DESCRIPTION.md

# Development of a Virtual Assistant Powered by the GPT-4 language model

This project is an innovative initiative by [Tall Tree Health](https://www.talltreehealth.ca/) to enhance the customer experience by integrating cutting-edge conversational Artificial Intelligence (AI) technologies. The goal is to build an advanced question-answering (Q&A) chatbot that seamlessly responds to real-time queries, providing users with personalized guidance as they navigate the healthcare landscape offered by Tall Tree. The Retrieval Augmented Generation (RAG) technique is used to improve the accuracy and reliability of chatbot responses by fetching relevant and up-to-date information from the Tall Tree database.

# Computational Tools

The application was developed using the Python programming language. The back-end architecture was built using LangChain, while the front-end, specifically the chat interface, was created using Streamlit. At the core of our chatbot is OpenAI’s GPT-4 (Generative Pre-trained Transformer 4), a state-of-the-art language model known for its advanced comprehension and generation capabilities. For storage of the embeddings and efficient similarity search, the Qdrant vector database was chosen. LangChain offers seamless integration with both the OpenAI API and Qdrant, ensuring a smooth workflow.