PDF Vector icon

PDF Vector

Convert PDFs, Word, Excel documents, and images to clean markdown, extract structured data with AI, process invoices with specialized parsing, and search millions of academic papers across PubMed, ArXiv, Google Scholar, and more.

Actions18

Document → Parse

AI-generated

Overview

The node parses documents such as PDFs, Word, Excel, CSV, and images to extract clean markdown and structured data using AI models. It supports input via a public URL or binary data from a previous node. Users can select different AI model tiers based on document complexity and size, and optionally include page-separated markdown in the output. This node is useful for automating document processing, data extraction, and content conversion tasks.

Use Case Examples

  1. Parsing a PDF invoice to extract structured data for accounting automation.
  2. Converting a Word document into markdown for content management.
  3. Extracting tables from an Excel file for data analysis.

Properties

Name Meaning
Input Type How to provide the document, either via a public URL or binary data from a previous node.
Document URL Public URL of the document file (PDF, DOCX, XLSX, CSV, PNG, JPG). Required if Input Type is URL.
Input Binary Field Name of the binary property from a previous node containing the file. Required if Input Type is Binary Data.
Model AI model tier for parsing. Higher tiers support more complex documents but cost more credits.
Include Pages Whether to include page-separated markdown in the pages array. The full document markdown is still returned.
Document ID Optional identifier for usage tracking. Returned in the response.

Output

JSON

  • markdown - The full document content converted to markdown format.
  • pages - An array of page-separated markdown content if 'Include Pages' is enabled.
  • documentId - The optional identifier provided for usage tracking, returned in the response.

Dependencies

  • An API key credential for the PDF Vector API

Troubleshooting

  • Common issues include invalid or inaccessible document URLs, unsupported file formats, or exceeding size/page limits of the selected AI model tier.
  • Error messages may indicate network issues, authentication failures, or input validation errors. Ensure the API key is valid and the input document meets the format and size requirements.

Links

Discussion