A Python utility that can take a bunch of files and output them into a single training file as .txt for using with LLMs.
This script is designed to work in a Google Colab notebook that you create.
Instructions:
- Paste the Python script from convert-data-to-text.py into a blank Google Colab notebook.
- Select the menu at top, Runtime > "Run All".
- See the choose file and upload box appear below the script (Screenshot below).
- Upload your input file (supports only xlsx and zip right now), and the script will join all the file contents and output structured data in a .txt file.