E-commerce platform powered by agents with vector search, recommendations, order/cart management capabilities.
# S-TORE: AI-Powered E-commerce Platform
A full-stack e-commerce platform featuring an intelligent AI shopping assistant, vector-based product search with Pinecone, and a modern React/Next.js frontend. **Chatbot with advanced product search, recommendations, and order/cart management.**


## Features
### **AI Shopping Assistant**
- Natural language product search and recommendations
- State-of-the-art AI with 1M token context window
- Advanced conversation memory and tool orchestration
- AI-driven product suggestions based on user behavior
### **Advanced Search & Discovery**
- Vector-based product discovery using Pinecone
- Find products by description, features, or use cases
- Price range, brand, category, ratings, and availability
- Context-aware product suggestions
### **Complete E-commerce Experience**
- Persistent cart with real-time updates
- Favorites, likes, and personalized settings
- Real-time stock management and availability
## Architecture
```
├── Frontend (Next.js)
│ ├── Modern UI
│ ├── Responsive design & animations
│ ├── Real-time chat interface
│ └── Shopping cart & product pages
│
├── Backend API (Flask + Python)
│ ├── RESTful API endpoints
│ ├── JWT authentication
│ ├── Database models & services
│ └── AI chatbot integration
│
├── AI Services
│ ├── Google Gemini Flash 2.0
│ ├── LangChain orchestration
│ ├── Pinecone vector database
│ └── Sentence Transformers
│
└── Data Layer
├── SQLite database (for dev)
├── Vector embeddings
└── Session management
```
## Quick Start
### Prerequisites
- **Node.js** 18+ (for frontend)
- **Python** 3.12+ (for backend)
- **Google AI Studio** API key
- **Pinecone** account and API key
### Tech
- **Language Model**: Google Gemini Flash 2.0
- **Framework**: LangChain for orchestration
- **Vector Database**: Pinecone for semantic search
- **Embeddings**: Sentence Transformers
### Development GuideliGoogle's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.