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

Identity Document → Ask

AI-generated

Overview

This node processes identity documents by asking a specific question about the document content using AI models. It supports input via a public URL or binary data from a previous node. The node is useful for extracting specific information or insights from identity documents such as passports, ID cards, or other personal documents by querying them with custom questions.

Use Case Examples

  1. Extracting the main findings or details from an identity document PDF by providing its URL and asking a question like 'What is the full name on the document?'
  2. Using binary data from a scanned image of an identity document to ask about the document's expiration date.

Properties

Name Meaning
Input Type How to provide the identity document, either via a public URL or binary data from a previous node.
Identity Document URL Public URL of the identity 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 to use for processing the document. Higher tiers produce better results but cost more credits.
Question The question to ask about the identity document. Minimum 4 characters.
Document ID Optional identifier for usage tracking. Returned in the response.

Output

JSON

  • answer - The AI-generated answer to the question asked about the identity document.
  • documentId - The optional identifier provided for usage tracking, returned in the response.
  • metadata - Additional metadata about the processed identity document and the AI model used.

Dependencies

  • An API key credential for the PDF Vector API

Troubleshooting

  • Ensure the input document URL is publicly accessible if using URL input type.
  • Verify the binary data field name matches the output of the previous node if using binary input.
  • The question must be at least 4 characters long to be accepted.
  • Check API credentials and domain configuration if authentication errors occur.
  • Handle errors gracefully by enabling 'Continue On Fail' to process multiple items without stopping on errors.

Links

Discussion