​
Overview

The File Extraction tools allow you to extract information from files using their base64 representation. This is particularly useful for analyzing images or documents where you need to extract text or other relevant data.

​
Key Features

  • PDF_EXTRACT_TEXT: Extract text from PDF files.
  • DOCX_EXTRACT_TEXT: Extract text from DOCX files.
  • EXCEL_EXTRACT_TEXT: Extract structured data from Excel files.

​
Example: Extract Data from Base64 Files

- id: extract_pdf
  tool: PDF_EXTRACT_TEXT
  config:
    []
  input:
    - name: pdf_base64
      value: "{{secrets.PDF_FILE_BASE64}}"
- id: extract_docx
  tool: DOCX_EXTRACT_TEXT
  config:
    []
  input:
    - name: docx_base64
      value: "{{secrets.DOCX_FILE_BASE64}}"
- id: extract_pdf
  tool: PDF_EXTRACT_TEXT
  config:
    []
  input:
    - name: pdf_base64
      value: "{{secrets.PDF_FILE_BASE64}}"