ERMA

Educational Research Methods Chatbot - Setup Guide

This guide provides instructions for setting up and running the Educational Research Methods Chatbot.

Prerequisites

• Python 3.8 or higher
• pip (Python package installer)
• An OpenAI API key for Command R+ access

Installation

1. Clone or download the repository to your local machine.

2. Navigate to the project directory:

   cd research_methods_chatbot
   

3. Install the required dependencies:

   pip install -r src/requirements.txt
   

4. Create a .env file in the src directory with your OpenAI API key:

   OPENAI_API_KEY=your_api_key_here
   

Running the Chatbot

1. Start the application:

   cd src
   python main.py
   

2. Open your web browser and navigate to:

   http://localhost:8080
   

3. You should see the chatbot interface where you can ask questions about educational research methods.

Features

• Research Method Recommendations: Get advice on which research methods are appropriate for your educational research project.
• APA7 Citations: All information is provided with proper APA7 citations from published scientific resources.
• Conversation History: The chatbot maintains context throughout your conversation for more coherent interactions.
• Responsive Design: Works on both desktop and mobile devices.

Architecture

The chatbot uses a Retrieval Augmented Generation (RAG) architecture with the following components:

1. Command R+ LLM: Powers the natural language understanding and generation.
2. Vector Database: Stores embeddings of research methods information for efficient retrieval.
3. FastAPI Backend: Handles API requests and manages the RAG pipeline.
4. Web Frontend: Provides a user-friendly interface for interacting with the chatbot.

Customization

To customize the chatbot with additional research methods information:

1. Add your information to the research_methods_info.md file.
2. Restart the application to rebuild the vector database with the new information.

Troubleshooting

• If you encounter CORS issues, check that the frontend URL matches the allowed origins in the backend configuration.
• If the chatbot doesn't provide citations, ensure that the research methods information is properly formatted with source information.
• If you receive API errors, verify that your OpenAI API key is valid and has sufficient credits.

License

This project is licensed under the MIT License - see the LICENSE file for details.