fusor-scraper

Fusor Chatbot

Overview

The Fusor Chatbot is designed to facilitate access to information about Farnsworth fusion reactors. It taps into a database of content from fusor.net, enabling users to ask questions and receive informative responses. The chatbot utilizes Pinecone's vector database for information retrieval and OpenAI's GPT-4-turbo for generating responses, to provide accurate and relevant answers. This tool is useful for hobbyists, or anyone interested in the domain of fusors, offering a streamlined way to navigate through a wealth of data.

Features

• Targeted Information Retrieval: Leverages Pinecone's vector database for extracting information from a specialized dataset comprised of discussions and posts related to Farnsworth fusion reactors.
• Natural Language Processing: Utilizes OpenAI's GPT-4-turbo to generate responses that are contextually appropriate, enhancing the user's understanding of the topic.
• Streamlit-Based Interface: A straightforward and interactive interface built with Streamlit, simplifying the user interaction process and making the retrieval of complex information more accessible.

Installation & Setup

Prerequisites

• Python 3.x
• Poetry for dependency management

Installation Steps

1. Clone the repository:

   git clone https://github.com/olivia-li/fusor-scraper.git
   cd fusor-chatbot
   
   

2. Install dependencies:

   poetry install
   
   

3. Set up environment variables: Create a .env file in the root directory and add the following variables:

     OPENAI_API_KEY=your_openai_api_key
     PINECONE_API_KEY=your_pinecone_api_key
     DB_NAME=your_database_name
     DB_USER=your_database_user
     DB_PASSWORD=your_database_password
     DB_HOST=your_database_host
   
   

4. Run the application:

     poetry run streamlit run app.py
   
   

Usage

After starting the application, navigate to the local URL provided by Streamlit (http://localhost:8501). Enter your question in the input field and receive a response generated by the chatbot.

Contributing

Contributions are welcome! If you have suggestions or improvements, feel free to fork the repository and submit a pull request.

License

MIT License