Repository files navigation

Redis-powered grocery e-commerce with intelligent shopping assistance.

Redish is an AI-powered grocery shopping platform that combines Redis's speed with LangGraph's intelligent workflow orchestration. Get personalized recipe recommendations, smart product suggestions, and lightning-fast responses through semantic caching.

• Smart Grocery Shopping: AI-powered assistant helps you find ingredients, discover recipes, and manage your cart
• Product Search: Both text and vector-based search across grocery products with embeddings
• Recipe Intelligence: Get ingredient lists with suggested products for any recipe
• Cart Management: Add, view, and manage shopping cart items

• Recipe Ingredients: Ask for ingredients for any recipe and get suggested products
• Product Search: Find products by name, category, or description
• Smart Recommendations: AI suggests alternatives and complementary items
• Cart Management: Add, remove, and view cart items through natural conversation

• Semantic Cache: Similar queries return instantly using Redis LangCache
• Vector Search: Find products using AI-powered similarity search
• Redis as memory layer: for fast data retrieval
• LangGraph Workflows: AI agent routing, tool selection
• Multi-tool Agent: Recipe tools, search tools, cart tools, and knowledge tools

• OpenAI Version Setup: Seeopenai-version/README.md
• AWS Bedrock Version Setup: Seeaws-bedrock-version/README.md
• AWS Bedrock Guardrails: Seeaws-bedrock-version/docs/guardrails.md

This repository contains two versions of the demo:

│ ├── openai-version/       # OpenAI-powered version│   ├── package.json│   ├── index.js│   ├── services/│   └── ...│   └── README.md         # Setup instructions│├── aws-bedrock-version/  # AWS Bedrock version│   ├── package.json│   ├── index.js│   ├── services/│   └── ...│   └── README.md         # Setup instructions└── README.md             # This file

Choose your preferred AI provider:

cd openai-version# Follow setup instructions in openai-version/README.md

cd aws-bedrock-version# Follow setup instructions in aws-bedrock-version/README.md

• Node.js +Express (Backend API)
• Redis (Product store, agentic AI memory, conversational history, and semantic caching with Redis LangCache)
• LangGraph (AI workflow orchestration)
• HTML + CSS + Vanilla JS (Frontend)

• Main Version: OpenAI API (GPT-4 for intelligent responses)
• AWS Bedrock Version: AWS Bedrock (Claude 3.5 Sonnet + Titan Text Embeddings V2)

The grocery agent uses a LangGraph-powered AI agent that routes requests through specialized tools.

1. Cache Check: First checks Redis semantic cache for similar queries
2. AI Agent: Routes to appropriate tools based on request type
3. Specialized Tools: Recipe ingredients, product search, cart operations, direct answers
4. Services Layer: Product, cart, and chat services
5. Redis Storage: Vector embeddings, semantic cache, and session data

services/  ├── products/                # Product Business Component  │   ├── api/                    # REST API endpoints  │   ├── domain/                 # Business logic  │   └── data/                   # Data access layer  ├── cart/                    # Cart Business Component  │   ├── api/  │   ├── domain/  │   └── data/  ├──chat/                     # Chat/Cache Business Component  │   ├── api/  │   ├── domain/  │   └── data/  ├── ai/grocery-ai-agent/     # AI Agent  │   ├── tools.js                # API/Interface Layer  │   ├── nodes.js                # Agent Logic  │   ├── index.js                # Orchestration  │   └── state/                  # Data Access

• POST /api/chat - Main chat interface for AI shopping assistant
• GET /api/products/search - Search products with text/vector similarity
• POST /api/cart/add - Add items to shopping cart
• GET /api/cart - View cart contents
• DELETE /api/cart - Clear cart

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

This project is licensed under the MIT License - see theLICENSE file for details.

If you find a bug or have a feature request,open an issue.