For AI agents: a documentation index is available at the root level at /llms.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Creates and starts a digitise job from files or pre-uploaded handles. Digitise converts documents into structured HTML or Markdown while preserving layout.
**Input:** Exactly one of `file` and `upload_ids` must be provided. Use `POST /doc-ai/v1/job/upload` to obtain upload IDs.
**Processing:** the job runs asynchronously. Poll `GET /doc-ai/v1/job/{job_id}/status` until a terminal status (`completed`, `partially_completed`, `failed`, `rejected`), then fetch output via the results or download-url endpoints.
Digitise JSON results include blocks with text, tag and bounding box.
Authentication
api-subscription-keystring
API Key authentication via header
Request
This endpoint expects a multipart form with multiple files.
filefilesOptional
Document file(s) to digitise. Repeatable multipart part. Exactly one of file and upload_ids must be provided.
upload_idsstringOptional
Comma-separated upload IDs returned by POST /doc-ai/v1/job/upload. Exactly one of file and upload_ids must be provided.
languagestringOptionalDefaults to en-IN
Language code of the document (BCP-47), e.g. en-IN, hi-IN.
output_formatenumOptionalDefaults to html
Output format of the digitised document.
Allowed values:
content_typeenumOptionalDefaults to printed
Nature of the document content.
Allowed values:
auto_orientstringOptionalDefaults to true
Automatically correct page orientation before processing. Boolean sent as text: true or false.
modelstringOptionalDefaults to sarvam-vision-v1
Model to use for digitisation.
Response
Created
job_idstring
The unique identifier of the job.
statusstring
Current status of the job.
run_idstring
The unique identifier of the job run.
Errors
400
Bad Request Error
402
Payment Required Error
403
Forbidden Error
413
Content Too Large Error
429
Too Many Requests Error
503
Service Unavailable Error
Creates and starts a digitise job from files or pre-uploaded handles. Digitise converts documents into structured HTML or Markdown while preserving layout.
Input: Exactly one of file and upload_ids must be provided. Use POST /doc-ai/v1/job/upload to obtain upload IDs.
Processing: the job runs asynchronously. Poll GET /doc-ai/v1/job/{job_id}/status until a terminal status (completed, partially_completed, failed, rejected), then fetch output via the results or download-url endpoints.
Digitise JSON results include blocks with text, tag and bounding box.