parse-pdf

name	parse_pdf
description	Extract text and metadata from a PDF file.
type	tool
category	document
tool	{"module":"app.skills.parse_pdf.tool","function":"parse_pdf","async":true}
metadata	{"author":"oniva","version":"1.0.0"}
audit-level	basic

Parse PDF

Extract text and metadata from PDF documents.

Usage

result = await parse_pdf(path="/documents/report.pdf", max_pages=10)

Parameters

Parameter	Type	Required	Default	Description
path	string	Yes	-	Path to the PDF file
max_pages	int	No	10	Maximum pages to extract text from

Response

{
  "success": true,
  "metadata": {
    "title": "Annual Report 2024",
    "author": "Financial Corp",
    "pages": 45
  },
  "pages_extracted": 10,
  "text": "Full extracted text content...",
  "truncated": false
}

Error Response

{
  "success": false,
  "error": "File not found: /path/to/file.pdf"
}