Document Processor for RAG Chatbot

This project handles document ingestion and processing for the RAG (Retrieval-Augmented Generation) chatbot. It's separate from the main chatbot deployment to keep the cloud instance clean and focused.

Directory Structure

• src/: Python source code for document processing
• data/input/: Place input documents here
• data/output/: Processed data will be stored here

Setup

1. Create a virtual environment:

   python -m venv .venv
   source .venv/bin/activate  # On Linux/Mac
   # or
   .venv\Scripts\activate  # On Windows

2. Install dependencies:

   pip install -r requirements.txt

Usage

1. Place documents to be processed in the data/input/ directory
2. Run the processing scripts from the src/ directory
3. The processed data will be stored in the data/output/ directory, ready for use by the RAG engine