read_pdf
Extract text, bounding boxes, and metadata from PDF documents using OCR. Returns comprehensive markdown-formatted content for AI workflows, including all pages in the response.
Instructions
Read a PDF document and return the complete OCRResponse as a dictionary.
Returns the full OCR response including all pages, not just the first page. The response includes pages with markdown content, bounding boxes, and other OCR metadata.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| absolute_path | Yes |
Input Schema (JSON Schema)
{
"properties": {
"absolute_path": {
"title": "Absolute Path",
"type": "string"
}
},
"required": [
"absolute_path"
],
"title": "read_pdfArguments",
"type": "object"
}