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

Bank Statement → Extract

AI-generated

Overview

This node extracts structured data from bank statement files using AI. It supports input via a public URL or binary data from a previous node. Users provide an extraction prompt and a JSON schema to define the data structure to extract. The node supports multiple AI model tiers for different capabilities and file types. It is useful for automating data extraction from various bank statement formats such as PDF, DOCX, XLSX, CSV, PNG, and JPG.

Use Case Examples

  1. Extracting transaction details like date, amount, and description from a PDF bank statement.
  2. Extracting summary information such as account holder name and balance from an image of a bank statement.
  3. Using a JSON schema to extract specific fields like title and summary from a bank statement document.

Properties

Name Meaning
Input Type How to provide the bank statement file, either via a public URL or binary data from a previous node.
Bank Statement URL Public URL of the bank statement file, 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 extraction, affecting capabilities and cost.
Extraction Prompt Instructions for what data to extract from the bank statement, minimum 4 characters.
JSON Schema JSON Schema defining the structure of the data to extract, required.
Document ID Optional identifier for usage tracking, returned in the response.

Output

JSON

  • title - Extracted title from the bank statement as defined by the JSON schema.
  • summary - Extracted summary or other structured data from the bank statement as defined by the JSON schema.
  • documentId - Optional document identifier returned if provided.

Dependencies

  • An API key credential for the PDF Vector API

Troubleshooting

  • Ensure the input file URL is publicly accessible if using URL input type.
  • Verify the binary property name matches the output of the previous node if using binary input.
  • The extraction prompt must be at least 4 characters long to be valid.
  • The JSON schema must be valid and correctly define the expected output structure.
  • Errors related to API calls may include status codes or messages; check credentials and network connectivity.

Links

Discussion