refactor(docker): 更新 Docker 配置，优化 PostgreSQL 启动和健康检查逻辑，提升系统稳定性和性能

docker-compose.yml

@@ -3,9 +3,6 @@ services:
     build:
       context: .
       dockerfile: docker/api.Dockerfile
-      args:
-        http_proxy: ${HTTP_PROXY:-}
-        https_proxy: ${HTTPS_PROXY:-}
     image: yuxi-api:0.2.0.dev
     container_name: api-dev
     working_dir: /app
@@ -15,13 +12,6 @@ services:
       - ./saves:/app/saves
       - ./test:/app/test
       - ${MODEL_DIR:-./models}:/models  # 使用默认值处理未定义的环境变量
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              device_ids: ['0']  # 使用GPU 1
-              capabilities: [gpu]
     ports:
       - "5050:5050"
     networks:
@@ -45,16 +35,19 @@ services:
       - POSTGRES_DATABASE=${POSTGRES_DATABASE:-lightrag}
       - POSTGRES_USER=${POSTGRES_USER:-lightrag}
       - POSTGRES_PASSWORD=${POSTGRES_PASSWORD:-lightrag}
+      # 连接池配置
+      - POSTGRES_MAX_CONNECTIONS=50
+      - POSTGRES_MIN_CONNECTIONS=5
       - MODEL_DIR=/models
       - RUNNING_IN_DOCKER=true
     command: uv run uvicorn server.main:app --host 0.0.0.0 --port 5050 --reload
     restart: unless-stopped
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5050/health || exit 1"]
-      interval: 20s
+      interval: 30s
-      timeout: 10s
+      timeout: 15s
-      retries: 5
+      retries: 8
-      start_period: 60s
+      start_period: 180s
     depends_on:
       postgres:
         condition: service_healthy
@@ -103,11 +96,11 @@ services:
     ports:
       - "5432:5432"
     healthcheck:
-      test: ["CMD-SHELL", "PGPASSWORD=${POSTGRES_PASSWORD:-lightrag} psql -h localhost -U ${POSTGRES_USER:-lightrag} -d ${POSTGRES_DATABASE:-lightrag} -c 'SELECT 1' || exit 1"]
+      test: ["CMD-SHELL", "PGPASSWORD=${POSTGRES_PASSWORD:-lightrag} psql -h localhost -U ${POSTGRES_USER:-lightrag} -d ${POSTGRES_DATABASE:-lightrag} -c \"SELECT ag_catalog.create_graph('test_ready');\" || PGPASSWORD=${POSTGRES_PASSWORD:-lightrag} psql -h localhost -U ${POSTGRES_USER:-lightrag} -d ${POSTGRES_DATABASE:-lightrag} -c 'SELECT 1'"]
-      interval: 20s
+      interval: 30s
-      timeout: 10s
+      timeout: 15s
-      retries: 10
+      retries: 15
-      start_period: 60s
+      start_period: 120s
     networks:
       - app-network
     restart: unless-stopped

docker/api.Dockerfile

@@ -1,34 +1,34 @@
-# 使用基础镜像
+# 使用轻量级Python基础镜像
-FROM nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04
+FROM python:3.11-slim
 COPY --from=ghcr.io/astral-sh/uv:0.7.2 /uv /uvx /bin/
 
 # 设置工作目录
 WORKDIR /app
 
 # 环境变量设置
-ARG http_proxy
-ARG https_proxy
 ENV TZ=Asia/Shanghai \
-    UV_LINK_MODE=copy
+    UV_LINK_MODE=copy \
+    DEBIAN_FRONTEND=noninteractive
 
-# 只有当代理变量不为空时才设置代理
+# 设置代理和时区，更换镜像源，安装系统依赖 - 合并为一个RUN减少层数
-RUN if [ -n "$http_proxy" ]; then echo "export http_proxy=$http_proxy" >> /etc/environment; fi
+RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone && \
-RUN if [ -n "$https_proxy" ]; then echo "export https_proxy=$https_proxy" >> /etc/environment; fi
+    # 更换为阿里云镜像源加速下载
-
+    sed -i 's/deb.debian.org/mirrors.aliyun.com/g' /etc/apt/sources.list.d/debian.sources && \
-RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
+    sed -i 's/security.debian.org/mirrors.aliyun.com/g' /etc/apt/sources.list.d/debian.sources && \
-
+    # 安装系统依赖
-# 安装系统依赖
+    apt-get update && apt-get install -y --no-install-recommends \
-RUN apt-get update && apt-get install -y \
+        python3-dev \
-    python3-dev \
+        ffmpeg \
-    ffmpeg \
+        libsm6 \
-    libsm6 \
+        libxext6 \
-    libxext6
+        curl \
+        && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 
 # 复制项目配置文件
 COPY ../pyproject.toml /app/pyproject.toml
 COPY ../.python-version /app/.python-version
 
-# 安装依赖项（不使用lock文件）
+# 安装依赖项
 RUN --mount=type=cache,target=/root/.cache/uv \
     uv sync --no-install-project
 

docker/init-postgres.sh

@@ -16,9 +16,13 @@ echo "PostgreSQL service started, waiting for it to be ready..."
 # 等待 PostgreSQL 完全启动
 while ! su - postgres -c "pg_isready" > /dev/null 2>&1; do
     echo "Waiting for PostgreSQL to be ready..."
-    sleep 2
+    sleep 5
 done
 
+# 额外等待以确保数据库完全启动
+echo "PostgreSQL is ready, waiting additional time for full initialization..."
+sleep 10
+
 echo "PostgreSQL is ready, creating user and database..."
 
 # 创建用户（如果不存在）
@@ -142,7 +146,11 @@ CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_lightrag_doc_status_updated_at ON li
 
 # 等待图表创建完成后创建 AGE 相关索引
 echo "Waiting for graph tables to be fully initialized..."
-sleep 5
+sleep 15
+
+# 验证 AGE 扩展是否正确加载
+echo "Verifying AGE extension is working..."
+su - postgres -c "psql -d ${POSTGRES_DATABASE:-lightrag} -c \"SELECT ag_catalog.create_graph('test_graph'); SELECT ag_catalog.drop_graph('test_graph', true);\"" || echo "AGE extension verification failed, but continuing..."
 
 echo "Creating AGE performance indexes..."
 
@@ -242,10 +250,32 @@ su - postgres -c "psql -c \"ALTER SYSTEM SET effective_cache_size = '1GB';\""
 su - postgres -c "psql -c \"ALTER SYSTEM SET maintenance_work_mem = '64MB';\""
 su - postgres -c "psql -c \"ALTER SYSTEM SET random_page_cost = 1.1;\""
 su - postgres -c "psql -c \"ALTER SYSTEM SET effective_io_concurrency = 200;\""
-su - postgres -c "psql -c \"ALTER SYSTEM SET work_mem = '4MB';\""
+su - postgres -c "psql -c \"ALTER SYSTEM SET work_mem = '8MB';\""
 
-# 启用查询计划缓存
+# 连接和查询超时配置
+su - postgres -c "psql -c \"ALTER SYSTEM SET statement_timeout = '300000';\""  # 5分钟查询超时
+su - postgres -c "psql -c \"ALTER SYSTEM SET idle_in_transaction_session_timeout = '600000';\""  # 10分钟事务超时
+su - postgres -c "psql -c \"ALTER SYSTEM SET tcp_keepalives_idle = '600';\""  # TCP keepalive 设置
+su - postgres -c "psql -c \"ALTER SYSTEM SET tcp_keepalives_interval = '30';\""
+su - postgres -c "psql -c \"ALTER SYSTEM SET tcp_keepalives_count = '3';\""
+
+# 查询优化配置
+su - postgres -c "psql -c \"ALTER SYSTEM SET max_parallel_workers_per_gather = '2';\""
+su - postgres -c "psql -c \"ALTER SYSTEM SET max_parallel_workers = '4';\""
+su - postgres -c "psql -c \"ALTER SYSTEM SET enable_parallel_hash = 'on';\""
+
+# 内存和查询限制优化
+su - postgres -c "psql -c \"ALTER SYSTEM SET temp_buffers = '16MB';\""
+su - postgres -c "psql -c \"ALTER SYSTEM SET max_stack_depth = '2MB';\""
+su - postgres -c "psql -c \"ALTER SYSTEM SET huge_pages = 'try';\""
+
+# 启用查询计划缓存和日志记录
 su - postgres -c "psql -c \"ALTER SYSTEM SET plan_cache_mode = 'auto';\""
+su - postgres -c "psql -c \"ALTER SYSTEM SET log_statement = 'all';\""
+su - postgres -c "psql -c \"ALTER SYSTEM SET log_duration = 'on';\""
+su - postgres -c "psql -c \"ALTER SYSTEM SET log_min_duration_statement = '1000';\""  # 记录超过1秒的查询
+su - postgres -c "psql -c \"ALTER SYSTEM SET log_disconnections = 'on';\""
+su - postgres -c "psql -c \"ALTER SYSTEM SET log_connections = 'on';\""
 
 # 重新加载配置
 su - postgres -c "psql -c \"SELECT pg_reload_conf();\""
@@ -303,6 +333,15 @@ echo "Graph: lightrag"
 echo "Tables: lightrag_kv_store, lightrag_doc_status + AGE graph tables"
 echo "Connection: postgresql://${POSTGRES_USER:-lightrag}:***@localhost:5432/${POSTGRES_DATABASE:-lightrag}"
 
+# 最终验证数据库完全准备就绪
+echo "Performing final readiness check..."
+sleep 5
+if PGPASSWORD="${POSTGRES_PASSWORD:-lightrag}" psql -h localhost -p 5432 -U ${POSTGRES_USER:-lightrag} -d ${POSTGRES_DATABASE:-lightrag} -c "SELECT ag_catalog.create_graph('final_test'); SELECT ag_catalog.drop_graph('final_test', true);" > /dev/null 2>&1; then
+    echo "✅ Database is fully ready for LightRAG operations!"
+else
+    echo "⚠️  Database basic operations work, but AGE may need more time to be fully ready"
+fi
+
 # 显示数据库统计信息
 echo "Database statistics:"
 su - postgres -c "psql -d ${POSTGRES_DATABASE:-lightrag} -c \"

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "yuxi-know"
-version = "0.1.0"
+version = "0.2.0.dev"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.11"
@@ -10,7 +10,6 @@ dependencies = [
     "dashscope>=1.23.2",
     "docx2txt>=0.9",
     "fastapi>=0.115.12",
-    "flagembedding>=1.3.4",
     "graspologic>=3.3.0",
     "langchain-community>=0.3.22",
     "langchain-deepseek>=0.1.3",
@@ -60,6 +59,10 @@ dev = [
     "vllm>=0.8.5.post1",
 ]
 
-# uv 配置 - 使用阿里云镜像源
+# uv 配置 - 使用清华大学镜像源
 [tool.uv]
-index-url = "https://mirrors.aliyun.com/pypi/simple/"
+index-url = "https://pypi.tuna.tsinghua.edu.cn/simple/"
+extra-index-url = [
+    "https://mirrors.aliyun.com/pypi/simple/",
+    "https://pypi.douban.com/simple/"
+]