rednote-hilab/dots.mocr

Document layout + OCR (vLLM). Accepts one image_url or a document_url PDF; no text-only input. Default method: markdown. parse_layout* emit layout regions; ocr / markdown emit strings.

Output by method

Method	Payload kind	Image `content.object`	Payload
`markdown`	markdown	none	Reading-order Markdown string (default)
`ocr`	markdown	none	Plain OCR text
`parse_layout`	json	`dots_mocr.parse_layout.regions`	Region items with `bbox_xywh`, `label`, `text`
`parse_layout_only`	json	`dots_mocr.parse_layout_only.regions`	Region items with `bbox_xywh` and `label`, no text

The payload kind is the same for an image and for each page of a PDF. Text mode emits the payload alone for one image, and one <document> / <page> block per PDF, each page declaring its kind in format. In JSON mode an image content is the tagged container above, and a document page content is always document.page.blocks. Coordinates are normalized 0-1 at precision decimals (default 4). See Methods & Response Format.

markdown: reading-order Markdown page output. (default)
parse_layout: structured layout parse with text for tables, figures, and reading order.
parse_layout_only: layout regions and bounding boxes without transcribed text.
ocr: plain OCR text extraction.

Request

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.vlm.run/v1/openai",
    api_key="<VLMRUN_API_KEY>",
)

response = client.chat.completions.create(
    model="rednote-hilab/dots.mocr",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "document_url",
                    "document_url": {
                        "url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/finance.sec-filings/tsla-8k.pdf"
                    },
                },
            ],
        }
    ],
    extra_body={"method": "markdown"},
)

print(response.choices[0].message.content)

curl https://gateway.vlm.run/v1/openai/chat/completions \
  -X POST \
  -H "Authorization: Bearer $VLMRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "rednote-hilab/dots.mocr",
    "method": "markdown",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "document_url",
            "document_url": {
              "url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/finance.sec-filings/tsla-8k.pdf"
            }
          }
        ]
      }
    ]
  }'

Response

Text mode
JSON mode
JSON mode (parse_layout)

One <document> block per PDF, one <page> block per page. A failed page is self-closing, with status="error" and no body:

<document file_name="tsla-8k.pdf" file_hash="sha256:1b7f…" file_bytes="182417" mimetype="application/pdf" num_pages="2" dpi="72">
<page page_index="0" format="markdown" page_width="992" page_height="1400">
# Annual Report 2024

## Overview
The company reported revenue of $1.2M.
</page>
<page page_index="1" format="markdown" page_width="992" page_height="1400" status="error"/>
</document>

With method="parse_layout" each page body is the block container instead, and the page carries format="json".

One document entry; each page’s content is one Markdown block. A failed page carries "status": "error" and no content:

{
  "model": "rednote-hilab/dots.mocr",
  "method": "markdown",
  "data": [
    {
      "object": "document",
      "file_name": "tsla-8k.pdf",
      "file_hash": "sha256:1b7f...",
      "file_bytes": 182417,
      "mimetype": "application/pdf",
      "num_pages": 2,
      "dpi": 72,
      "pages": [
        {
          "object": "document.page",
          "page_index": 0,
          "page_width": 992,
          "page_height": 1400,
          "content": {
            "object": "document.page.blocks",
            "items": [
              {"index": 0, "text": "# Annual Report 2024\n\n## Overview\nThe company reported revenue of $1.2M."}
            ]
          }
        },
        {"object": "document.page", "page_index": 1, "page_width": 992, "page_height": 1400, "status": "error"}
      ]
    }
  ]
}

With method="parse_layout", each page’s blocks carry the geometry:

{
  "object": "document.page",
  "page_index": 0,
  "page_width": 992,
  "page_height": 1400,
  "content": {
    "object": "document.page.blocks",
    "items": [
      {"index": 0, "bbox_xywh": [0.0343, 0.0143, 0.1774, 0.0343], "label": "title", "text": "Annual Report 2024"},
      {"index": 1, "bbox_xywh": [0.0343, 0.0857, 0.6048, 0.4286], "label": "table", "text": "| Item | Qty |\n| --- | --- |"}
    ]
  }
}

On an image the same request returns {"object": "dots_mocr.parse_layout.regions", "items": [...]}.

To get the structured layout regions instead (bounding boxes + labels), set method="parse_layout"; see the output-by-method table above.

Overview

Guides

API Reference

Misc

rednote-hilab/dots.mocr

Output by method

Request

Response

​Output by method

​Request

​Response

Output by method

Request

Response