Welcome to the Hello TT chatbot project, developed for the Temasek X SUTD Gen AI Hackathon 2024. Hello TT is an innovative chatbot designed to assist users in resolving issues by utilizing textual information and screenshots. This chatbot creates a step-by-step guide to solving various issues, complemented by relevant screenshots for a more intuitive assistance experience.
- Textual Issue Resolution: Generates step-by-step guides based on textual information to resolve user queries.
- Screenshot Integration: Displays relevant screenshots alongside the guides to enhance understanding and provide visual assistance.
- AI-Powered: Utilizes OpenAI's GPT-3.5 and GPT-4-Vision models for advanced information processing and image recognition.
- Retrieval Augmented Generation: Employs a sophisticated mechanism to retrieve relevant information chunks from a user guide, ensuring accuracy and relevance in the solutions provided.
- Streamlit UI: Features an intuitive and user-friendly UI built with Streamlit, making it accessible for users with varying levels of technical expertise.
Due to NDA constraints, this chatbot has been sanitized of all training data used during the hackathon.
Follow these steps to set up and run the Hello TT chatbot on your local machine.
- Python 3.9 or above
-
Clone the Repository
git clone <repository-url>
Replace
<repository-url>
with the actual URL of this GitHub repository. -
Create a Virtual Environment
python -m venv venv
-
Activate the Virtual Environment
-
On Mac or WSL on Windows:
source venv/bin/activate
-
On Windows (if not using WSL):
.\venv\Scripts\activate
-
-
Install Required Packages
pip install -r requirements.txt
-
Set Up Environment Variables
Copy the
.env.example
file to.env
and replace the placeholders with the actual values.cp -i .env.example .env
-
To run the Hello TT chatbot:
streamlit run hackathon.py