$ show FutureUnreal/What-to-eat-today
This repository implements a full-stack AI-powered food recommendation application called 'δ»ε€©εδ»δΉ' (What to eat today). The system combines a Next.js frontend with a Python Flask backend that uses a GraphRAG (Retrieval-Augmented Generation) architecture leveraging Neo4j for graph-based recipe relationships and Milvus for vector similarity search. Users interact via a chat interface to receive personalized recipe recommendations with step-by-step cooking instructions. The application includes a comprehensive recipe knowledge base in markdown format, Docker-based deployment orchestration, and a modular RAG pipeline with intelligent query routing and session management.
The LLM identified 4 files worth highlighting for reuse:
A reusable UI component library (Button, Card, Input, Modal, Toast, LoadingSpinner) built with Tailwind CSS and Framer Motion. These components are decoupled from application logic, exported via an index file, and can be easily integrated into other Next.js projects with minimal adaptation.
A custom React hook that encapsulates chat interactions with the backend API, including message sending, streaming response handling, and error-toast notifications. This hook abstracts the communication layer and could be adapted for other chat-based applications by modifying the API endpoints and message formats.
Implements a sophisticated hybrid retrieval strategy combining entity-level, topic-level, and vector search with round-robin result merging. This module demonstrates non-obvious relevance balancing techniques and could be extracted for use in other retrieval systems with minimal changes to the data source interfaces.
Core GraphRAG implementation performing multi-hop traversal in the Neo4j graph to extract relevant subgraphs for context enrichment. This module showcases advanced graph-based reasoning patterns that could be reused in other knowledge graph applications with adjustments to the schema-specific Cypher queries.