Assignment 09 - Laptop Consultant Chatbot

A conversational AI chatbot that provides personalized laptop recommendations using Azure OpenAI and ChromaDB vector search.

Overview

This project implements a Retrieval-Augmented Generation (RAG) system that:

• Understands user laptop requirements through natural language
• Searches a vector database of laptop specifications
• Provides tailored recommendations using Azure OpenAI's chat completion API

Files

• Assignment_09.py - Complete Python script implementation
• Assignment_09.ipynb - Jupyter Notebook with detailed documentation
• README.md - This file

Requirements

pip install openai chromadb

Configuration

Set your Azure OpenAI credentials in the environment variables:

• AZURE_OPENAI_EMBEDDING_API_KEY
• AZURE_OPENAI_EMBEDDING_ENDPOINT
• AZURE_OPENAI_LLM_API_KEY
• AZURE_OPENAI_LLM_ENDPOINT

Usage

Python Script

# Using virtual environment (recommended)
source .venv/bin/activate
python Assignment_09.py

# Or using full path
"/Users/haopq1/AI Course/Assignment_09/.venv/bin/python" Assignment_09.py

Jupyter Notebook

Open Assignment_09.ipynb in Jupyter Lab/Notebook for step-by-step execution with detailed explanations.

Features

• Vector Search: ChromaDB for semantic similarity matching
• AI Recommendations: Azure OpenAI GPT-4o-mini for personalized suggestions
• Automated Testing: Predefined queries for business, gaming, and student use cases
• Clean Output: Professional console messages without emojis

Sample Queries

The system automatically processes three test scenarios:

1. Lightweight business laptop with long battery life
2. High-performance gaming laptop with best graphics
3. Budget-friendly laptop for student tasks

Architecture

1. Embedding Generation: Convert laptop descriptions to vectors
2. Vector Storage: Store embeddings in ChromaDB collection
3. Similarity Search: Find relevant laptops based on user query
4. Context Building: Format retrieved data for LLM
5. AI Response: Generate personalized recommendations

Author

HaoPQ1