How to follow this process

1. Set up the development environment
   Install Python and use an IDE such as PyCharm or VS Code.

2. Create a project folder
   Organize the project with folders for source documents, extracted JSON, chunks, and final test files.

3. Add source documents
   Place sample Word, PDF, Excel, text, Markdown, or CSV files in the dataset folder.

4. Run the Python pipeline
   The pipeline scans the files, extracts text, and prepares the content for search.