优化 Dockerfile

Dockerfile

@@ -13,29 +13,8 @@ USER root
 
 WORKDIR /ragflow
 
-# Set UV HTTP timeout to handle large package downloads (e.g., nvidia-cusolver-cu12)
+# Python dependencies are already installed in base image
-# Default is 30s, increase to 600s (10 minutes) for large packages
+# Build web application
-ENV UV_HTTP_TIMEOUT=600
-
-# install dependencies from pyproject.toml
-COPY pyproject.toml ./
-# https://github.com/astral-sh/uv/issues/10462
-# uv records index url into uv.lock but doesn't failover among multiple indexes
-# Generate uv.lock from pyproject.toml and install dependencies with cache
-RUN --mount=type=cache,id=ragflow_uv,target=/root/.cache/uv,sharing=locked \
-    if [ "$NEED_MIRROR" == "1" ]; then \
-        uv lock --index-url https://mirrors.aliyun.com/pypi/simple; \
-        sed -i 's|pypi.org|mirrors.aliyun.com/pypi|g' uv.lock; \
-    else \
-        uv lock; \
-        sed -i 's|mirrors.aliyun.com/pypi|pypi.org|g' uv.lock; \
-    fi; \
-    if [ "$LIGHTEN" == "1" ]; then \
-        uv sync --python 3.10 --frozen; \
-    else \
-        uv sync --python 3.10 --frozen --all-extras; \
-    fi
-
 COPY web web
 COPY docs docs
 RUN --mount=type=cache,id=ragflow_npm,target=/root/.npm,sharing=locked \
@@ -58,11 +37,7 @@ USER root
 
 WORKDIR /ragflow
 
-# Copy Python environment and packages
+# Python environment is already set up in base image
-ENV VIRTUAL_ENV=/ragflow/.venv
-COPY --from=builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
-ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
-
 ENV PYTHONPATH=/ragflow/
 
 COPY web web

Dockerfile.base

@@ -137,3 +137,31 @@ RUN --mount=type=bind,from=infiniflow/ragflow_deps:latest,source=/,target=/deps
         dpkg -i /deps/libssl1.1_1.1.1f-1ubuntu2_arm64.deb; \
     fi
 
+# Install Python dependencies from pyproject.toml
+# This is done in base image since dependencies don't change frequently
+COPY pyproject.toml ./
+# https://github.com/astral-sh/uv/issues/10462
+# uv records index url into uv.lock but doesn't failover among multiple indexes
+# Generate uv.lock from pyproject.toml and install dependencies with cache
+# Set UV HTTP timeout based on mirror usage:
+# - With mirror (NEED_MIRROR=1): 600s for potentially slower mirror connections
+# - Without mirror (abroad): 300s should be sufficient for PyPI with good network
+RUN --mount=type=cache,id=ragflow_uv,target=/root/.cache/uv,sharing=locked \
+    export UV_HTTP_TIMEOUT=$([ "$NEED_MIRROR" == "1" ] && echo "600" || echo "300") && \
+    if [ "$NEED_MIRROR" == "1" ]; then \
+        uv lock --index-url https://mirrors.aliyun.com/pypi/simple; \
+        sed -i 's|pypi.org|mirrors.aliyun.com/pypi|g' uv.lock; \
+    else \
+        uv lock; \
+        sed -i 's|mirrors.aliyun.com/pypi|pypi.org|g' uv.lock; \
+    fi && \
+    if [ "$LIGHTEN" == "1" ]; then \
+        uv sync --python 3.10 --frozen; \
+    else \
+        uv sync --python 3.10 --frozen --all-extras; \
+    fi
+
+# Set Python environment variables
+ENV VIRTUAL_ENV=/ragflow/.venv
+ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
+

docker/docker-compose-base.yml

@@ -4,7 +4,7 @@ services:
     container_name: ragflow-opensearch-01
     profiles:
       - opensearch
-    image: hub.icert.top/opensearchproject/opensearch:2.19.1
+    image: hub.icert.top/opensearchproject/opensearch:3.3.2
     volumes:
       - osdata01:/usr/share/opensearch/data
     ports:
@@ -38,6 +38,61 @@ services:
       - ragflow
     restart: on-failure
 
+  opensearch-dashboards:
+    container_name: ragflow-opensearch-dashboards
+    profiles:
+      - opensearch
+    image: opensearchproject/opensearch-dashboards:3.3.0
+    env_file: .env
+    environment:
+      - OPENSEARCH_HOSTS=["http://opensearch01:9201"]
+      - OPENSEARCH_USERNAME=admin
+      - OPENSEARCH_PASSWORD=${OPENSEARCH_PASSWORD}
+      - TZ=${TIMEZONE}
+    ports:
+      - 5601:5601
+    depends_on:
+      - opensearch01
+    networks:
+      - ragflow
+    restart: on-failure
+
+  es01:
+    container_name: ragflow-es-01
+    profiles:
+      - elasticsearch
+    image: elasticsearch:${STACK_VERSION}
+    volumes:
+      - esdata01:/usr/share/elasticsearch/data
+    ports:
+      - ${ES_PORT}:9200
+    env_file: .env
+    environment:
+      - node.name=es01
+      - ELASTIC_PASSWORD=${ELASTIC_PASSWORD}
+      - bootstrap.memory_lock=false
+      - discovery.type=single-node
+      - xpack.security.enabled=true
+      - xpack.security.http.ssl.enabled=false
+      - xpack.security.transport.ssl.enabled=false
+      - cluster.routing.allocation.disk.watermark.low=5gb
+      - cluster.routing.allocation.disk.watermark.high=3gb
+      - cluster.routing.allocation.disk.watermark.flood_stage=2gb
+      - TZ=${TIMEZONE}
+    mem_limit: ${MEM_LIMIT}
+    ulimits:
+      memlock:
+        soft: -1
+        hard: -1
+    healthcheck:
+      test: ["CMD-SHELL", "curl http://localhost:9200"]
+      interval: 10s
+      timeout: 10s
+      retries: 120
+    networks:
+      - ragflow
+    restart: on-failure
+
 
   postgres:
     image: postgres:15