Spaces:

kabuda777
/

Code2MCP-FoamAgent

Running

App Files Files Community

kabudadada commited on Sep 13, 2025

Commit

3de53ca

1 Parent(s): 06f289c

Update README: convert to English, simplify environment config, and update secrets section

Browse files

Files changed (1) hide show

README.md +47 -75

README.md CHANGED Viewed

@@ -11,103 +11,80 @@ pinned: false
 # Code2MCP-FoamAgent
-Foam-Agent 的 MCP (Model Context Protocol) 服务包装器，提供基于自然语言的 OpenFOAM CFD 仿真工作流。
-## 功能特性
-- 🧪 基于自然语言的 CFD 仿真需求
-- 🤖 多智能体工作流自动化
-- 📊 自动错误检测和修正
-- 🔧 自定义网格支持 (GMSH .msh 文件)
-- 🌐 多种 LLM 提供商支持
-## 快速开始
-### 1. 环境配置
-复制环境变量模板并配置：
-```bash
-cp env.example .env
-```
-编辑 `.env` 文件，设置您的 API 密钥：
-```env
-# OpenAI API Configuration
-OPENAI_API_KEY=your_openai_api_key_here
-OPENAI_BASE_URL=https://api.openai.com/v1
-# 或者使用自定义 API 端点
-# OPENAI_BASE_URL=https://api.gptsapi.net/v1
-```
-### 2. 安装依赖
-#### 使用 conda（推荐）
 ```bash
-# 创建 conda 环境
 conda env create -f environment.yml
-# 激活环境
 conda activate openfoamAgent
-# 安装额外的 MCP 依赖
 pip install fastapi uvicorn[standard] fastmcp
 ```
-### 3. 运行 MCP 服务
 ```bash
 python Foam-Agent/mcp_output/start_mcp.py
 ```
-### 4. Docker 部署
-#### 方法一：使用 .env 文件（推荐）
-```bash
-# 1. 创建 .env 文件
-cp env.example .env
-# 编辑 .env 文件，填入您的 API 密钥
-# 2. 使用 docker-compose（推荐）
-docker-compose up -d
-# 3. 或者使用 docker run
-docker run -p 7860:7860 --env-file .env code2mcp-foamagent
-```
-#### 方法二：直接设置环境变量
 ```bash
-# 构建镜像
 docker build -t code2mcp-foamagent .
-# 运行容器（设置环境变量）
 docker run -p 7860:7860 \
   -e OPENAI_API_KEY=your_api_key_here \
   -e OPENAI_BASE_URL=https://api.openai.com/v1 \
   code2mcp-foamagent
 ```
-## 使用方法
-### 基本 CFD 仿真
 ```python
-# 运行简单的 CFD 仿真
 result = run_foam_agent(
     requirements="Do an incompressible lid driven cavity flow...",
     output_dir="./output"
 )
 ```
-### 使用自定义网格
 ```python
-# 使用自定义 GMSH 网格文件
 result = run_foam_agent(
     requirements="Simulate flow over a tandem wing...",
     output_dir="./output",
@@ -115,10 +92,10 @@ result = run_foam_agent(
 )
 ```
-### 完整基准测试
 ```python
-# 运行完整的 Foam-Agent 基准测试
 result = run_foam_benchmark(
     openfoam_path="/opt/openfoam10",
     requirements="Your CFD requirements...",
@@ -126,32 +103,27 @@ result = run_foam_benchmark(
 )
 ```
-## 环境变量
-| 变量名 | 描述 | 默认值 |
-|--------|------|--------|
-| `OPENAI_API_KEY` | OpenAI API 密钥 | 必需 |
-| `OPENAI_BASE_URL` | OpenAI API 基础 URL | `https://api.openai.com/v1` |
-| `WM_PROJECT_DIR` | OpenFOAM 安装路径 | `/opt/openfoam10` |
-| `MODEL_PROVIDER` | LLM 提供商 | `openai` |
-| `MODEL_VERSION` | 模型版本 | `gpt-4o` |
-| `MCP_TRANSPORT` | MCP 传输模式 | `http` |
-| `MCP_PORT` | MCP 服务端口 | `7860` |
-## 系统要求
 - Python 3.11+
 - OpenFOAM v10
-- OpenAI API 密钥或其他 LLM 提供商
-- 预处理的 OpenFOAM 数据库
-## 故障排除
-1. **检查系统状态**：使用 `check_foam_agent_status` 工具
-2. **验证 API 配置**：确保 API 密钥和 URL 正确设置
-3. **检查依赖**：确保所有 Python 包已正确安装
-4. **OpenFOAM 环境**：确保 OpenFOAM 已正确安装并配置
-## 许可证
 MIT License

 # Code2MCP-FoamAgent
+MCP (Model Context Protocol) service wrapper for Foam-Agent, providing natural language-based OpenFOAM CFD simulation workflows.
+## Features
+- 🧪 Natural language CFD simulation requirements
+- 🤖 Multi-agent workflow automation
+- 📊 Automatic error detection and correction
+- 🔧 Custom mesh support (GMSH .msh files)
+- 🌐 Multiple LLM provider support
+## Quick Start
+### 1. Environment Configuration
+Environment variables are configured in Hugging Face Spaces secrets. No local configuration needed.
+### 2. Install Dependencies
+#### Using conda (Recommended)
 ```bash
+# Create conda environment
 conda env create -f environment.yml
+# Activate environment
 conda activate openfoamAgent
+# Install additional MCP dependencies
 pip install fastapi uvicorn[standard] fastmcp
 ```
+### 3. Run MCP Service
 ```bash
 python Foam-Agent/mcp_output/start_mcp.py
 ```
+### 4. Docker Deployment
+#### Using environment variables
 ```bash
+# Build image
 docker build -t code2mcp-foamagent .
+# Run container (set environment variables)
 docker run -p 7860:7860 \
   -e OPENAI_API_KEY=your_api_key_here \
   -e OPENAI_BASE_URL=https://api.openai.com/v1 \
   code2mcp-foamagent
 ```
+### 5. Hugging Face Spaces Deployment
+Environment variables are configured in Hugging Face Spaces secrets. The service is ready to use once deployed.
+**Note**: Due to Hugging Face Spaces limitations, OpenFOAM may not run completely, but the MCP service itself can work normally.
+## Usage
+### Basic CFD Simulation
 ```python
+# Run simple CFD simulation
 result = run_foam_agent(
     requirements="Do an incompressible lid driven cavity flow...",
     output_dir="./output"
 )
 ```
+### Using Custom Mesh
 ```python
+# Use custom GMSH mesh file
 result = run_foam_agent(
     requirements="Simulate flow over a tandem wing...",
     output_dir="./output",
 )
 ```
+### Complete Benchmark
 ```python
+# Run complete Foam-Agent benchmark
 result = run_foam_benchmark(
     openfoam_path="/opt/openfoam10",
     requirements="Your CFD requirements...",
 )
 ```
+## Environment Secrets
+| Variable | Description | Required |
+|----------|-------------|----------|
+| `OPENAI_API_KEY` | OpenAI API key | Yes |
+| `OPENAI_BASE_URL` | OpenAI API base URL | No |
+## System Requirements
 - Python 3.11+
 - OpenFOAM v10
+- OpenAI API key or other LLM provider
+- Preprocessed OpenFOAM database
+## Troubleshooting
+1. **Check system status**: Use `check_foam_agent_status` tool
+2. **Verify API configuration**: Ensure API key and URL are correctly set
+3. **Check dependencies**: Ensure all Python packages are properly installed
+4. **OpenFOAM environment**: Ensure OpenFOAM is properly installed and configured
+## License
 MIT License