Create Parsing Job

POST/v1/parsing/jobs

Authorization

Authorizationstringrequired

Bearer token for API authentication. Format: `Bearer YOUR_API_KEY`

Request Body

file_idstringrequired

The ID of the file to parse

element_typesElementType[]

The elements to extract from the document

chunking_strategyenum

Strategy used for chunking document content.

Possible values

page

return_formatenum

Format options for the returned document content.

Possible values

htmlmarkdownplain

modeenum

The mode of the document parser.

Possible values

fasthigh_quality

Response Body

idstringrequired

The ID of the job

file_idstringrequired

The ID of the file to parse

filenamestring

The name of the file

statusenumrequired

ParsingJobStatus

Possible values

pendingin_progresscancelledcompletedfailed

errorobject

The error of the job

resultDocumentParserResult

The result of the job

started_atstring

The started time of the job

finished_atstring

The finished time of the job

created_atstring(date-time)

The creation time of the job

updated_atstring

The updated time of the job

objectstringdefault: parsing_job

The type of the object

Request

POST/v1/parsing/jobs

from mixedbread import Mixedbread

mxbai = Mixedbread(api_key="YOUR_API_KEY")

response = mxbai.parsing.jobs.create(
    file_id="f47ac10b-58cc-4372-a567-0e02b2c3d479",
    element_types=["text", "title", "picture"],
    chunking_strategy="page",
    return_format="markdown",
    mode="high_quality",
)

print(response)

Response

JSON

{
  "id": "job_xyz789",
  "file_id": "f47ac10b-58cc-4372-a567-0e02b2c3d479",
  "status": "pending",
  "error": null,
  "result": null,
  "started_at": null,
  "finished_at": null,
  "created_at": "2025-01-15T17:00:00.000Z",
  "updated_at": null,
  "object": "parsing_job"
}