Smarter Recipe
What is Smarter Recipe
smarter_recipe is an AI recipe recommendation system built on a Flask microservices architecture. It integrates Retrieval-Augmented Generation (RAG), large language models, and image generation models to recommend recipes based on user input and generate recipe content and style images.
Use cases
Use cases include personalized recipe suggestions based on user preferences, generating detailed recipe descriptions, creating visually appealing recipe images, and searching for specific recipes based on ingredients or cuisine.
How to use
To use smarter_recipe, clone the repository, start the services using Docker Compose, and access the services through the provided API endpoints for user registration, recipe recommendations, and AI-generated content.
Key features
Key features include an API gateway for unified access, user service for managing user preferences, core service for recommendation logic, AI service for text and image generation, and retrieval service for recipe searching.
Where to use
smarter_recipe can be used in culinary applications, food tech startups, recipe websites, and any platform that requires personalized recipe recommendations and content generation.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Smarter Recipe
smarter_recipe is an AI recipe recommendation system built on a Flask microservices architecture. It integrates Retrieval-Augmented Generation (RAG), large language models, and image generation models to recommend recipes based on user input and generate recipe content and style images.
Use cases
Use cases include personalized recipe suggestions based on user preferences, generating detailed recipe descriptions, creating visually appealing recipe images, and searching for specific recipes based on ingredients or cuisine.
How to use
To use smarter_recipe, clone the repository, start the services using Docker Compose, and access the services through the provided API endpoints for user registration, recipe recommendations, and AI-generated content.
Key features
Key features include an API gateway for unified access, user service for managing user preferences, core service for recommendation logic, AI service for text and image generation, and retrieval service for recipe searching.
Where to use
smarter_recipe can be used in culinary applications, food tech startups, recipe websites, and any platform that requires personalized recipe recommendations and content generation.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
AI菜谱推荐系统
基于Flask微服务架构的AI菜谱推荐系统，集成RAG、大语言模型和图片生成模型，支持根据用户输入推荐菜谱、生成菜谱内容和样式图。
系统架构
系统由以下微服务组成：
- api-gateway: API网关，统一入口
- user-service: 用户服务，处理用户相关功能
- core-service: 核心服务，处理推荐逻辑
- ai-service: AI服务，处理文本和图片生成
- retrieval-service: 检索服务，处理菜谱检索
技术栈
- Web框架：Flask
- 数据库：PostgreSQL
- 缓存：Redis
- 服务注册发现：Nacos
- 容器管理：Docker (docker-compose)
- AI模型：
- 文本生成：deepseek-llm-7b-instruct
- 图片生成：stable-diffusion-v1-5
- 文本嵌入：all-MiniLM-L6-v2
部署要求
- Docker和Docker Compose
- NVIDIA GPU（16GB显存以上）
- 至少16GB内存
- 至少100GB存储空间
快速开始
- 克隆仓库：
git clone [repository-url]
cd small_recipe_recommdation
- 启动服务：
docker-compose up -d
- 访问服务：
- API网关：http://localhost:8000
- 用户服务：http://localhost:8001
- 核心服务：http://localhost:8002
- AI服务：http://localhost:8003
- 检索服务：http://localhost:8004
API文档
用户服务
- POST /register - 用户注册
- POST /login - 用户登录
- GET /preferences - 获取用户偏好
- PUT /preferences - 更新用户偏好
- POST /feedback - 提交反馈
- GET /history - 获取历史记录
核心服务
- POST /recommend - 获取菜谱推荐
AI服务
- POST /generate/description - 生成菜谱描述
- POST /generate/image - 生成菜谱图片
检索服务
- POST /search - 搜索菜谱
- POST /index - 索引新菜谱
开发指南
- 环境准备：
python -m venv venv
source venv/bin/activate # Linux/Mac
# 或
.\venv\Scripts\activate # Windows
pip install -r requirements.txt
- 本地开发：
# 启动单个服务
python api-gateway/app.py
python user-service/app.py
python core-service/app.py
python ai-service/app.py
python retrieval-service/app.py
- 测试：
# 运行测试
pytest
注意事项
- 首次启动时，AI服务需要下载模型，可能需要较长时间
- 确保NVIDIA驱动和CUDA正确安装
- 生产环境部署时，请修改默认密码和密钥
- 建议使用HTTPS进行生产环境部署
贡献指南
- Fork项目
- 创建特性分支
- 提交更改
- 推送到分支
- 创建Pull Request
许可证
MIT License
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.
