​
What can you do with it?

Process files uploaded by users or from URLs. Extract text from documents, parse data files, and handle various file formats including PDFs, Office documents, images, and data files.

​
How to use it?

​
Basic Command Structure

/file-inputs
action: process uploaded files
file type: what kind of files to process

​
Parameters

  • action: What to do with the files (extract, parse, convert)
  • file type: Type of files to process (pdf, excel, word, csv, json)
  • file name (optional): Specific file to process
  • pattern (optional): File pattern to match multiple files
  • output format (optional): How to save processed data

​
Response Format

Returns processed data in the requested format or extracted text content from documents.

​
Examples

​
Basic Usage

Extract text from a PDF:

/file-inputs
action: extract text from uploaded PDF
file name: report.pdf

​
Advanced Usage

Process multiple Excel files:

/file-inputs
action: convert all Excel files to JSON
pattern: *.xlsx
output format: separate JSON files

​
Specific Use Case

Parse and combine CSV data:

/file-inputs
action: combine all CSV files
pattern: sales_*.csv
output format: single JSON file with all data

​
Notes

  • Automatically detects and parses JSON and CSV files
  • Extracts text from PDFs, Word (.docx), Excel (.xlsx), PowerPoint (.pptx)
  • Older Office formats (.xls, .doc, .ppt) are not supported
  • Use exactMatch option for filenames with special characters
  • Excel dates are properly formatted during extraction