---
title: "GET /documents/v1/jobs/{job_id}"
method: GET
path: "/documents/v1/jobs/{job_id}"
tags: ["jobs"]
---

# GET /documents/v1/jobs/{job_id}

`GET /documents/v1/jobs/{job_id}`

## Path parameters

- `job_id` string, required

## Response `200`

Get Job Output

- JobResponse
  - `message` string, nullable — An error message if the job failed This field is optional and will be `None` if the job was successful.
  - `jobId` string, required — The unique identifier for the job This is a public ID that can be used to reference the job in other API calls. It has the format of job-<readable-id>
  - `fileId` string, nullable — The unique identifier for the file associated with the job This is an optional field that will be `None` if the job was submitted with a public URL file.
  - `fileName` string, nullable — The name of the file associated with the job This is an optional field that will be `None` if the job was submitted with a public URL
  - `traceId` string, nullable — The trace ID for the job This value will be `None` if the job is in the `Pending` state. This is used for tracing the job execution in the system. Share this ID with the support team if you need help with a specific job.
  - `pageRange` string, nullable — The page range for the job This value will be `None` if the job was submitted for the entire document. If the job was submitted with a specific page range, this will be in the format "1-5" or "1,3,5"
  - `parsedPages` integer, nullable — The number of pages that were parsed in the job This value will be `None` if the job is still processing or if it failed.
  - `outputs` ParsedJobOutput
    - `chunks` union
      - Chunk[]
        - `content` string, required
        - `page_number` integer, required
      - string[]
    - `pages` unknown
    - `num_pages` integer, nullable
    - `structured_data` StructuredDataResponse
      - `pages` StructuredDataPage[]
        - `page_number` union
          - integer
          - integer[]
        - `json_result` unknown
    - `errors` OutputErrorsResponse
      - `errors` OutputErrorResponse[]
        - `context` string, required
        - `err_message` string, required
  - `chunks` Chunk[], nullable — The chunks of text extracted from the document This field is deprecated and will be removed in a future version. Use `outputs` instead.
    - `content` string, required
    - `page_number` integer, required
  - `document` unknown
  - `structuredOutput` unknown
  - `status` 'failure' | 'pending' | 'processing' | 'successful', required
  - `settings` Settings, required
    - `tableParsingMode` 'tsr' | 'vlm' | 'unknown'
    - `tableOutputMode` 'markdown' | 'html'
    - `tableSummarization` boolean — Whether to summarize the contents of the tables.
    - `tableSummarizationPrompt` string, nullable — The prompt to use for table summarization.
    - `figureSummarization` boolean — Whether to summarize the contents of the figures.
    - `figureSummarizationPrompt` string, nullable — The prompt to use for figure summarization. If not provided, the default prompt will be used.
    - `formDetectionMode` 'vlm' | 'tsr' | 'unknown'
    - `chunkStrategy` 'page' | 'section' | 'fragment' — Chunking strategy determines how the document is chunked into smaller pieces. This is only supported in Markdown mode.
    - `jsonSchema` unknown
    - `structuredExtractionPrompt` string, nullable — Overide the prompt to customize structured extractions. Use this if you want to extract data from a file using a different prompt than the one we use to extract.
    - `modelProvider` 'tensorlake' | 'claude-3-5-sonnet-latest' | 'gpt-4o-mini' — The model provider to use for structured data extraction.
    - `deliverWebhook` boolean — Whether to deliver a webhook when the job is completed. A webhook needs to be configured for this to work. If a webhook is not configured, the job will still be processed but the webhook will not be delivered.
    - `detectSignature` boolean — Boolean to perform signature detection.
    - `skewCorrection` boolean — Skew correction for the document.
    - `disableLayoutDetection` boolean — Whether to disable layout detection.
    - `structuredExtractionSkipOcr` boolean — Whether to skip OCR for structured extraction.
    - `detectStrikethrough` boolean
  - `tasksCompleted` integer, nullable — The number of tasks that have been completed for the job This field is optional and will be `None` if the job is still processing or if it failed.
  - `tasksTotal` integer, nullable — The total number of tasks that are expected to be completed for the job This field is optional and will be `None` if the job is still processing or if it failed.
  - `createdAt` string, required — The timestamp when the job was created
  - `finishedAt` string, nullable — The timestamp when the job was finished, if applicable
  - `labels` object — Additional metadata for the job, that was provided during the parse request.

## Other responses

- `400` — Invalid request
- `401` — Unauthorized. Invalid or missing credentials
- `403` — Forbidden. You do not have permission to access this resource
- `500` — Internal server error

---

[API](https://skmtc.net/tensorlakeai/apis/tensorlake-api.md) · [All operations](https://skmtc.net/tensorlakeai/apis/tensorlake-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/tensorlakeai/tensorlake-api/revisions/fb161f7c0ab7/schema)