Add GPU support and improve Docker deployment

- Add GPU deployment support with NVIDIA runtime - Update Dockerfile.allinone with GPU environment variables - Add comprehensive GPU_DEPLOYMENT.md guide - Make port 11434 (Ollama) optional for security - Update DEPLOYMENT.md with CPU and GPU deployment options - Simplify default docker run commands - Update healthcheck to only check web application - Add memory requirements documentation - Create MEMORY_REQUIREMENTS.md with model comparison - Add build-8b.sh script for lower memory usage - Document OOM troubleshooting steps - Improve Docker build process - Add BUILD_TROUBLESHOOTING.md for common issues - Add DISTRIBUTION.md for image distribution methods - Update .gitignore to exclude large binary files - Improve docker-entrypoint.sh with better diagnostics - Update .dockerignore to include ollama-linux-amd64.tgz - Add backup file exclusions to .gitignore
fix: export only required models instead of entire Ollama directory
2025-12-08 17:08:45 +08:00 · 2025-12-08 12:00:11 +08:00 · 2025-12-08 10:10:38 +08:00 · 2025-12-08 09:43:20 +08:00
19 changed files with 1642 additions and 89 deletions
--- a/.dockerignore
+++ b/.dockerignore
@@ -0,0 +1,28 @@
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+*.so
+*.egg
+*.egg-info
+dist
+build
+.git
+.gitignore
+.vscode
+.idea
+*.md
+!README.md
+# Include pre-downloaded Ollama binary for offline build
+!ollama-linux-amd64.tgz
+local_docs
+examples
+outputs
+.DS_Store
+*.log
+.env
+.venv
+venv
+env
+
--- a/.gitignore
+++ b/.gitignore
@@ -149,6 +149,16 @@ outputs/
 *.log
 local_docs/

+# Docker build artifacts (DO NOT commit these - they are huge!)
+ollama-models/
+*.tar
+ollama-linux-amd64.tgz
+system-prompt-optimizer-*.tar
+*.tar.gz
+
+# Backup files from scripts
+*.bak
+
 # Node modules (if any frontend dependencies)
 node_modules/
 package-lock.json
--- a/DEPLOYMENT.md
+++ b/DEPLOYMENT.md
@@ -0,0 +1,461 @@
+# Docker 部署指南
+
+本文档说明如何在无外网访问的服务器上部署系统提示词优化工具。
+
+## 部署方案
+
+本项目提供两种部署方案：
+
+### 方案 A: All-in-One 镜像（推荐，适用于无外网服务器）
+
+**优点**：
+- 包含所有依赖：应用代码 + Ollama + LLM 模型
+- 一个镜像文件，部署简单
+- 无需在目标服务器上安装任何额外软件（除了 Docker）
+
+**缺点**：
+- 镜像文件很大（10-20GB）
+- 传输时间较长
+
+### 方案 B: 分离部署（适用于已有 Ollama 的服务器）
+
+**优点**：
+- 镜像文件较小（~500MB）
+- 可以复用现有的 Ollama 服务
+
+**缺点**：
+- 需要在目标服务器上单独安装和配置 Ollama
+- 需要手动下载模型
+
+---
+
+## 方案 A: All-in-One 部署（推荐）
+
+### 前置要求
+
+#### 在开发机器上（有外网访问）
+
+1. **Docker** 已安装
+2. **Ollama** 已安装并运行
+3. **磁盘空间**：至少 30GB 可用空间
+4. 已下载所需的 Ollama 模型：
+   - `qwen3:14b` (主模型，~8GB)
+   - `qwen3-embedding:4b` (嵌入模型，~2GB)
+
+#### 在目标服务器上（无外网访问）
+
+1. **Docker** 已安装
+2. **磁盘空间**：至少 25GB 可用空间
+
+### 部署步骤
+
+#### 步骤 1: 下载所需的 Ollama 模型
+
+在开发机器上，确保已下载所需模型：
+
+```bash
+# 下载主模型（约 8GB）
+ollama pull qwen3:14b
+
+# 下载嵌入模型（约 2GB）
+ollama pull qwen3-embedding:4b
+
+# 验证模型已下载
+ollama list
+```
+
+#### 步骤 2: 导出 Ollama 模型
+
+```bash
+# 运行导出脚本
+./export-ollama-models.sh
+```
+
+这将创建 `ollama-models/` 目录，包含所有模型文件。
+
+#### 步骤 3: 构建 All-in-One Docker 镜像
+
+```bash
+# 运行构建脚本（推荐）
+./build-allinone.sh
+
+# 或手动构建
+docker build -f Dockerfile.allinone -t system-prompt-optimizer:allinone .
+```
+
+**注意**：构建过程可能需要 10-30 分钟，取决于机器性能。
+
+#### 步骤 4: 导出 Docker 镜像
+
+如果使用 `build-allinone.sh`，镜像已自动导出。否则手动导出：
+
+```bash
+# 导出镜像（约 10-20GB）
+docker save -o system-prompt-optimizer-allinone.tar system-prompt-optimizer:allinone
+
+# 验证文件大小
+ls -lh system-prompt-optimizer-allinone.tar
+```
+
+#### 步骤 5: 传输到目标服务器
+
+使用 scp、U盘或其他方式传输镜像文件：
+
+```bash
+# 使用 scp（如果网络可达）
+scp system-prompt-optimizer-allinone.tar user@server:/path/
+
+# 或使用 rsync（支持断点续传）
+rsync -avP --progress system-prompt-optimizer-allinone.tar user@server:/path/
+
+# 或使用 U盘/移动硬盘物理传输
+```
+
+#### 步骤 6: 在目标服务器上加载镜像
+
+```bash
+# 加载镜像（需要几分钟）
+docker load -i system-prompt-optimizer-allinone.tar
+
+# 如果遇到权限错误，使用 sudo
+# sudo docker load -i system-prompt-optimizer-allinone.tar
+
+# 验证镜像已加载
+docker images | grep system-prompt-optimizer
+```
+
+#### 步骤 7: 启动服务
+
+**CPU 模式（默认）:**
+
+```bash
+# 启动容器（推荐：仅暴露 Web 端口）
+docker run -d \
+  --name system-prompt-optimizer \
+  -p 8010:8010 \
+  --restart unless-stopped \
+  system-prompt-optimizer:allinone
+
+# 查看启动日志
+docker logs -f system-prompt-optimizer
+```
+
+**GPU 模式（推荐，如果有 NVIDIA GPU）:**
+
+```bash
+# 使用所有可用 GPU（推荐）
+docker run -d \
+  --name system-prompt-optimizer \
+  --gpus all \
+  -p 8010:8010 \
+  --restart unless-stopped \
+  system-prompt-optimizer:allinone
+
+# 或指定特定 GPU
+docker run -d \
+  --name system-prompt-optimizer \
+  --gpus '"device=0"' \
+  -p 8010:8010 \
+  --restart unless-stopped \
+  system-prompt-optimizer:allinone
+
+# 查看启动日志
+docker logs -f system-prompt-optimizer
+```
+
+**GPU 部署前提条件**:
+- 已安装 NVIDIA 驱动 (`nvidia-smi` 可用)
+- 已安装 NVIDIA Container Toolkit
+- GPU 显存 ≥ 10GB (14b 模型) 或 ≥ 6GB (8b 模型)
+
+**详细 GPU 部署指南**: 参见 [GPU_DEPLOYMENT.md](GPU_DEPLOYMENT.md)
+
+**重要**：
+- 首次启动需要等待 30-60 秒（CPU）或 10-20 秒（GPU），Ollama 服务需要初始化
+- GPU 模式下推理速度提升 5-10 倍
+- 端口 11434 (Ollama) 是可选的，仅在需要外部访问 Ollama 时暴露
+- 不暴露 11434 更安全，因为 Ollama API 没有身份验证
+
+#### 步骤 8: 验证部署
+
+```bash
+# 等待服务启动（约 30-60 秒）
+sleep 60
+
+# 健康检查
+curl http://localhost:8010/health
+
+# 应该返回：
+# {"status":"ok","version":"0.1.0"}
+
+# 检查 Ollama 服务
+curl http://localhost:11434/api/tags
+
+# 检查可用模型
+curl http://localhost:8010/models
+
+# 访问 Web 界面
+# 浏览器打开: http://<服务器IP>:8010/ui/opro.html
+```
+
+---
+
+## 方案 B: 分离部署
+
+### 前置要求
+
+#### 在目标服务器上
+
+1. **Docker** 已安装
+2. **Ollama** 服务已安装并运行
+3. 已拉取所需的 Ollama 模型：
+   - `qwen3:14b` (主模型)
+   - `qwen3-embedding:4b` (嵌入模型)
+
+### 部署步骤
+
+#### 步骤 1: 构建应用镜像
+
+```bash
+# 在开发机器上构建
+docker build -t system-prompt-optimizer:latest .
+
+# 导出镜像
+docker save -o system-prompt-optimizer.tar system-prompt-optimizer:latest
+```
+
+#### 步骤 2: 传输并加载
+
+```bash
+# 传输到目标服务器
+scp system-prompt-optimizer.tar user@server:/path/
+
+# 在目标服务器上加载
+docker load -i system-prompt-optimizer.tar
+```
+
+#### 步骤 3: 启动服务
+
+```bash
+# 使用 Docker Compose
+docker-compose up -d
+
+# 或使用 Docker 命令
+docker run -d \
+  --name system-prompt-optimizer \
+  -p 8010:8010 \
+  -e OLLAMA_HOST=http://host.docker.internal:11434 \
+  -v $(pwd)/outputs:/app/outputs \
+  --add-host host.docker.internal:host-gateway \
+  --restart unless-stopped \
+  system-prompt-optimizer:latest
+```
+
+## 配置说明
+
+### 环境变量
+
+在 `docker-compose.yml` 或 `docker run` 命令中可以配置以下环境变量：
+
+- `OLLAMA_HOST`: Ollama 服务地址（默认: `http://host.docker.internal:11434`）
+- `PYTHONUNBUFFERED`: Python 输出缓冲（默认: `1`）
+
+### 端口映射
+
+- **8010**: Web 界面和 API 端口（必需）
+- **11434**: Ollama API 端口（可选，仅用于调试或外部访问 Ollama）
+
+### 数据持久化
+
+- `./outputs`: 用户反馈日志存储目录（映射到容器内 `/app/outputs`）
+
+## 故障排查
+
+### 0. Docker 守护进程连接错误
+
+**问题**: 运行 `docker` 命令时提示 "Cannot connect to the Docker daemon"
+
+**症状**:
+```
+Cannot connect to the Docker daemon at unix:///var/run/docker.sock. Is the docker daemon running?
+```
+
+**解决方案**:
+
+**方法 1: 检查 Docker 服务状态**
+```bash
+# 检查 Docker 是否运行
+sudo systemctl status docker
+
+# 如果未运行，启动它
+sudo systemctl start docker
+
+# 设置开机自启
+sudo systemctl enable docker
+```
+
+**方法 2: 添加用户到 docker 组（推荐）**
+```bash
+# 将当前用户添加到 docker 组
+sudo usermod -aG docker $USER
+
+# 应用组变更（需要重新登录或使用 newgrp）
+newgrp docker
+
+# 或者直接注销并重新登录
+
+# 验证
+docker info
+```
+
+**方法 3: 修复 Docker socket 权限**
+```bash
+# 检查 socket 权限
+ls -l /var/run/docker.sock
+
+# 修复权限
+sudo chown root:docker /var/run/docker.sock
+sudo chmod 660 /var/run/docker.sock
+```
+
+**方法 4: 临时使用 sudo**
+```bash
+# 如果上述方法不可行，使用 sudo 运行 Docker 命令
+sudo docker load -i system-prompt-optimizer-allinone.tar
+sudo docker run -d --name system-prompt-optimizer ...
+```
+
+**验证修复**:
+```bash
+# 应该能正常显示 Docker 信息
+docker info
+
+# 应该能看到当前用户在 docker 组中
+groups | grep docker
+```
+
+---
+
+### 1. 无法连接 Ollama 服务
+
+**问题**: 容器内无法访问宿主机的 Ollama 服务
+
+**解决方案**:
+```bash
+# 确保使用了 --add-host 参数
+--add-host host.docker.internal:host-gateway
+
+# 或者直接使用宿主机 IP
+-e OLLAMA_HOST=http://192.168.1.100:11434
+```
+
+### 2. 模型不可用（All-in-One 部署）
+
+**问题**: 容器内模型未正确加载
+
+**解决方案**:
+```bash
+# 进入容器检查
+docker exec -it system-prompt-optimizer bash
+
+# 在容器内检查模型
+ollama list
+
+# 如果模型不存在，检查模型目录
+ls -la /root/.ollama/models/
+
+# 退出容器
+exit
+```
+
+如果模型确实丢失，可能需要重新构建镜像。
+
+### 3. 模型不可用（分离部署）
+
+**问题**: Ollama 模型未安装
+
+**解决方案**:
+```bash
+# 在宿主机上拉取模型
+ollama pull qwen3:14b
+ollama pull qwen3-embedding:4b
+
+# 验证模型已安装
+ollama list
+```
+
+### 4. 容器启动失败
+
+**问题**: 端口被占用或权限问题
+
+**解决方案**:
+```bash
+# 检查端口占用
+netstat -tulpn | grep 8010
+netstat -tulpn | grep 11434
+
+# 更换端口（All-in-One 需要两个端口）
+docker run -p 8011:8010 -p 11435:11434 ...
+
+# 查看容器日志
+docker logs system-prompt-optimizer
+```
+
+### 5. 性能问题
+
+**问题**: 生成速度慢
+
+**解决方案**:
+- 确保 Ollama 使用 GPU 加速
+- 使用更小的模型（如 `qwen3:4b`）
+- 调整 `config.py` 中的 `GENERATION_POOL_SIZE`
+
+## 更新部署
+
+```bash
+# 1. 在开发机器上重新构建镜像
+docker build -t system-prompt-optimizer:latest .
+
+# 2. 导出新镜像
+docker save -o system-prompt-optimizer-new.tar system-prompt-optimizer:latest
+
+# 3. 传输到服务器并加载
+docker load -i system-prompt-optimizer-new.tar
+
+# 4. 重启服务
+docker-compose down
+docker-compose up -d
+
+# 或使用 docker 命令
+docker stop system-prompt-optimizer
+docker rm system-prompt-optimizer
+docker run -d ...  # 使用相同的启动命令
+```
+
+## 安全建议
+
+1. **网络隔离**: 如果不需要外部访问，只绑定到 localhost
+   ```bash
+   -p 127.0.0.1:8010:8010
+   ```
+
+2. **防火墙**: 配置防火墙规则限制访问
+   ```bash
+   # 只允许特定 IP 访问
+   iptables -A INPUT -p tcp --dport 8010 -s 192.168.1.0/24 -j ACCEPT
+   iptables -A INPUT -p tcp --dport 8010 -j DROP
+   ```
+
+3. **日志管理**: 定期清理日志文件
+   ```bash
+   # 限制 Docker 日志大小
+   docker run --log-opt max-size=10m --log-opt max-file=3 ...
+   ```
+
+## 联系支持
+
+如有问题，请查看：
+- 应用日志: `docker logs system-prompt-optimizer`
+- Ollama 日志: `journalctl -u ollama -f`
+- API 文档: http://localhost:8010/docs
+
--- a/38
+++ b/38
@@ -0,0 +1,38 @@
+FROM python:3.10-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements file
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY _qwen_xinference_demo/ ./_qwen_xinference_demo/
+COPY frontend/ ./frontend/
+COPY config.py .
+
+# Create outputs directory
+RUN mkdir -p outputs
+
+# Expose port
+EXPOSE 8010
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+ENV OLLAMA_HOST=http://host.docker.internal:11434
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:8010/health || exit 1
+
+# Run the application
+CMD ["uvicorn", "_qwen_xinference_demo.api:app", "--host", "0.0.0.0", "--port", "8010"]
+
--- a/Dockerfile.allinone
+++ b/Dockerfile.allinone
@@ -0,0 +1,58 @@
+FROM --platform=linux/amd64 python:3.10-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    curl \
+    ca-certificates \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Ollama manually for amd64
+# Copy pre-downloaded Ollama binary to avoid slow downloads during build
+# Using v0.13.1 (latest stable as of Dec 2024)
+COPY ollama-linux-amd64.tgz /tmp/ollama-linux-amd64.tgz
+RUN tar -C /usr -xzf /tmp/ollama-linux-amd64.tgz \
+    && rm /tmp/ollama-linux-amd64.tgz
+
+# Copy requirements file
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY _qwen_xinference_demo/ ./_qwen_xinference_demo/
+COPY frontend/ ./frontend/
+COPY config.py .
+
+# Create necessary directories
+RUN mkdir -p outputs /root/.ollama
+
+# Copy pre-downloaded Ollama models
+# This includes qwen3:14b and qwen3-embedding:4b
+COPY ollama-models/ /root/.ollama/
+
+# Expose ports
+EXPOSE 8010 11434
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+ENV OLLAMA_HOST=http://localhost:11434
+# Enable GPU support for Ollama (will auto-detect NVIDIA GPU if available)
+ENV NVIDIA_VISIBLE_DEVICES=all
+ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
+
+# Copy startup script
+COPY docker-entrypoint.sh /docker-entrypoint.sh
+RUN chmod +x /docker-entrypoint.sh
+
+# Health check
+# Only check the web application, not Ollama (internal service)
+HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
+    CMD curl -f http://localhost:8010/health || exit 1
+
+# Run the startup script
+ENTRYPOINT ["/docker-entrypoint.sh"]
+
--- a/QUICK_START.md
+++ b/QUICK_START.md
@@ -0,0 +1,117 @@
+# 快速开始指南
+
+## 离线部署（All-in-One 方案）
+
+### 在开发机器上（有外网）
+
+```bash
+# 1. 下载模型
+ollama pull qwen3:14b
+ollama pull qwen3-embedding:4b
+
+# 2. 导出模型
+./export-ollama-models.sh
+
+# 3. 构建并导出 Docker 镜像
+./build-allinone.sh
+
+# 4. 传输到目标服务器
+# 文件: system-prompt-optimizer-allinone.tar (约 10-20GB)
+scp system-prompt-optimizer-allinone.tar user@server:/path/
+```
+
+### 在目标服务器上（无外网）
+
+```bash
+# 1. 加载镜像
+docker load -i system-prompt-optimizer-allinone.tar
+
+# 2. 启动服务
+docker run -d \
+  --name system-prompt-optimizer \
+  -p 8010:8010 \
+  -p 11434:11434 \
+  -v $(pwd)/outputs:/app/outputs \
+  --restart unless-stopped \
+  system-prompt-optimizer:allinone
+
+# 3. 等待启动（约 60 秒）
+sleep 60
+
+# 4. 验证
+curl http://localhost:8010/health
+curl http://localhost:11434/api/tags
+
+# 5. 访问界面
+# http://<服务器IP>:8010/ui/opro.html
+```
+
+## 常用命令
+
+```bash
+# 查看日志
+docker logs -f system-prompt-optimizer
+
+# 重启服务
+docker restart system-prompt-optimizer
+
+# 停止服务
+docker stop system-prompt-optimizer
+
+# 删除容器
+docker rm -f system-prompt-optimizer
+
+# 进入容器
+docker exec -it system-prompt-optimizer bash
+
+# 检查模型
+docker exec -it system-prompt-optimizer ollama list
+```
+
+## 端口说明
+
+- **8010**: Web 界面和 API
+- **11434**: Ollama 服务（仅 All-in-One 方案需要暴露）
+
+## 文件说明
+
+- `system-prompt-optimizer-allinone.tar`: 完整镜像（10-20GB）
+- `outputs/`: 用户反馈日志目录
+
+## 故障排查
+
+### 服务无法启动
+
+```bash
+# 查看日志
+docker logs system-prompt-optimizer
+
+# 检查端口占用
+netstat -tulpn | grep 8010
+netstat -tulpn | grep 11434
+```
+
+### 模型不可用
+
+```bash
+# 进入容器检查
+docker exec -it system-prompt-optimizer ollama list
+
+# 应该看到:
+# qwen3:14b
+# qwen3-embedding:4b
+```
+
+### 性能慢
+
+- 确保服务器有足够的 RAM（建议 16GB+）
+- 如果有 GPU，使用支持 GPU 的 Docker 运行时
+- 调整 `config.py` 中的 `GENERATION_POOL_SIZE`
+
+## 更多信息
+
+详细文档请参考：
+- `DEPLOYMENT.md`: 完整部署指南
+- `README.md`: 项目说明
+- http://localhost:8010/docs: API 文档
+
--- a/README.md
+++ b/README.md
@@ -1,58 +1,65 @@
-# OPRO Prompt Optimizer
+# System Prompt Generator

 ## 功能概述

-OPRO (Optimization by PROmpting) 是一个基于大语言模型的提示词优化系统。本项目实现了真正的 OPRO 算法，通过迭代优化系统指令（System Instructions）来提升 LLM 在特定任务上的性能。
+这是一个基于大语言模型的系统提示词（System Prompt）生成和迭代优化工具。通过简单的任务描述，自动生成高质量的系统指令，并支持基于用户选择的迭代改进。

 ### 核心功能

- **系统指令优化**：使用 LLM 作为优化器，基于历史性能轨迹生成更优的系统指令
- **多轮迭代优化**：支持多轮优化，每轮基于前一轮的性能反馈生成新的候选指令
+- **智能指令生成**：根据任务描述自动生成多个高质量的系统指令候选
+- **迭代式改进**：基于用户选择的指令生成改进版本，避免被拒绝的方向
+- **角色定义格式**：所有生成的指令都以角色定义开头（如"你是一个..."），符合最佳实践
 - **智能候选选择**：通过语义聚类和多样性选择，从大量候选中筛选出最具代表性的指令
- **性能评估**：支持自定义测试用例对系统指令进行自动评估
- **会话管理**：支持多个优化任务的并行管理和历史记录
+- **会话管理**：支持多个任务的并行管理和历史记录
+- **全面覆盖要求**：生成的指令全面覆盖任务的所有要求和细节，而非仅追求风格多样性

 ### 用户界面

 - **现代化聊天界面**：类似 Google Gemini 的简洁设计
 - **侧边栏会话管理**：可折叠的侧边栏，支持多会话切换
- **实时优化反馈**：每轮优化生成 3-5 个候选指令，用户可选择继续优化或执行
+- **实时生成反馈**：每轮生成 5 个候选指令，用户可选择继续优化或复制使用
 - **模型选择**：支持在界面中选择不同的 LLM 模型

-## 主要优化改进
+## 核心特性

-### 1. 真正的 OPRO 实现
+### 1. 简单直观的工作流程

-原始代码实现的是查询重写（Query Rewriting），而非真正的 OPRO。我们添加了完整的 OPRO 功能：
+不同于复杂的 OPRO 算法（需要测试用例和自动评估），本工具采用简单直观的迭代改进方式：

- **系统指令生成**：`generate_system_instruction_candidates()` - 生成多样化的系统指令候选
- **性能评估**：`evaluate_system_instruction()` - 基于测试用例评估指令性能
- **轨迹优化**：基于历史 (instruction, score) 轨迹生成更优指令
- **元提示工程**：专门设计的元提示用于指导 LLM 生成和优化系统指令
+- **初始生成**：输入任务描述 → 生成 5 个全面的系统指令候选
+- **迭代改进**：选择喜欢的指令 → 生成基于该指令的改进版本，同时避免被拒绝的方向
+- **无需评分**：不需要测试用例或性能评分，完全基于用户偏好进行改进

-### 2. 性能优化
+### 2. 高质量指令生成

- **候选池大小优化**：从 20 个候选减少到 10 个，速度提升约 2 倍
- **智能聚类选择**：使用 AgglomerativeClustering 从候选池中选择最具多样性的 Top-K
+- **角色定义格式**：所有指令以"你是一个..."开头，符合系统提示词最佳实践
+- **全面覆盖要求**：生成的指令全面覆盖任务的所有要求和细节
+- **清晰可执行**：指令清晰、具体、可执行，包含必要的行为规范和输出格式
+- **简体中文**：所有生成的指令使用简体中文
+
+### 3. 性能优化
+
+- **候选池大小优化**：生成 10 个候选，通过聚类选择 5 个最具多样性的
+- **智能聚类选择**：使用 AgglomerativeClustering 从候选池中选择最具代表性的指令
 - **嵌入服务回退**：Xinference → Ollama 自动回退机制，确保服务可用性

-### 3. API 架构改进
+### 4. API 架构

- **新增 OPRO 端点**：
-  - `POST /opro/create` - 创建 OPRO 优化任务
-  - `POST /opro/generate_and_evaluate` - 生成并自动评估候选
-  - `POST /opro/execute` - 执行系统指令
-  - `GET /opro/runs` - 获取所有优化任务
-  - `GET /opro/run/{run_id}` - 获取特定任务详情
- **会话状态管理**：完整的 OPRO 运行状态跟踪（轨迹、测试用例、迭代次数）
+- **核心端点**：
+  - `POST /opro/create` - 创建新任务
+  - `POST /opro/generate_and_evaluate` - 生成初始候选
+  - `POST /opro/refine` - 基于用户选择进行迭代改进
+  - `GET /opro/sessions` - 获取所有会话
+  - `GET /opro/runs` - 获取所有任务
+- **会话管理**：支持多会话、多任务的并行管理
 - **向后兼容**：保留原有查询重写功能，标记为 `opro-legacy`

-### 4. 前端界面重构
+### 5. 前端界面

 - **Gemini 风格设计**：简洁的白色/灰色配色，圆角设计，微妙的阴影效果
 - **可折叠侧边栏**：默认折叠，支持会话列表管理
 - **多行输入框**：支持多行文本输入，底部工具栏包含模型选择器
- **候选指令卡片**：每个候选显示编号、内容、分数，提供"继续优化"、"复制"、"执行"按钮
+- **候选指令卡片**：每个候选显示编号和内容，提供"继续优化"和"复制"按钮
 - **简体中文界面**：所有 UI 文本和生成的指令均使用简体中文

 ## 快速开始
@@ -97,19 +104,18 @@ uvicorn _qwen_xinference_demo.api:app --host 0.0.0.0 --port 8010

 ### 访问界面

- **OPRO 优化界面**：http://127.0.0.1:8010/ui/opro.html
+- **系统指令生成器**：http://127.0.0.1:8010/ui/opro.html
 - **传统三栏界面**：http://127.0.0.1:8010/ui/
 - **API 文档**：http://127.0.0.1:8010/docs
 - **OpenAPI JSON**：http://127.0.0.1:8010/openapi.json

 ### 使用示例

-1. **创建新会话**：在 OPRO 界面点击"新建会话"或侧边栏的 + 按钮
-2. **输入任务描述**：例如"将中文翻译成英文"
-3. **查看候选指令**：系统生成 3-5 个优化的系统指令
-4. **继续优化**：点击"继续优化"进行下一轮迭代
-5. **执行指令**：点击"执行此指令"测试指令效果
-6. **复制指令**：点击"复制"按钮将指令复制到剪贴板
+1. **创建新会话**：在界面点击"新建会话"或侧边栏的 + 按钮
+2. **输入任务描述**：例如"帮我写一个专业的营销文案生成助手"
+3. **查看候选指令**：系统生成 5 个全面的系统指令，每个都以角色定义开头
+4. **选择并改进**：点击喜欢的指令上的"继续优化"按钮，生成基于该指令的改进版本
+5. **复制使用**：点击"复制"按钮将指令复制到剪贴板，用于你的应用中

 ## 配置说明

@@ -123,8 +129,8 @@ OLLAMA_HOST = "http://127.0.0.1:11434"
 DEFAULT_CHAT_MODEL = "qwen3:8b"
 DEFAULT_EMBED_MODEL = "qwen3-embedding:4b"

-# OPRO 优化参数
-GENERATION_POOL_SIZE = 10  # 生成候选池大小
+# 生成参数
+GENERATION_POOL_SIZE = 10  # 生成候选池大小（生成10个，聚类选择5个）
 TOP_K = 5                   # 返回给用户的候选数量
 CLUSTER_DISTANCE_THRESHOLD = 0.15  # 聚类距离阈值

@@ -157,11 +163,30 @@ XINFERENCE_EMBED_URL = "http://127.0.0.1:9997/models/bge-base-zh/embed"

 ## API 端点

-### OPRO 相关（推荐使用）
+### 会话管理
+
+- `POST /opro/session/create` - 创建新会话
+- `GET /opro/sessions` - 获取所有会话
+- `GET /opro/session/{session_id}` - 获取会话详情
+
+### 任务管理
+
+- `POST /opro/create` - 在会话中创建新任务
+  - 请求体：`{"session_id": "xxx", "task_description": "任务描述", "model_name": "qwen3:8b"}`
+  - 返回：`{"run_id": "xxx", "task_description": "...", "iteration": 0}`
+
+### 指令生成
+
+- `POST /opro/generate_and_evaluate` - 生成初始候选指令
+  - 请求体：`{"run_id": "xxx", "top_k": 5, "pool_size": 10}`
+  - 返回：`{"candidates": [{"instruction": "...", "score": null}, ...]}`
+
+- `POST /opro/refine` - 基于用户选择进行迭代改进
+  - 请求体：`{"run_id": "xxx", "selected_instruction": "用户选择的指令", "rejected_instructions": ["被拒绝的指令1", "被拒绝的指令2"]}`
+  - 返回：`{"candidates": [{"instruction": "...", "score": null}, ...], "iteration": 1}`
+
+### 任务查询

- `POST /opro/create` - 创建优化任务
- `POST /opro/generate_and_evaluate` - 生成并评估候选
- `POST /opro/execute` - 执行系统指令
 - `GET /opro/runs` - 获取所有任务
 - `GET /opro/run/{run_id}` - 获取任务详情

@@ -181,6 +206,37 @@ XINFERENCE_EMBED_URL = "http://127.0.0.1:9997/models/bge-base-zh/embed"

 详细 API 文档请访问：http://127.0.0.1:8010/docs

+## 工作原理
+
+### 初始生成流程
+
+1. 用户输入任务描述（如"帮我写一个专业的营销文案生成助手"）
+2. 系统使用 LLM 生成 10 个候选指令
+3. 通过语义嵌入和聚类算法选择 5 个最具多样性的候选
+4. 所有候选都以角色定义开头，全面覆盖任务要求
+
+### 迭代改进流程
+
+1. 用户选择喜欢的指令（如候选 #3）
+2. 系统记录被拒绝的指令（候选 #1, #2, #4, #5）
+3. 向 LLM 发送改进请求："基于选中的指令生成改进版本，避免被拒绝指令的方向"
+4. 生成新的 10 个候选，聚类选择 5 个返回
+5. 用户可以继续迭代或复制使用
+
+### 与 OPRO 的区别
+
+**OPRO（原始算法）**：
+- 需要测试用例（如数学题的正确答案）
+- 自动评分（如准确率 0.73, 0.81）
+- 基于性能轨迹优化
+- 适用于有明确评估标准的任务
+
+**本工具（简单迭代改进）**：
+- 不需要测试用例
+- 不需要自动评分
+- 基于用户偏好改进
+- 适用于任意通用任务
+
 ## 常见问题

 ### 1. 无法连接 Ollama 服务
@@ -198,11 +254,17 @@ ollama serve

 ### 3. 生成速度慢

- 调整 `GENERATION_POOL_SIZE` 减少候选数量
+- 调整 `GENERATION_POOL_SIZE` 减少候选数量（如改为 6，返回 3 个）
 - 使用更小的模型（如 `qwen3:4b`）
 - 确保 Ollama 使用 GPU 加速

-### 4. 界面显示异常
+### 4. 生成的指令质量不高
+
+- 提供更详细的任务描述
+- 多次迭代改进，选择最好的继续优化
+- 尝试不同的模型
+
+### 5. 界面显示异常

 硬刷新浏览器缓存：
 - **Mac**: `Cmd + Shift + R`
--- a/_qwen_xinference_demo/api.py
+++ b/_qwen_xinference_demo/api.py
@@ -24,7 +24,8 @@ from .opro.session_state import (
 from .opro.user_prompt_optimizer import generate_candidates
 from .opro.user_prompt_optimizer import (
    generate_system_instruction_candidates,
-    evaluate_system_instruction
+    evaluate_system_instruction,
+    refine_instruction_candidates
 )

 from .opro.ollama_client import call_qwen
@@ -159,6 +160,15 @@ class OPROExecuteReq(BaseModel):
    model_name: Optional[str] = None


+class OPRORefineReq(BaseModel):
+    """Request to refine based on selected instruction (simple iterative refinement, NOT OPRO)."""
+    run_id: str
+    selected_instruction: str
+    rejected_instructions: List[str]
+    top_k: Optional[int] = None
+    pool_size: Optional[int] = None
+
+
 # ============================================================================
 # LEGACY ENDPOINTS (Query Rewriting - NOT true OPRO)
 # ============================================================================
@@ -696,3 +706,44 @@ def opro_execute(req: OPROExecuteReq):
        })
    except Exception as e:
        raise AppException(500, f"Execution failed: {e}", "EXECUTION_ERROR")
+
+
+@app.post("/opro/refine", tags=["opro-true"])
+def opro_refine(req: OPRORefineReq):
+    """
+    Simple iterative refinement based on user selection (NOT OPRO).
+
+    This generates new candidates based on the selected instruction while avoiding rejected ones.
+    No scoring, no trajectory - just straightforward refinement based on user preference.
+    """
+    run = get_opro_run(req.run_id)
+    if not run:
+        raise AppException(404, "OPRO run not found", "RUN_NOT_FOUND")
+
+    top_k = req.top_k or config.TOP_K
+    pool_size = req.pool_size or config.GENERATION_POOL_SIZE
+
+    try:
+        candidates = refine_instruction_candidates(
+            task_description=run["task_description"],
+            selected_instruction=req.selected_instruction,
+            rejected_instructions=req.rejected_instructions,
+            top_k=top_k,
+            pool_size=pool_size,
+            model_name=run["model_name"]
+        )
+
+        # Update iteration counter
+        update_opro_iteration(req.run_id, candidates)
+
+        # Get updated run info
+        run = get_opro_run(req.run_id)
+
+        return ok({
+            "run_id": req.run_id,
+            "iteration": run["iteration"],
+            "candidates": [{"instruction": c, "score": None} for c in candidates],
+            "task_description": run["task_description"]
+        })
+    except Exception as e:
+        raise AppException(500, f"Refinement failed: {e}", "REFINEMENT_ERROR")
--- a/_qwen_xinference_demo/opro/prompt_utils.py
+++ b/_qwen_xinference_demo/opro/prompt_utils.py
@@ -56,14 +56,15 @@ def generate_initial_system_instruction_candidates(task_description: str, pool_s
 目标任务描述：
 【{task_description}】

-请根据以上任务，生成 {pool_size} 条高质量、风格各异的"System Instruction"候选指令。
+请根据以上任务，生成 {pool_size} 条高质量、全面的"System Instruction"候选指令。

 要求：
-1. 每条指令必须有明显不同的风格和侧重点
-2. 覆盖不同的实现策略（例如：简洁型、详细型、示例型、角色扮演型、步骤型等）
-3. 这些指令应指导LLM的行为和输出格式，以最大化任务性能
-4. 每条指令单独成行，不包含编号或额外说明
-5. 所有生成的指令必须使用简体中文
+1. 每条指令必须以角色定义开头（例如："你是一个..."、"你是..."等）
+2. 每条指令必须全面覆盖任务的所有要求和细节
+3. 指令应清晰、具体、可执行，能够有效指导LLM完成任务
+4. 确保指令包含必要的行为规范、输出格式、注意事项等
+5. 每条指令单独成行，不包含编号或额外说明
+6. 所有生成的指令必须使用简体中文

 生成 {pool_size} 条指令：
 """
@@ -120,11 +121,68 @@ def generate_optimized_system_instruction(
 然后，生成 {pool_size} 条新的、有潜力超越 {highest_score:.4f} 分的System Instruction。

 要求：
-1. 每条指令必须有明显不同的改进策略
-2. 结合高分指令的优点，避免低分指令的缺陷
-3. 探索新的优化方向和表达方式
-4. 每条指令单独成行，不包含编号或额外说明
-5. 所有生成的指令必须使用简体中文
+1. 每条指令必须以角色定义开头（例如："你是一个..."、"你是..."等）
+2. 每条指令必须全面覆盖任务的所有要求和细节
+3. 结合高分指令的优点，避免低分指令的缺陷
+4. 指令应清晰、具体、可执行，能够有效指导LLM完成任务
+5. 每条指令单独成行，不包含编号或额外说明
+6. 所有生成的指令必须使用简体中文

 生成 {pool_size} 条优化后的指令：
 """
+
+
+def refine_based_on_selection(
+    task_description: str,
+    selected_instruction: str,
+    rejected_instructions: List[str],
+    pool_size: int = None
+) -> str:
+    """
+    Simple refinement: Generate variations based on selected instruction while avoiding rejected ones.
+
+    This is NOT OPRO - it's straightforward iterative refinement based on user preference.
+    No scoring, no trajectory, just: "I like this one, give me more like it (but not like those)."
+
+    Args:
+        task_description: Description of the task
+        selected_instruction: The instruction the user selected
+        rejected_instructions: The instructions the user didn't select
+        pool_size: Number of new candidates to generate
+
+    Returns:
+        Prompt for generating refined candidates
+    """
+    import config
+    pool_size = pool_size or config.GENERATION_POOL_SIZE
+
+    rejected_text = ""
+    if rejected_instructions:
+        rejected_formatted = "\n".join(f"- {inst}" for inst in rejected_instructions)
+        rejected_text = f"""
+**用户未选择的指令（避免这些方向）：**
+{rejected_formatted}
+"""
+
+    return f"""
+你是一个"System Prompt 改进助手"。
+目标任务描述：
+【{task_description}】
+
+**用户选择的指令（基于此改进）：**
+{selected_instruction}
+{rejected_text}
+
+请基于用户选择的指令，生成 {pool_size} 条改进版本。
+
+要求：
+1. 每条指令必须以角色定义开头（例如："你是一个..."、"你是..."等）
+2. 保留用户选择指令的核心优点
+3. 每条指令必须全面覆盖任务的所有要求和细节
+4. 指令应清晰、具体、可执行，能够有效指导LLM完成任务
+5. 避免与未选择指令相似的方向
+6. 每条指令单独成行，不包含编号或额外说明
+7. 所有生成的指令必须使用简体中文
+
+生成 {pool_size} 条改进后的指令：
+"""
--- a/_qwen_xinference_demo/opro/user_prompt_optimizer.py
+++ b/_qwen_xinference_demo/opro/user_prompt_optimizer.py
@@ -11,7 +11,8 @@ from .prompt_utils import (
    refine_instruction,
    refine_instruction_with_history,
    generate_initial_system_instruction_candidates,
-    generate_optimized_system_instruction
+    generate_optimized_system_instruction,
+    refine_based_on_selection
 )

 def parse_candidates(raw: str) -> list:
@@ -147,3 +148,46 @@ def evaluate_system_instruction(
            correct += 1

    return correct / total
+
+
+def refine_instruction_candidates(
+    task_description: str,
+    selected_instruction: str,
+    rejected_instructions: List[str],
+    top_k: int = config.TOP_K,
+    pool_size: int = None,
+    model_name: str = None
+) -> List[str]:
+    """
+    Simple refinement: Generate new candidates based on user's selection.
+
+    This is NOT OPRO - just straightforward iterative refinement.
+    User picks a favorite, we generate variations of it while avoiding rejected ones.
+
+    Args:
+        task_description: Description of the task
+        selected_instruction: The instruction the user selected
+        rejected_instructions: The instructions the user didn't select
+        top_k: Number of diverse candidates to return
+        pool_size: Number of candidates to generate before clustering
+        model_name: Optional model name to use
+
+    Returns:
+        List of refined instruction candidates
+    """
+    pool_size = pool_size or config.GENERATION_POOL_SIZE
+
+    # Generate the refinement prompt
+    meta_prompt = refine_based_on_selection(
+        task_description,
+        selected_instruction,
+        rejected_instructions,
+        pool_size
+    )
+
+    # Use LLM to generate refined candidates
+    raw = call_qwen(meta_prompt, temperature=0.9, max_tokens=1024, model_name=model_name)
+
+    # Parse and cluster
+    all_candidates = parse_candidates(raw)
+    return cluster_and_select(all_candidates, top_k=top_k)
--- a/build-8b.sh
+++ b/build-8b.sh
@@ -0,0 +1,141 @@
+#!/bin/bash
+
+# Quick build script for qwen3:8b (lower memory usage)
+# Use this if your server has less than 12GB RAM
+
+set -e
+
+echo "=========================================="
+echo "Building with qwen3:8b (Lower Memory)"
+echo "=========================================="
+echo ""
+echo "Memory requirements:"
+echo "  - qwen3:8b: ~5GB RAM"
+echo "  - qwen3:14b: ~10GB RAM"
+echo ""
+
+# Check if 8b model is available
+if ! ollama list | grep -q "qwen3:8b"; then
+    echo "ERROR: qwen3:8b model not found!"
+    echo ""
+    echo "Please download it first:"
+    echo "  ollama pull qwen3:8b"
+    echo ""
+    exit 1
+fi
+
+# Clean up
+echo "Cleaning up previous builds..."
+rm -rf ollama-models/
+docker rmi system-prompt-optimizer:allinone 2>/dev/null || true
+
+# Export 8b model
+echo ""
+echo "Exporting qwen3:8b model..."
+mkdir -p ollama-models/models/{manifests/registry.ollama.ai/library,blobs}
+
+# Function to get blob hashes from manifest
+get_blobs_from_manifest() {
+    local manifest_file=$1
+    grep -o 'sha256:[a-f0-9]\{64\}' "$manifest_file" | sed 's/sha256://' | sort -u
+}
+
+# Function to copy model files
+copy_model() {
+    local model_name=$1
+    local model_tag=$2
+    local manifest_dir="$HOME/.ollama/models/manifests/registry.ollama.ai/library/$model_name"
+    
+    if [ ! -d "$manifest_dir" ]; then
+        echo "ERROR: Model manifest not found: $manifest_dir"
+        return 1
+    fi
+    
+    echo "  Copying $model_name:$model_tag manifest..."
+    mkdir -p "ollama-models/models/manifests/registry.ollama.ai/library/$model_name"
+    
+    if [ -f "$manifest_dir/$model_tag" ]; then
+        cp "$manifest_dir/$model_tag" "ollama-models/models/manifests/registry.ollama.ai/library/$model_name/"
+        
+        echo "  Finding blob files for $model_name:$model_tag..."
+        local blob_hashes=$(get_blobs_from_manifest "$manifest_dir/$model_tag")
+        local blob_count=0
+        
+        for blob_hash in $blob_hashes; do
+            local blob_file="$HOME/.ollama/models/blobs/sha256-$blob_hash"
+            if [ -f "$blob_file" ]; then
+                cp "$blob_file" "ollama-models/models/blobs/" 2>/dev/null
+                blob_count=$((blob_count + 1))
+            fi
+        done
+        
+        echo "  ✓ $model_name:$model_tag copied ($blob_count blobs)"
+    else
+        echo "ERROR: Manifest file not found: $manifest_dir/$model_tag"
+        return 1
+    fi
+}
+
+# Copy models
+copy_model "qwen3" "8b" || exit 1
+copy_model "qwen3-embedding" "4b" || exit 1
+
+echo ""
+echo "✓ Models exported successfully"
+echo ""
+
+# Update config.py to use 8b
+echo "Updating config.py to use qwen3:8b..."
+sed -i.bak 's/DEFAULT_CHAT_MODEL = "qwen3:14b"/DEFAULT_CHAT_MODEL = "qwen3:8b"/' config.py
+
+# Update docker-entrypoint.sh to check for 8b
+echo "Updating docker-entrypoint.sh to check for qwen3:8b..."
+sed -i.bak 's/qwen3:14b/qwen3:8b/g' docker-entrypoint.sh
+
+# Build image
+echo ""
+echo "Building Docker image..."
+docker build --platform linux/amd64 \
+    -f Dockerfile.allinone \
+    -t system-prompt-optimizer:allinone .
+
+if [ $? -ne 0 ]; then
+    echo ""
+    echo "Build failed!"
+    # Restore backups
+    mv config.py.bak config.py
+    mv docker-entrypoint.sh.bak docker-entrypoint.sh
+    exit 1
+fi
+
+# Export image
+echo ""
+echo "Exporting Docker image..."
+docker save -o system-prompt-optimizer-allinone.tar system-prompt-optimizer:allinone
+
+# Restore original files
+mv config.py.bak config.py
+mv docker-entrypoint.sh.bak docker-entrypoint.sh
+
+echo ""
+echo "=========================================="
+echo "Build Complete!"
+echo "=========================================="
+ls -lh system-prompt-optimizer-allinone.tar
+echo ""
+echo "This image uses qwen3:8b (~5GB RAM required)"
+echo ""
+echo "Transfer to server and run:"
+echo ""
+echo "  CPU mode:"
+echo "  docker load -i system-prompt-optimizer-allinone.tar"
+echo "  docker run -d -p 8010:8010 --restart unless-stopped system-prompt-optimizer:allinone"
+echo ""
+echo "  GPU mode (recommended):"
+echo "  docker load -i system-prompt-optimizer-allinone.tar"
+echo "  docker run -d --gpus all -p 8010:8010 --restart unless-stopped system-prompt-optimizer:allinone"
+echo ""
+echo "Note: GPU mode provides 5-10x faster inference."
+echo "      See GPU_DEPLOYMENT.md for GPU setup instructions."
+echo ""
+
--- a/build-allinone.sh
+++ b/build-allinone.sh
@@ -0,0 +1,133 @@
+#!/bin/bash
+
+# Build all-in-one Docker image with Ollama and models
+# This creates a complete offline-deployable image
+
+set -e
+
+IMAGE_NAME="system-prompt-optimizer"
+IMAGE_TAG="allinone"
+EXPORT_FILE="${IMAGE_NAME}-${IMAGE_TAG}.tar"
+
+echo "=========================================="
+echo "Building All-in-One Docker Image"
+echo "=========================================="
+echo ""
+echo "This will create a Docker image containing:"
+echo "  - Python application"
+echo "  - Ollama service (v0.13.1)"
+echo "  - qwen3:14b model"
+echo "  - qwen3-embedding:4b model"
+echo ""
+echo "Target platform: linux/amd64 (x86_64)"
+echo ""
+echo "WARNING: The final image will be 10-20GB in size!"
+echo ""
+echo "NOTE: If you're building on Apple Silicon (M1/M2/M3),"
+echo "      Docker will use emulation which may be slower."
+echo "      The image will still work on x86_64 servers."
+echo ""
+
+# Check if ollama-models directory exists
+if [ ! -d "ollama-models" ]; then
+    echo "ERROR: ollama-models directory not found!"
+    echo ""
+    echo "Please run ./export-ollama-models.sh first to export the models."
+    exit 1
+fi
+
+echo "✓ Found ollama-models directory"
+echo ""
+
+# Check if Ollama binary exists
+if [ ! -f "ollama-linux-amd64.tgz" ]; then
+    echo "ERROR: ollama-linux-amd64.tgz not found!"
+    echo ""
+    echo "Please download it first:"
+    echo "  curl -L -o ollama-linux-amd64.tgz https://github.com/ollama/ollama/releases/download/v0.13.1/ollama-linux-amd64.tgz"
+    echo ""
+    exit 1
+fi
+
+echo "✓ Found ollama-linux-amd64.tgz"
+echo ""
+
+# Check disk space
+AVAILABLE_SPACE=$(df -h . | awk 'NR==2 {print $4}')
+echo "Available disk space: $AVAILABLE_SPACE"
+echo "Required: ~20GB for build process"
+echo ""
+
+read -p "Continue with build? (y/n) " -n 1 -r
+echo
+if [[ ! $REPLY =~ ^[Yy]$ ]]; then
+    echo "Build cancelled."
+    exit 1
+fi
+
+echo ""
+echo "=========================================="
+echo "Building Docker image..."
+echo "=========================================="
+echo "Platform: linux/amd64 (x86_64)"
+echo "This may take 20-40 minutes depending on your machine..."
+echo ""
+
+# Build for amd64 platform explicitly
+docker build --platform linux/amd64 -f Dockerfile.allinone -t ${IMAGE_NAME}:${IMAGE_TAG} .
+
+echo ""
+echo "=========================================="
+echo "Build complete!"
+echo "=========================================="
+docker images | grep ${IMAGE_NAME}
+
+echo ""
+echo "=========================================="
+echo "Exporting image to ${EXPORT_FILE}..."
+echo "=========================================="
+echo "This will take several minutes..."
+docker save -o ${EXPORT_FILE} ${IMAGE_NAME}:${IMAGE_TAG}
+
+echo ""
+echo "=========================================="
+echo "Export complete!"
+echo "=========================================="
+ls -lh ${EXPORT_FILE}
+
+echo ""
+echo "=========================================="
+echo "Deployment Instructions"
+echo "=========================================="
+echo ""
+echo "1. Transfer ${EXPORT_FILE} to target server:"
+echo "   scp ${EXPORT_FILE} user@server:/path/"
+echo ""
+echo "2. On target server, load the image:"
+echo "   docker load -i ${EXPORT_FILE}"
+echo ""
+echo "3. Run the container:"
+echo ""
+echo "   CPU mode:"
+echo "   docker run -d \\"
+echo "     --name system-prompt-optimizer \\"
+echo "     -p 8010:8010 \\"
+echo "     --restart unless-stopped \\"
+echo "     ${IMAGE_NAME}:${IMAGE_TAG}"
+echo ""
+echo "   GPU mode (recommended if NVIDIA GPU available):"
+echo "   docker run -d \\"
+echo "     --name system-prompt-optimizer \\"
+echo "     --gpus all \\"
+echo "     -p 8010:8010 \\"
+echo "     --restart unless-stopped \\"
+echo "     ${IMAGE_NAME}:${IMAGE_TAG}"
+echo ""
+echo "   Note: Port 11434 (Ollama) is optional and only needed for debugging."
+echo "   GPU mode provides 5-10x faster inference. See GPU_DEPLOYMENT.md for details."
+echo ""
+echo "4. Access the application:"
+echo "   http://<server-ip>:8010/ui/opro.html"
+echo ""
+echo "See DEPLOYMENT.md for more details."
+
--- a/build-and-export.sh
+++ b/build-and-export.sh
@@ -0,0 +1,37 @@
+#!/bin/bash
+
+# Build and export Docker image for offline deployment
+# Usage: ./build-and-export.sh
+
+set -e
+
+IMAGE_NAME="system-prompt-optimizer"
+IMAGE_TAG="latest"
+EXPORT_FILE="${IMAGE_NAME}.tar"
+
+echo "=========================================="
+echo "Building Docker image..."
+echo "=========================================="
+docker build -t ${IMAGE_NAME}:${IMAGE_TAG} .
+
+echo ""
+echo "=========================================="
+echo "Exporting Docker image to ${EXPORT_FILE}..."
+echo "=========================================="
+docker save -o ${EXPORT_FILE} ${IMAGE_NAME}:${IMAGE_TAG}
+
+echo ""
+echo "=========================================="
+echo "Export complete!"
+echo "=========================================="
+ls -lh ${EXPORT_FILE}
+
+echo ""
+echo "Next steps:"
+echo "1. Transfer ${EXPORT_FILE} to target server"
+echo "2. Transfer docker-compose.yml to target server (optional)"
+echo "3. On target server, run: docker load -i ${EXPORT_FILE}"
+echo "4. On target server, run: docker-compose up -d"
+echo ""
+echo "See DEPLOYMENT.md for detailed instructions."
+
--- a/config.py
+++ b/config.py
@@ -7,7 +7,7 @@ APP_CONTACT = {"name": "OPRO Team", "url": "http://127.0.0.1:8010/ui/"}
 OLLAMA_HOST = "http://127.0.0.1:11434"
 OLLAMA_GENERATE_URL = f"{OLLAMA_HOST}/api/generate"
 OLLAMA_TAGS_URL = f"{OLLAMA_HOST}/api/tags"
-DEFAULT_CHAT_MODEL = "qwen3:8b"
+DEFAULT_CHAT_MODEL = "qwen3:14b"
 DEFAULT_EMBED_MODEL = "qwen3-embedding:4b"

 # Xinference
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -0,0 +1,23 @@
+version: '3.8'
+
+services:
+  app:
+    build: .
+    container_name: system-prompt-optimizer
+    ports:
+      - "8010:8010"
+    environment:
+      - OLLAMA_HOST=http://host.docker.internal:11434
+      - PYTHONUNBUFFERED=1
+    volumes:
+      - ./outputs:/app/outputs
+    restart: unless-stopped
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8010/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 5s
+
--- a/docker-entrypoint.sh
+++ b/docker-entrypoint.sh
@@ -0,0 +1,103 @@
+#!/bin/bash
+
+set -e
+
+echo "=========================================="
+echo "System Prompt Optimizer - Starting Up"
+echo "=========================================="
+echo ""
+
+# Check if Ollama binary exists
+if ! command -v ollama &> /dev/null; then
+    echo "ERROR: Ollama binary not found!"
+    echo "Expected location: /usr/bin/ollama or /usr/local/bin/ollama"
+    ls -la /usr/bin/ollama* 2>/dev/null || echo "No ollama in /usr/bin/"
+    ls -la /usr/local/bin/ollama* 2>/dev/null || echo "No ollama in /usr/local/bin/"
+    exit 1
+fi
+
+echo "✓ Ollama binary found: $(which ollama)"
+echo ""
+
+# Check if model files exist
+echo "Checking model files..."
+if [ ! -d "/root/.ollama/models" ]; then
+    echo "ERROR: /root/.ollama/models directory not found!"
+    exit 1
+fi
+
+MANIFEST_COUNT=$(find /root/.ollama/models/manifests -type f 2>/dev/null | wc -l)
+BLOB_COUNT=$(find /root/.ollama/models/blobs -type f 2>/dev/null | wc -l)
+
+echo "✓ Found $MANIFEST_COUNT manifest files"
+echo "✓ Found $BLOB_COUNT blob files"
+
+if [ "$BLOB_COUNT" -lt 10 ]; then
+    echo "WARNING: Very few blob files found. Models may not be complete."
+fi
+echo ""
+
+echo "Starting Ollama service..."
+ollama serve > /tmp/ollama.log 2>&1 &
+OLLAMA_PID=$!
+
+# Wait for Ollama to be ready
+echo "Waiting for Ollama to start..."
+OLLAMA_READY=false
+for i in {1..60}; do
+    if curl -s http://localhost:11434/api/tags > /dev/null 2>&1; then
+        echo "Ollama is ready!"
+        OLLAMA_READY=true
+        break
+    fi
+    echo "Waiting for Ollama... ($i/60)"
+    sleep 3
+done
+
+if [ "$OLLAMA_READY" = false ]; then
+    echo ""
+    echo "ERROR: Ollama failed to start within 3 minutes!"
+    echo ""
+    echo "Ollama logs:"
+    cat /tmp/ollama.log
+    echo ""
+    echo "Check full logs with: docker logs system-prompt-optimizer"
+    exit 1
+fi
+
+# Check if models exist, if not, show warning
+echo ""
+echo "Checking for models..."
+ollama list
+
+echo ""
+if ! ollama list | grep -q "qwen3:14b"; then
+    echo "ERROR: qwen3:14b model not found!"
+    echo "The application requires qwen3:14b to function properly."
+    echo ""
+    echo "Available models:"
+    ollama list
+    echo ""
+    exit 1
+fi
+
+if ! ollama list | grep -q "qwen3-embedding"; then
+    echo "WARNING: qwen3-embedding model not found!"
+    echo "The application requires qwen3-embedding:4b for embeddings."
+    echo "Continuing anyway, but embeddings may not work."
+fi
+
+echo ""
+echo "✓ All required models are available"
+echo ""
+echo "=========================================="
+echo "Starting FastAPI application..."
+echo "=========================================="
+echo "Application will be available at:"
+echo "  - Web UI: http://localhost:8010/ui/opro.html"
+echo "  - API Docs: http://localhost:8010/docs"
+echo "  - Ollama: http://localhost:11434"
+echo ""
+
+exec uvicorn _qwen_xinference_demo.api:app --host 0.0.0.0 --port 8010
+
--- a/export-ollama-models.sh
+++ b/export-ollama-models.sh
@@ -0,0 +1,168 @@
+#!/bin/bash
+
+# Export Ollama models for offline deployment
+# This script copies Ollama models from your local machine
+# so they can be bundled into the Docker image
+#
+# Required models:
+# - qwen3:14b (main chat model)
+# - qwen3-embedding:4b (embedding model)
+
+set -e
+
+MODELS_DIR="ollama-models"
+OLLAMA_MODELS_PATH="$HOME/.ollama"
+
+echo "=========================================="
+echo "Exporting Ollama models for offline deployment"
+echo "=========================================="
+
+# Check if Ollama is installed
+if ! command -v ollama &> /dev/null; then
+    echo "ERROR: Ollama is not installed or not in PATH"
+    exit 1
+fi
+
+# Check if required models are available
+echo ""
+echo "Checking for required models..."
+MISSING_MODELS=0
+
+if ! ollama list | grep -q "qwen3:14b"; then
+    echo "ERROR: qwen3:14b model not found!"
+    echo "Please run: ollama pull qwen3:14b"
+    MISSING_MODELS=1
+fi
+
+if ! ollama list | grep -q "qwen3-embedding:4b"; then
+    echo "ERROR: qwen3-embedding:4b model not found!"
+    echo "Please run: ollama pull qwen3-embedding:4b"
+    MISSING_MODELS=1
+fi
+
+if [ $MISSING_MODELS -eq 1 ]; then
+    echo ""
+    echo "Please download the required models first:"
+    echo "  ollama pull qwen3:14b"
+    echo "  ollama pull qwen3-embedding:4b"
+    exit 1
+fi
+
+echo "✓ All required models found"
+
+# Check if Ollama directory exists
+if [ ! -d "$OLLAMA_MODELS_PATH" ]; then
+    echo "ERROR: Ollama directory not found at $OLLAMA_MODELS_PATH"
+    exit 1
+fi
+
+# Create export directory structure
+echo ""
+echo "Creating export directory: $MODELS_DIR"
+rm -rf "$MODELS_DIR"
+mkdir -p "$MODELS_DIR/models/manifests/registry.ollama.ai/library"
+mkdir -p "$MODELS_DIR/models/blobs"
+
+echo ""
+echo "Copying only required models (qwen3:14b and qwen3-embedding:4b)..."
+echo "This may take several minutes (models are large)..."
+
+# Function to get blob hashes from manifest
+get_blobs_from_manifest() {
+    local manifest_file=$1
+    # Extract all sha256 hashes from the manifest JSON
+    grep -oE 'sha256:[a-f0-9]{64}' "$manifest_file" 2>/dev/null | sed 's/sha256://' | sort -u
+}
+
+# Function to copy model files
+copy_model() {
+    local model_name=$1
+    local model_tag=$2
+    local manifest_dir="$OLLAMA_MODELS_PATH/models/manifests/registry.ollama.ai/library/$model_name"
+
+    if [ ! -d "$manifest_dir" ]; then
+        echo "ERROR: Model manifest not found: $manifest_dir"
+        return 1
+    fi
+
+    echo "  Copying $model_name:$model_tag manifest..."
+    mkdir -p "$MODELS_DIR/models/manifests/registry.ollama.ai/library/$model_name"
+
+    # Copy the specific tag manifest
+    if [ -f "$manifest_dir/$model_tag" ]; then
+        cp "$manifest_dir/$model_tag" "$MODELS_DIR/models/manifests/registry.ollama.ai/library/$model_name/"
+
+        # Get all blob hashes referenced in this manifest
+        echo "  Finding blob files for $model_name:$model_tag..."
+        local blob_hashes=$(get_blobs_from_manifest "$manifest_dir/$model_tag")
+        local blob_count=0
+
+        for blob_hash in $blob_hashes; do
+            local blob_file="$OLLAMA_MODELS_PATH/models/blobs/sha256-$blob_hash"
+            if [ -f "$blob_file" ]; then
+                cp "$blob_file" "$MODELS_DIR/models/blobs/" 2>/dev/null
+                blob_count=$((blob_count + 1))
+            fi
+        done
+
+        echo "  ✓ $model_name:$model_tag copied ($blob_count blobs)"
+    else
+        echo "ERROR: Manifest file not found: $manifest_dir/$model_tag"
+        return 1
+    fi
+}
+
+# Copy required models with specific tags
+copy_model "qwen3" "14b" || exit 1
+copy_model "qwen3-embedding" "4b" || exit 1
+
+echo ""
+echo "=========================================="
+echo "Models exported successfully!"
+echo "=========================================="
+echo ""
+echo "Total size:"
+du -sh "$MODELS_DIR"
+
+echo ""
+echo "Models included:"
+if [ -d "$MODELS_DIR/models/manifests/registry.ollama.ai/library" ]; then
+    ls -lh "$MODELS_DIR/models/manifests/registry.ollama.ai/library/"
+fi
+
+echo ""
+echo "Blob files:"
+if [ -d "$MODELS_DIR/models/blobs" ]; then
+    echo "  Total blobs: $(ls -1 "$MODELS_DIR/models/blobs" | wc -l)"
+    du -sh "$MODELS_DIR/models/blobs"
+fi
+
+echo ""
+echo "=========================================="
+echo "Summary"
+echo "=========================================="
+echo "✓ Only qwen3:14b and qwen3-embedding:4b were exported"
+echo ""
+echo "Models in your Ollama that were NOT copied:"
+ollama list | grep -v "qwen3:14b" | grep -v "qwen3-embedding:4b" | tail -n +2 || echo "  (none)"
+echo ""
+echo "This keeps the Docker image size minimal!"
+
+echo ""
+echo "=========================================="
+echo "Next steps:"
+echo "=========================================="
+echo "1. Build the all-in-one Docker image:"
+echo "   ./build-allinone.sh"
+echo ""
+echo "2. Or manually:"
+echo "   docker build -f Dockerfile.allinone -t system-prompt-optimizer:allinone ."
+echo ""
+echo "3. Export the image:"
+echo "   docker save -o system-prompt-optimizer-allinone.tar system-prompt-optimizer:allinone"
+echo ""
+echo "4. Transfer to target server:"
+echo "   scp system-prompt-optimizer-allinone.tar user@server:/path/"
+echo ""
+echo "Note: The final Docker image will be very large (10-20GB) due to the models."
+
--- a/frontend/opro.html
+++ b/frontend/opro.html
@@ -6,7 +6,7 @@
    <meta http-equiv="Cache-Control" content="no-cache, no-store, must-revalidate">
    <meta http-equiv="Pragma" content="no-cache">
    <meta http-equiv="Expires" content="0">
-    <title>OPRO - System Instruction Optimizer</title>
+    <title>系统提示词优化</title>
    <script crossorigin src="https://unpkg.com/react@18/umd/react.production.min.js"></script>
    <script crossorigin src="https://unpkg.com/react-dom@18/umd/react-dom.production.min.js"></script>
    <script src="https://cdn.tailwindcss.com"></script>
@@ -304,41 +304,55 @@
                createNewRun(msg);
            }

-            async function handleContinueOptimize(selectedInstruction, selectedScore) {
-                if (!currentRunId || loading) return;
+            async function handleContinueOptimize(selectedInstruction, allCandidates) {
+                if (!currentRunId || loading || !selectedInstruction) return;

-                // First, evaluate the selected instruction to add it to trajectory
-                if (selectedInstruction) {
-                    setLoading(true);
-                    try {
-                        // Add the selected instruction to trajectory
-                        const res = await fetch(`${API_BASE}/opro/evaluate`, {
-                            method: 'POST',
-                            headers: { 'Content-Type': 'application/json' },
-                            body: JSON.stringify({
-                                run_id: currentRunId,
-                                instruction: selectedInstruction
-                            })
-                        });
-                        const data = await res.json();
+                setLoading(true);
+                try {
+                    // Get rejected instructions (all except the selected one)
+                    const rejectedInstructions = allCandidates
+                        .map(c => c.instruction)
+                        .filter(inst => inst !== selectedInstruction);

-                        if (!data.success) {
-                            throw new Error(data.error || 'Failed to evaluate instruction');
-                        }
+                    // Call the refinement endpoint
+                    const res = await fetch(`${API_BASE}/opro/refine`, {
+                        method: 'POST',
+                        headers: { 'Content-Type': 'application/json' },
+                        body: JSON.stringify({
+                            run_id: currentRunId,
+                            selected_instruction: selectedInstruction,
+                            rejected_instructions: rejectedInstructions
+                        })
+                    });
+                    const data = await res.json();

-                        console.log('Evaluated instruction, score:', data.data.score);
-                    } catch (err) {
-                        alert('评估指令失败: ' + err.message);
-                        console.error('Error evaluating instruction:', err);
-                        setLoading(false);
-                        return;
-                    } finally {
-                        setLoading(false);
+                    if (!data.success) {
+                        throw new Error(data.error || 'Failed to refine instruction');
                    }
-                }

-                // Then generate new candidates based on updated trajectory
-                await generateCandidates(currentRunId);
+                    // Add refined candidates to messages
+                    const newMessage = {
+                        role: 'assistant',
+                        type: 'candidates',
+                        iteration: data.data.iteration,
+                        candidates: data.data.candidates
+                    };
+
+                    setMessages(prev => {
+                        const updated = [...prev, newMessage];
+                        // Save to session messages
+                        setSessionMessages(prevSessions => ({
+                            ...prevSessions,
+                            [currentSessionId]: updated
+                        }));
+                        return updated;
+                    });
+                } catch (err) {
+                    alert('优化失败: ' + err.message);
+                    console.error('Error refining instruction:', err);
+                } finally {
+                    setLoading(false);
+                }
            }

            function handleExecute(instruction) {
@@ -495,7 +509,7 @@
                    // Header
                    React.createElement('div', { className: 'px-4 py-3 border-b border-gray-200 bg-white flex items-center gap-3' },
                        React.createElement('h1', { className: 'text-lg font-normal text-gray-800' },
-                            'OPRO'
+                            '系统提示词优化'
                        ),
                        currentSessionId && React.createElement('div', { className: 'text-sm text-gray-500' },
                            sessions.find(s => s.session_id === currentSessionId)?.session_name || '当前会话'
@@ -537,7 +551,7 @@
                                                        ),
                                                        React.createElement('div', { className: 'flex gap-2' },
                                                            React.createElement('button', {
-                                                                onClick: () => handleContinueOptimize(cand.instruction, cand.score),
+                                                                onClick: () => handleContinueOptimize(cand.instruction, msg.candidates),
                                                                disabled: loading,
                                                                className: 'px-4 py-2 bg-white border border-gray-300 text-gray-700 rounded-lg hover:bg-gray-50 disabled:bg-gray-100 disabled:text-gray-400 disabled:cursor-not-allowed transition-colors text-sm font-medium'
                                                            }, '继续优化'),
--- a/requirements.txt
+++ b/requirements.txt
@@ -0,0 +1,7 @@
+fastapi==0.109.0
+uvicorn==0.27.0
+requests==2.31.0
+numpy==1.26.3
+scikit-learn==1.4.0
+pydantic==2.5.3
+
Author	SHA1	Message	Date
leehwui	0b5319b31c	Add GPU support and improve Docker deployment - Add GPU deployment support with NVIDIA runtime - Update Dockerfile.allinone with GPU environment variables - Add comprehensive GPU_DEPLOYMENT.md guide - Make port 11434 (Ollama) optional for security - Update DEPLOYMENT.md with CPU and GPU deployment options - Simplify default docker run commands - Update healthcheck to only check web application - Add memory requirements documentation - Create MEMORY_REQUIREMENTS.md with model comparison - Add build-8b.sh script for lower memory usage - Document OOM troubleshooting steps - Improve Docker build process - Add BUILD_TROUBLESHOOTING.md for common issues - Add DISTRIBUTION.md for image distribution methods - Update .gitignore to exclude large binary files - Improve docker-entrypoint.sh with better diagnostics - Update .dockerignore to include ollama-linux-amd64.tgz - Add backup file exclusions to .gitignore	2025-12-08 17:08:45 +08:00
leehwui	6426b73a5e	fix: export only required models instead of entire Ollama directory - Changed export-ollama-models.sh to selectively copy only qwen3:14b and qwen3-embedding:4b - Parses manifest files to identify required blob files - Significantly reduces Docker image size by excluding unrelated models - Added summary showing which models were skipped This prevents accidentally including other models (like deepseek-r1, bge-m3, etc.) that may exist in the user's Ollama directory but are not needed for the project.	2025-12-08 12:00:11 +08:00
leehwui	26f8e0c648	feat: add Docker support for offline deployment with qwen3:14b Major additions: - All-in-One Docker image with Ollama + models bundled - Separate deployment option for existing Ollama installations - Changed default model from qwen3:8b to qwen3:14b - Comprehensive deployment documentation Files added: - Dockerfile: Basic app-only image - Dockerfile.allinone: Complete image with Ollama + models - docker-compose.yml: Easy deployment configuration - docker-entrypoint.sh: Startup script for all-in-one image - requirements.txt: Python dependencies - .dockerignore: Exclude unnecessary files from image Scripts: - export-ollama-models.sh: Export models from local Ollama - build-allinone.sh: Build complete offline-deployable image - build-and-export.sh: Build and export basic image Documentation: - DEPLOYMENT.md: Comprehensive deployment guide - QUICK_START.md: Quick reference for common tasks Configuration: - Updated config.py: DEFAULT_CHAT_MODEL = qwen3:14b - Updated frontend/opro.html: Page title to 系统提示词优化	2025-12-08 10:10:38 +08:00
leehwui	65cdcf29dc	refactor: replace OPRO with simple iterative refinement Major changes: - Remove fake OPRO evaluation (no more fake 0.5 scores) - Add simple refinement based on user selection - New endpoint: POST /opro/refine (selected + rejected instructions) - Update prompt generation to focus on comprehensive coverage instead of style variety - All generated instructions now start with role definition (你是一个...) - Update README to reflect new approach and API endpoints Technical details: - Added refine_based_on_selection() in prompt_utils.py - Added refine_instruction_candidates() in user_prompt_optimizer.py - Added OPRORefineReq model and /opro/refine endpoint in api.py - Updated frontend handleContinueOptimize() to use new refinement flow - Changed prompt requirements from 'different styles' to 'comprehensive coverage' - Added role definition requirement as first item in all prompt templates	2025-12-08 09:43:20 +08:00