Update Dockerfile

Dockerfile

@@ -1,6 +1,7 @@
-# 调试版本 - 用于排查问题
+# 使用官方Python 3.10 slim镜像
 FROM python:3.10-slim
 
+# --- 1. 安装系统依赖 ---
 RUN apt-get update && apt-get install -y --no-install-recommends \
     git \
     git-lfs \
@@ -9,37 +10,54 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     curl \
     && rm -rf /var/lib/apt/lists/*
 
+# --- 2. 设置工作目录 ---
 WORKDIR /src
+
+# --- 3. Git LFS初始化 ---
 RUN git lfs install
 
-# 详细调试secrets和git clone（修复bash语法问题）
+# --- 4. 关键步骤：克隆私有仓库 ---
+# 保持你原有的secrets挂载方式，但修复bash语法问题
 RUN --mount=type=secret,id=GH_USER \
     --mount=type=secret,id=GH_TOKEN \
-    echo "=== 调试信息开始 ===" && \
-    echo "检查secrets目录:" && \
+    echo "Checking secrets..." && \
     ls -la /run/secrets/ && \
-    echo "GH_USER内容:" && \
-    cat /run/secrets/GH_USER && \
-    echo "GH_TOKEN长度:" && \
-    wc -c /run/secrets/GH_TOKEN && \
-    echo "开始设置变量..." && \
     GH_USER=$(cat /run/secrets/GH_USER) && \
     GH_TOKEN=$(cat /run/secrets/GH_TOKEN) && \
     echo "User: $GH_USER" && \
-    echo "Token已读取，长度正确" && \
-    echo "尝试克隆..." && \
+    echo "Starting git clone..." && \
     git clone https://$GH_USER:$GH_TOKEN@github.com/leoncool23/tcm_expert_builder.git && \
-    echo "克隆成功！" && \
-    ls -la tcm_expert_builder/ && \
-    echo "=== 调试信息结束 ==="
+    echo "Clone completed successfully" && \
+    ls -la tcm_expert_builder/
 
+# --- 5. 切换到项目目录 ---
 WORKDIR /src/tcm_expert_builder
 
-# 简单启动以测试基本功能
-RUN pip install flask gunicorn
-EXPOSE 7860
+# --- 6. 验证关键文件存在 ---
+RUN echo "Current directory:" && pwd && \
+    echo "Directory contents:" && ls -la && \
+    echo "Checking requirements.txt:" && cat requirements.txt
+
+# --- 7. 安装Python依赖 ---
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r requirements.txt
+
+# --- 8. 配置NLTK和ChromaDB环境 ---
+ENV NLTK_DATA=/usr/local/share/nltk_data
+ENV ANONYMIZED_TELEMETRY=false
+RUN python -m nltk.downloader -d $NLTK_DATA punkt stopwords || \
+    python -c "import nltk; nltk.download('punkt'); nltk.download('stopwords')"
 
-# 创建一个简单的测试应用
-RUN echo 'from flask import Flask\napp = Flask(__name__)\n@app.route("/")\ndef hello():\n    return "Hello from TCM Expert Builder!"\nif __name__ == "__main__":\n    app.run(host="0.0.0.0", port=7860)' > test_app.py
+# --- 9. 创建用户和设置权限 ---
+RUN useradd --create-home --shell /bin/bash appuser
+RUN chown -R appuser:appuser /src
+
+# --- 10. 以appuser身份创建目录 ---
+USER appuser
+RUN mkdir -p ./uploads ./data/vector_db ./data
+
+# --- 11. 暴露端口 ---
+EXPOSE 7860
 
-CMD ["python", "test_app.py"]
+# --- 12. 启动应用（保持你原有的gunicorn方式，但添加更多日志） ---
+CMD ["gunicorn", "--workers", "1", "--bind", "0.0.0.0:7860", "--timeout", "120", "--log-level", "debug", "--access-logfile", "-", "--error-logfile", "-", "app:app"]