details with page metrics

Errors

400
Bad Request Error
403
Forbidden Error
429
Too Many Requests Error
500
Internal Server Error
503
Service Unavailable Error