Codia PDF To Design

codia-pdf-to-design

Runtime And Auth

Use the local codia-design CLI for this feature. Before calling the API, verify that codia-design is available. If it is missing and global npm installs are allowed, install it with npm install -g @codia-ai/codia-design-cli. Then check codia-design auth status; if it is not connected, run codia-design auth login --platform codex or bind an API key with codia-design auth set --api-key api_key_xxx. Never print API keys or ~/.codia/design-skills/config.json.

Extract one or more pages of a PDF into structured design trees (one tree per page).

CLI Command

codia-design pdf-to-design --pdf <PATH|URL> --pages <0,1,2> [--out FILE]

Note: --pages is zero-based. Use 0 for the first page and 1 for the second page. pdf-to-ppt uses the same zero-based convention through the Task API.

Parameters

Two input modes:

• Local file (--pdf ./doc.pdf) → multipart upload, the CLI repeats page_no once per page (0, 1, 2) when --pages 0,1,2 is provided
• URL (--pdf https://...) → JSON request, the API expects page_no as a number array such as [0,1,2]; the CLI builds this from --pages

Response

{
  "ok": true,
  "data": {
    "configuration": {
      "scalingFactor": 1.0,
      "baseWidth": 260.94,
      "measurementUnit": "px"
    },
    "size": { "width": 260.94, "height": 240.94 },
    "pages": [
      {
        "page_no": 0,
        "schema": {
          "elementId": "Page 1_1",
          "elementType": "Layer",
          "childElements": []
        }
      }
    ]
  }
}

Top-level fields

pages[i].schema field (design tree node)

Each schema node is consistent with the visualElement structure of image-to-design, including:

Usage Example

# Local PDF, process first 3 pages
codia-design pdf-to-design --pdf ./report.pdf --pages 0,1,2 --out result.json

# URL pattern
codia-design pdf-to-design --pdf https://example.com/doc.pdf --pages 0,1 --out result.json

Iterate over all pages of text:

const { data } = require('./result.json');
for (const [i, page] of data.pages.entries()) {
  console.log('-- Page', i, '--');
  extractText(page.schema).forEach(t => console.log(t));
}

function extractText(node, acc = []) {
  if (node.elementType === 'Text') acc.push(node.contentData?.textValue);
  node.childElements?.forEach(c => extractText(c, acc));
  return acc;
}

Input Limits

The maximum rendering size and file size of each page of the input PDF depend on the plan tier:

Errors & Billing

Credits: 13 credits/page. After the command completes, the CLI checks available_credits and reminds the user if the remaining balance is below 2x the estimated page cost; this does not block generation. · Duration: Synchronous, long documents grow linearly by the number of pages