Start Document Intelligence Job

from sarvamai import SarvamAI
client = SarvamAI(
    api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
)
client.document_intelligence.start(
    job_id="job_id",
)

{
  "job_id": "string",
  "job_state": "Accepted",
  "created_at": "2024-01-15T09:30:00Z",
  "updated_at": "2024-01-15T09:30:00Z",
  "storage_container_type": "Azure",
  "total_files": 0,
  "successful_files_count": 0,
  "failed_files_count": 0,
  "error_message": "",
  "job_details": [
    {
      "inputs": [
        {
          "file_name": "string",
          "file_id": "string"
        }
      ],
      "outputs": [
        {
          "file_name": "string",
          "file_id": "string"
        }
      ],
      "state": "Pending",
      "total_pages": 0,
      "pages_processed": 0,
      "pages_succeeded": 0,
      "pages_failed": 0,
      "error_message": "",
      "error_code": "string",
      "page_errors": [
        {
          "page_number": 1,
          "error_code": "string",
          "error_message": "string"
        }
      ]
    }
  ]
}

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 500
User must have sufficient credits

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

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 500 - 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_filesinteger or nullDefaults to 0

Total input files (always 1)

successful_files_countinteger or nullDefaults to 0

Files that completed successfully

failed_files_countinteger or nullDefaults to 0

Files that failed

error_messagestring or nullDefaults to

Job-level error message

job_detailslist of objects or null

Per-file processing details with page metrics

Authentication

Path parameters

Response

Errors