Add go build files , reduce image size, update entrypoint-go.sh (#19041)

Add go build files , reduce image size, update entrypoint-go.sh

Dockerfile_go

@@ -0,0 +1,222 @@
+# base stage
+FROM ubuntu:24.04 AS base
+USER root
+SHELL ["/bin/bash", "-c"]
+
+ARG NEED_MIRROR=1
+
+#Optional parameter
+#If set NEED_MIRROR=1, and set GITEE_TOKEN="xxxxx" , donwload source from gitee.
+#If don't set GITEE_TOKEN , download from github
+#ARG GITEE_TOKEN=""
+
+WORKDIR /ragflow
+
+# copy models downloaded via download_deps.py
+# layout.laws/manual/paper.onnx are byte-identical to layout.onnx, so we
+# exclude them from the tar extract and symlink them to layout.onnx instead,
+# saving ~219MB in the image.
+RUN mkdir -p /ragflow/rag/res/deepdoc /root/.ragflow
+RUN --mount=type=bind,from=infiniflow/ragflow_deps:latest,source=/huggingface.co,target=/huggingface.co \
+    tar --exclude='.*' \
+        --exclude='layout.laws.onnx' \
+        --exclude='layout.manual.onnx' \
+        --exclude='layout.paper.onnx' \
+        -cf - \
+        /huggingface.co/InfiniFlow/text_concat_xgb_v1.0 \
+        /huggingface.co/InfiniFlow/deepdoc \
+        | tar -xf - --strip-components=3 -C /ragflow/rag/res/deepdoc && \
+    ln -s layout.onnx /ragflow/rag/res/deepdoc/layout.laws.onnx && \
+    ln -s layout.onnx /ragflow/rag/res/deepdoc/layout.manual.onnx && \
+    ln -s layout.onnx /ragflow/rag/res/deepdoc/layout.paper.onnx
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Setup apt
+RUN --mount=type=cache,id=ragflow_apt,target=/var/cache/apt,sharing=locked \
+    if [ "$NEED_MIRROR" == "1" ]; then \
+        # CI runners may inject a proxy whose TLS certificate is not trusted inside
+        # the fresh Ubuntu base image yet. Keep the Ubuntu mirror on HTTP here so
+        # the mirror switch remains usable before the full CA store is available.
+        sed -i 's|http://archive.ubuntu.com/ubuntu|http://mirrors.aliyun.com/ubuntu|g' /etc/apt/sources.list.d/ubuntu.sources; \
+        sed -i 's|http://security.ubuntu.com/ubuntu|http://mirrors.aliyun.com/ubuntu|g' /etc/apt/sources.list.d/ubuntu.sources; \
+    fi; \
+    rm -f /etc/apt/apt.conf.d/docker-clean && \
+    echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache && \
+    chmod 1777 /tmp && \
+    apt update && \
+    #apt --no-install-recommends install -y ca-certificates \
+    #libglib2.0-0 libglx-mesa0 libgl1 pkg-config libgdiplus default-jdk libatk-bridge2.0-0 \
+    #libgtk-4-1 libnss3 xdg-utils libjemalloc-dev gnupg unzip curl wget git vim less \
+    #ghostscript pandoc texlive texlive-latex-extra texlive-xetex texlive-lang-chinese \
+    #fonts-freefont-ttf fonts-noto-cjk postgresql-client
+
+    apt --no-install-recommends install -y ca-certificates libjemalloc2 curl vim unzip iproute2 && \
+    rm -rf /var/lib/apt/lists/*
+
+# Download resource from GitHub to /usr/share/infinity
+# Ship only the directories required by the runtime tokenizer:
+#   rag     - base analyzer dictionaries (mandatory)
+#   opencc  - Traditional/Simplified Chinese conversion
+#   wordnet - WordNet resources
+RUN --mount=type=cache,id=ragflow_apt,target=/var/cache/apt,sharing=locked \
+    apt-get update && \
+    apt-get install -y --no-install-recommends git && \
+    mkdir -p /usr/share/infinity/resource && \
+    if [ "$NEED_MIRROR" == "1" ]; then \
+        if [ -n "$GITEE_TOKEN" ]; then \
+            git clone --depth 1 --single-branch "https://oauth2:${GITEE_TOKEN}@gitee.com/infiniflow/resource" /tmp/resource; \
+        else \
+            git clone --depth 1 --single-branch https://github.com/infiniflow/resource.git /tmp/resource; \
+        fi; \
+    else \
+        git clone --depth 1 --single-branch https://github.com/infiniflow/resource.git /tmp/resource; \
+    fi && \
+    for d in rag opencc wordnet; do \
+        cp -r "/tmp/resource/$d" /usr/share/infinity/resource/; \
+    done && \
+    rm -rf /tmp/resource && \
+    apt-get purge -y git && \
+    apt-get autoremove -y && \
+    rm -rf /var/lib/apt/lists/*
+
+ARG NGINX_VERSION=1.31.3-1~noble
+RUN --mount=type=cache,id=ragflow_apt,target=/var/cache/apt,sharing=locked \
+    apt -o Acquire::Retries=5 update && \
+    apt -o Acquire::Retries=5 install -y --no-install-recommends gnupg && \
+    mkdir -p /etc/apt/keyrings && \
+    curl --retry 5 --retry-delay 2 --retry-all-errors -fsSL https://nginx.org/keys/nginx_signing.key | gpg --dearmor -o /etc/apt/keyrings/nginx-archive-keyring.gpg && \
+    echo "deb [signed-by=/etc/apt/keyrings/nginx-archive-keyring.gpg] https://nginx.org/packages/mainline/ubuntu/ noble nginx" > /etc/apt/sources.list.d/nginx.list && \
+    apt -o Acquire::Retries=5 update && \
+    apt -o Acquire::Retries=5 install -y --no-install-recommends nginx=${NGINX_VERSION} && \
+    apt-mark hold nginx && \
+    apt-get purge -y gnupg && \
+    apt-get autoremove -y && \
+    rm -rf /var/lib/apt/lists/*
+
+#ENV PATH=/root/.local/bin:$PATH
+
+# NOTE: Node.js is intentionally NOT installed in `base`. The pure-Go backend
+# serves the prebuilt static frontend via nginx and needs no Node runtime at
+# runtime. Node.js is only required to *build* the frontend, so it lives
+# exclusively in the `web-builder` stage and never reaches the final image.
+
+
+
+# ── cpp-builder stage ──────────────────────────────────────────────
+# Compile C++ static library (librag_tokenizer_c_api.a) using the
+# infinity_builder image which ships clang-20, cmake and other C++
+# tooling.  This stage is independent from the base image so that the
+# heavy C++ build toolchain does not bloat the final production image.
+FROM infiniflow/infinity_builder:ubuntu22_clang20 AS cpp-builder
+USER root
+SHELL ["/bin/bash", "-c"]
+
+ARG NEED_MIRROR=1
+WORKDIR /ragflow
+
+COPY internal/binding/cpp internal/binding/cpp
+COPY build.sh ./
+
+RUN git config --global safe.directory "*" && \
+    cd /ragflow && ./build.sh --cpp
+
+# ── go-builder stage ──
+FROM infiniflow/github_action_runner:latest AS go-builder
+USER root
+SHELL ["/bin/bash", "-c"]
+WORKDIR /ragflow
+
+COPY internal internal
+COPY cmd cmd
+COPY go.mod go.sum ./
+COPY build.sh ./
+
+# Overwrite C++ build artifact from cpp-builder
+COPY --from=cpp-builder \
+     /ragflow/internal/binding/cpp/cmake-build-release/librag_tokenizer_c_api.a \
+     /ragflow/internal/binding/cpp/cmake-build-release/librag_tokenizer_c_api.a
+
+RUN git config --global safe.directory "*" && \
+    ./build.sh -s --go
+
+
+# ── web-builder stage ──
+# Builds the static frontend. Node.js is installed HERE only, so the runtime
+# image (production, which extends `base`) never contains Node.js.
+FROM base AS web-builder
+USER root
+
+WORKDIR /ragflow
+
+# Install Node.js 22.x (Ubuntu 24.04's Node.js is too old)
+RUN --mount=type=cache,id=ragflow_apt,target=/var/cache/apt,sharing=locked \
+    curl -fsSL https://deb.nodesource.com/setup_22.x | bash - && \
+    apt-get purge -y nodejs npm && \
+    apt-get autoremove -y && \
+    apt-get update && \
+    apt-get install -y nodejs
+
+# Install frontend dependencies — depends only on package manifests so
+# web source / docs changes don't invalidate this layer.
+COPY web/package.json web/package-lock.json web/.npmrc ./web/
+RUN --mount=type=cache,id=ragflow_npm,target=/root/.npm,sharing=locked \
+    cd web && NODE_OPTIONS="--max-old-space-size=8192" npm install
+
+# Copy full web source and docs for the frontend build.
+COPY web web
+COPY docs docs
+RUN --mount=type=cache,id=ragflow_npm,target=/root/.npm,sharing=locked \
+    cd web && NODE_OPTIONS="--max-old-space-size=8192" VITE_BUILD_SOURCEMAP=false VITE_MINIFY=esbuild npm run build
+
+RUN --mount=type=bind,source=.git,target=/ragflow/.git \
+    --mount=type=cache,id=ragflow_apt,target=/var/cache/apt,sharing=locked \
+    apt-get update && \
+    apt-get install -y --no-install-recommends git && \
+    version_info=$(git describe --tags --match=v* --first-parent --always) && \
+    echo "$version_info" > /ragflow/VERSION && \
+    apt-get purge -y git && \
+    apt-get autoremove -y && \
+    rm -rf /var/lib/apt/lists/*
+
+# production stage
+FROM base AS production
+USER root
+
+WORKDIR /ragflow
+
+# Copy the compiled Go backend binaries (set exec bits at copy time to avoid a redundant chmod layer)
+COPY --from=go-builder --chmod=755 /ragflow/bin/ /ragflow/bin/
+
+ENV PYTHONPATH=/ragflow/
+
+COPY docker/service_conf.yaml.template ./conf/service_conf.yaml.template
+COPY docker/entrypoint*.sh ./
+RUN chmod +x ./entrypoint*.sh
+
+# Copy nginx configuration for frontend serving
+RUN mkdir -p /etc/nginx/conf.d /var/log/nginx
+
+COPY docker/nginx/nginx.conf docker/nginx/proxy.conf /etc/nginx/
+COPY docker/nginx/ragflow.conf.golang \
+#     docker/nginx/ragflow.conf.python \
+      docker/nginx/ragflow.conf.hybrid \
+     /etc/nginx/conf.d/
+
+RUN rm -f /etc/nginx/sites-enabled/default
+
+
+COPY conf conf
+COPY agent/templates agent/templates
+
+
+# Copy compiled web pages
+COPY --from=web-builder /ragflow/web/dist /ragflow/web/dist
+
+# Copy version info
+COPY --from=web-builder /ragflow/VERSION /ragflow/VERSION
+
+# Set environment variables
+ENV HF_ENDPOINT=https://hf-mirror.com
+
+ENTRYPOINT ["./entrypoint-go.sh"]

docker/.env-go

@@ -0,0 +1,405 @@
+# -----------------------------------------------------------------------------
+# SECURITY WARNING: DO NOT DEPLOY WITH DEFAULT PASSWORDS
+# For non-local deployments, please change all passwords (ELASTIC_PASSWORD,
+# MYSQL_PASSWORD, MINIO_PASSWORD, etc.) to strong, unique values.
+# You can generate a random string using: openssl rand -hex 32
+# -----------------------------------------------------------------------------
+
+# ------------------------------
+# docker env var for specifying vector db type at startup
+# (based on the vector db type, the corresponding docker
+# compose profile will be used)
+# ------------------------------
+# The type of doc engine to use.
+# Available options:
+# - `elasticsearch` (default)
+# - `infinity` (https://github.com/infiniflow/infinity)
+# - `oceanbase` (https://github.com/oceanbase/oceanbase)
+# - `opensearch` (https://github.com/opensearch-project/OpenSearch)
+# - `seekdb` (https://github.com/oceanbase/seekdb)
+# - `gaussdb` GaussDB Centralized / Distributed DocEngine
+DOC_ENGINE=${DOC_ENGINE:-elasticsearch}
+
+# The business metadata database type used by DB_TYPE.
+# Available options: mysql (default), postgres, gaussdb, oceanbase.
+DB_TYPE=${DB_TYPE:-mysql}
+
+# Device on which deepdoc inference run.
+# Available levels:
+# - `cpu` (default)
+# - `gpu`
+DEVICE=${DEVICE:-cpu}
+
+# This controls only the bundled metadata service started by Compose; DB_TYPE
+# independently selects the metadata backend used by RAGFlow. Keep `mysql` to
+# start the in-cluster MySQL service. For external GaussDB, set both
+# DB_TYPE=gaussdb and METADATA_DB_PROFILE=gaussdb so MySQL stays disabled.
+METADATA_DB_PROFILE=${METADATA_DB_PROFILE:-mysql}
+COMPOSE_PROFILES=${DOC_ENGINE},${DEVICE},metadata-${METADATA_DB_PROFILE}
+
+# The version of Elasticsearch.
+STACK_VERSION=${STACK_VERSION:-8.11.3}
+
+# The hostname where the Elasticsearch service is exposed
+ES_HOST=es01
+
+# The port used to expose the Elasticsearch service to the host machine,
+# allowing EXTERNAL access to the service running inside the Docker container.
+ES_PORT=1200
+
+# The password for Elasticsearch.
+# WARNING: Change this for production!
+ELASTIC_PASSWORD=infini_rag_flow
+
+# the hostname where OpenSearch service is exposed, set it not the same as elasticsearch
+OS_PORT=1201
+
+# The hostname where the OpenSearch service is exposed
+OS_HOST=opensearch01
+
+# The password for OpenSearch.
+# At least one uppercase letter, one lowercase letter, one digit, and one special character
+OPENSEARCH_PASSWORD=infini_rag_flow_OS_01
+
+# The port used to expose the Kibana service to the host machine,
+# allowing EXTERNAL access to the service running inside the Docker container.
+# To enable kibana, you need to:
+# 1. Ensure that COMPOSE_PROFILES includes kibana, for example: COMPOSE_PROFILES=${COMPOSE_PROFILES},kibana
+# 2. Comment out or delete the following configurations of the es service in docker-compose-base.yml: xpack.security.enabled、xpack.security.http.ssl.enabled、xpack.security.transport.ssl.enabled (for details: https://www.elastic.co/docs/deploy-manage/security/self-auto-setup#stack-existing-settings-detected)
+# 3. Adjust the es.hosts in conf/service_config.yaml or docker/service_conf.yaml.template to 'https://localhost:1200'
+# 4. After the startup is successful, in the es container, execute the command to generate the kibana token: `bin/elasticsearch-create-enrollment-token -s kibana`, then you can use kibana normally
+KIBANA_PORT=6601
+
+# The maximum amount of the memory, in bytes, that a specific Docker container can use while running.
+# Update it according to the available memory in the host machine.
+MEM_LIMIT=8073741824
+
+# The hostname where the Infinity service is exposed
+INFINITY_HOST=infinity
+
+# Port to expose Infinity API to the host
+INFINITY_THRIFT_PORT=23817
+INFINITY_HTTP_PORT=23820
+INFINITY_PSQL_PORT=5432
+
+# The hostname where the SereneDB service is exposed. SereneDB speaks the
+# PostgreSQL wire protocol, so DOC_ENGINE=serenedb connects over lib/pq/psycopg2.
+SERENEDB_HOST=serenedb
+# Port to expose SereneDB to the host
+SERENEDB_PORT=7890
+# The password for SereneDB (POSTGRES_PASSWORD in the container)
+SERENEDB_PASSWORD=infini_rag_flow
+
+# The hostname where the OceanBase service is exposed
+OCEANBASE_HOST=oceanbase
+# The port used to expose the OceanBase service
+OCEANBASE_PORT=2881
+# The username for OceanBase
+OCEANBASE_USER=root@ragflow
+# The password for OceanBase
+OCEANBASE_PASSWORD=infini_rag_flow
+# The doc database of the OceanBase service to use
+OCEANBASE_DOC_DBNAME=ragflow_doc
+
+# GaussDB DocEngine connection. RAGFlow does not start or manage GaussDB;
+# configure an existing GaussDB instance here.
+# GaussDB host.
+GAUSSDB_HOST=
+# GaussDB port.
+GAUSSDB_PORT=
+# GaussDB database name.
+GAUSSDB_DATABASE=postgres
+# GaussDB login user.
+GAUSSDB_USER=
+# GaussDB login password.
+GAUSSDB_PASSWORD=
+# GaussDB schema for RAGFlow DocEngine objects.
+GAUSSDB_SCHEMA=
+
+# OceanBase container configuration
+OB_CLUSTER_NAME=${OB_CLUSTER_NAME:-ragflow}
+OB_TENANT_NAME=${OB_TENANT_NAME:-ragflow}
+OB_SYS_PASSWORD=${OCEANBASE_PASSWORD:-infini_rag_flow}
+OB_TENANT_PASSWORD=${OCEANBASE_PASSWORD:-infini_rag_flow}
+OB_MEMORY_LIMIT=${OB_MEMORY_LIMIT:-10G}
+OB_SYSTEM_MEMORY=${OB_SYSTEM_MEMORY:-2G}
+OB_DATAFILE_SIZE=${OB_DATAFILE_SIZE:-20G}
+OB_LOG_DISK_SIZE=${OB_LOG_DISK_SIZE:-20G}
+
+# The hostname where the SeekDB service is exposed
+SEEKDB_HOST=seekdb
+# The port used to expose the SeekDB service
+SEEKDB_PORT=2881
+# The username for SeekDB
+SEEKDB_USER=root
+# The password for SeekDB
+SEEKDB_PASSWORD=infini_rag_flow
+# The doc database of the SeekDB service to use
+SEEKDB_DOC_DBNAME=ragflow_doc
+# SeekDB memory limit
+SEEKDB_MEMORY_LIMIT=2G
+
+# The password for MySQL.
+# WARNING: Change this for production!
+MYSQL_PASSWORD=infini_rag_flow
+# The hostname where the MySQL service is exposed
+MYSQL_HOST=mysql
+# The database of the MySQL service to use
+MYSQL_DBNAME=rag_flow
+# The port used to connect to MySQL from RAGFlow container.
+# Change this if you use external MySQL.
+MYSQL_PORT=3306
+# The port used to expose the MySQL service to the host machine,
+# allowing EXTERNAL access to the MySQL database running inside the Docker container.
+EXPOSE_MYSQL_PORT=3306
+# The maximum size of communication packets sent to the MySQL server
+MYSQL_MAX_PACKET=1073741824
+
+# External GaussDB metadata database settings, used when DB_TYPE=gaussdb.
+# These are intentionally separate from the GAUSSDB_* DocEngine settings.
+GAUSSDB_METADATA_HOST=
+GAUSSDB_METADATA_PORT=
+GAUSSDB_METADATA_USER=
+GAUSSDB_METADATA_PASSWORD=
+GAUSSDB_METADATA_DBNAME=rag_flow
+GAUSSDB_METADATA_SCHEMA=public
+GAUSSDB_METADATA_MAX_CONNECTIONS=100
+GAUSSDB_METADATA_STALE_TIMEOUT=30
+
+# The hostname where the MinIO service is exposed
+MINIO_HOST=minio
+# The port used to expose the MinIO console interface to the host machine,
+# allowing EXTERNAL access to the web-based console running inside the Docker container.
+MINIO_CONSOLE_PORT=9001
+# The port used to expose the MinIO API service to the host machine,
+# allowing EXTERNAL access to the MinIO object storage service running inside the Docker container.
+MINIO_PORT=9000
+# The username for MinIO.
+# When updated, you must revise the `minio.user` entry in service_conf.yaml accordingly.
+MINIO_USER=rag_flow
+# The password for MinIO.
+# When updated, you must revise the `minio.password` entry in service_conf.yaml accordingly.
+MINIO_PASSWORD=infini_rag_flow
+
+# The hostname where the Redis service is exposed
+REDIS_HOST=redis
+# The port used to expose the Redis service to the host machine,
+# allowing EXTERNAL access to the Redis service running inside the Docker container.
+REDIS_PORT=6379
+# The password for Redis.
+REDIS_PASSWORD=infini_rag_flow
+
+NATS_HOST=nats
+# Port used by RAGFlow's Go services to connect to NATS inside the container network.
+# Do NOT change this unless you also change `nats.port` in conf/service_conf.yaml.template.
+NATS_PORT=4222
+# Host-side port that maps to the NATS container port 4222. Change this to avoid
+# clashing with a port already used on the host machine. This ONLY affects the
+# published host port and is never read by RAGFlow's internal services.
+EXPOSE_NATS_PORT=4222
+
+# The hostname where the ClickHouse service is exposed
+CLICKHOUSE_HOST=clickhouse
+# Native TCP port used by RAGFlow's Go services to connect to ClickHouse inside
+# the container network. Do NOT change this unless you also change `clickhouse.port`
+# in conf/service_conf.yaml.template.
+CLICKHOUSE_TCP_PORT=9000
+# Host-side port that maps to the ClickHouse container native TCP port 9000. Change
+# this to avoid clashing with a port already used on the host machine. This ONLY
+# affects the published host port and is never read by RAGFlow's internal services.
+EXPOSE_CLICKHOUSE_TCP_PORT=9900
+# The port used to expose the ClickHouse HTTP service
+CLICKHOUSE_HTTP_PORT=8123
+# The username for ClickHouse
+CLICKHOUSE_USER=ragflow
+# The password for ClickHouse
+CLICKHOUSE_PASSWORD=infini_rag_flow
+# The database for ClickHouse
+CLICKHOUSE_DATABASE=ragflow
+
+# Jaeger (distributed tracing)
+# Enable by adding `jaeger` to COMPOSE_PROFILES, e.g.:
+# COMPOSE_PROFILES=${COMPOSE_PROFILES},jaeger
+# Then update otel.host in service_conf.yaml to "jaeger".
+JAEGER_VERSION=2.19.0
+JAEGER_OTLP_GRPC_PORT=4317
+JAEGER_OTLP_HTTP_PORT=4318
+JAEGER_UI_PORT=16686
+
+# The port used to expose RAGFlow's HTTP API service to the host machine,
+# allowing EXTERNAL access to the service running inside the Docker container.
+SVR_WEB_HTTP_PORT=80
+SVR_WEB_HTTPS_PORT=443
+SVR_HTTP_PORT=9380
+ADMIN_SVR_HTTP_PORT=9381
+SVR_MCP_PORT=9382
+GO_HTTP_PORT=9384
+GO_ADMIN_PORT=9383
+
+# API_PROXY_SCHEME=hybrid # go and python hybrid deploy mode
+API_PROXY_SCHEME=go # use go server deployment
+#API_PROXY_SCHEME=python # use pure python server deployment
+
+# Development-only: set to 1 to bypass host safety checks for test_db_connection and allow private/local database hosts.
+# Do not enable in production.
+ALLOW_ANY_HOST=0
+
+# The RAGFlow Docker image to download. v0.22+ doesn't include embedding models.
+RAGFLOW_IMAGE=infiniflow/ragflow:go-test-1
+
+# If you cannot download the RAGFlow Docker image:
+# RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:v0.27.0
+# RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:v0.27.0
+#
+# - For the `nightly` edition, uncomment either of the following:
+# RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:nightly
+# RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:nightly
+
+# The embedding service image, model and port.
+# Important: To enable the embedding service, you need to uncomment one of the following two lines:
+# COMPOSE_PROFILES=${COMPOSE_PROFILES},tei-cpu
+# COMPOSE_PROFILES=${COMPOSE_PROFILES},tei-gpu
+
+# The embedding service image:
+TEI_IMAGE_CPU=infiniflow/text-embeddings-inference:cpu-1.8
+TEI_IMAGE_GPU=infiniflow/text-embeddings-inference:1.8
+
+# The embedding service model:
+# Available options:
+# - `Qwen/Qwen3-Embedding-0.6B` (default, requires 25GB RAM/vRAM to load)
+# - `BAAI/bge-m3` (requires 21GB RAM/vRAM to load)
+# - `BAAI/bge-small-en-v1.5` (requires 1.2GB RAM/vRAM to load)
+TEI_MODEL=${TEI_MODEL:-Qwen/Qwen3-Embedding-0.6B}
+
+# The embedding service port:
+TEI_HOST=tei
+# The port used to expose the TEI service to the host machine,
+# allowing EXTERNAL access to the service running inside the Docker container.
+TEI_PORT=6380
+
+# The local time zone.
+TZ=Asia/Shanghai
+
+# Uncomment the following line if you have limited access to huggingface.co:
+# HF_ENDPOINT=https://hf-mirror.com
+
+# Optimizations for MacOS
+# Uncomment the following line if your operating system is MacOS:
+# MACOS=1
+
+# The maximum file size limit (in bytes) for each upload to your dataset or RAGFlow's File system.
+# To change the 1GB file size limit, uncomment the line below and update as needed.
+# MAX_CONTENT_LENGTH=1073741824
+# After updating, ensure `client_max_body_size` in nginx/nginx.conf is updated accordingly.
+# Note that neither `MAX_CONTENT_LENGTH` nor `client_max_body_size` sets the maximum size for files uploaded to an agent.
+# See https://ragflow.io/docs/dev/begin_component for details.
+
+# Controls how many documents are processed in a single batch.
+# Defaults to 4 if DOC_BULK_SIZE is not explicitly set.
+DOC_BULK_SIZE=${DOC_BULK_SIZE:-4}
+
+# Defines the number of items to process per batch when generating embeddings.
+# Defaults to 16 if EMBEDDING_BATCH_SIZE is not set in the environment.
+EMBEDDING_BATCH_SIZE=${EMBEDDING_BATCH_SIZE:-16}
+
+# Log level for the RAGFlow's own and imported packages.
+# Available levels:
+# - `DEBUG`
+# - `INFO` (default)
+# - `WARNING`
+# - `ERROR`
+# For example, the following line changes the log level of `ragflow.es_conn` to `DEBUG`:
+# LOG_LEVELS=ragflow.es_conn=DEBUG
+
+# aliyun OSS configuration
+# STORAGE_IMPL=OSS
+# ACCESS_KEY=xxx
+# SECRET_KEY=eee
+# ENDPOINT=http://oss-cn-hangzhou.aliyuncs.com
+# REGION=cn-hangzhou
+# BUCKET=ragflow65536
+#
+
+# A user registration switch:
+# - Enable registration: 1
+# - Disable registration: 0
+REGISTER_ENABLED=1
+ENABLE_REGISTER=1
+
+# -----------------------------------------------------------------------------
+# Sandbox
+# -----------------------------------------------------------------------------
+# Sandbox provider type and runtime settings are configured in Admin > Sandbox
+# Settings.
+
+# Enable sandbox support.
+# SANDBOX_ENABLED=1
+# COMPOSE_PROFILES=${COMPOSE_PROFILES},sandbox
+
+# Shared sandbox settings
+# The MinIO bucket name for storing sandbox-generated artifacts.
+# SANDBOX_ARTIFACT_BUCKET=sandbox-artifacts
+
+# Number of days before sandbox artifacts are automatically deleted.
+# SANDBOX_ARTIFACT_EXPIRE_DAYS=7
+
+# Self-managed deployment defaults
+# These values are used by the `sandbox` compose profile and shown in Admin as
+# deployment defaults for the self-managed provider.
+# Pull the required base images before running:
+#   docker pull infiniflow/sandbox-base-nodejs:latest
+#   docker pull infiniflow/sandbox-base-python:latest
+# Default runtime images include:
+# - Node.js base image: axios
+# - Python base image: requests, numpy, pandas
+# SANDBOX_EXECUTOR_MANAGER_IMAGE=${SANDBOX_EXECUTOR_MANAGER_IMAGE:-infiniflow/sandbox-executor-manager:latest}
+# SANDBOX_EXECUTOR_MANAGER_POOL_SIZE=${SANDBOX_EXECUTOR_MANAGER_POOL_SIZE:-3}
+# SANDBOX_BASE_PYTHON_IMAGE=${SANDBOX_BASE_PYTHON_IMAGE:-infiniflow/sandbox-base-python:latest}
+# SANDBOX_BASE_NODEJS_IMAGE=${SANDBOX_BASE_NODEJS_IMAGE:-infiniflow/sandbox-base-nodejs:latest}
+# SANDBOX_EXECUTOR_MANAGER_PORT=${SANDBOX_EXECUTOR_MANAGER_PORT:-9385}
+# SANDBOX_ENABLE_SECCOMP=false
+# SANDBOX_MAX_MEMORY=256m # b, k, m, g
+# SANDBOX_TIMEOUT=10s # s, m, 1m30s
+
+# -----------------------------------------------------------------------------
+# Sandbox End
+# -----------------------------------------------------------------------------
+
+# Enable DocLing
+USE_DOCLING=false
+
+# Enable Mineru
+# Uncommenting these lines will automatically add MinerU to the model provider whenever possible.
+# More details see https://ragflow.io/docs/faq#how-to-use-mineru-to-parse-pdf-documents.
+# MINERU_DELETE_OUTPUT=0   # keep output directory
+# MINERU_BACKEND=pipeline  # or another backend you prefer
+
+# pptx support
+DOTNET_SYSTEM_GLOBALIZATION_INVARIANT=1
+
+# crypto utils
+# RAGFLOW_CRYPTO_ENABLED=true
+# RAGFLOW_CRYPTO_ALGORITHM=aes-256-cbc # one of aes-256-cbc, aes-128-cbc, sm4-cbc
+# RAGFLOW_CRYPTO_KEY=ragflow-crypto-key
+
+
+# Used for ThreadPoolExecutor
+THREAD_POOL_MAX_WORKERS=128
+
+#Option to disable login form for SSO
+DISABLE_PASSWORD_LOGIN=false
+
+# -----------------------------------------------------------------------------
+# DeepDoc OSS Vision Service
+# -----------------------------------------------------------------------------
+# URL for the deepdoc vision API (DLA, OCR, TSR) served by OSS ONNX models.
+# The `deepdoc` service defined in docker-compose.yml provides this endpoint.
+# When unset, the parser falls back to inline ONNX Runtime inference.
+
+# Comment existing COMPOSE_PROFILES and uncomment below if need deepdoc service.
+# COMPOSE_PROFILES=${DOC_ENGINE},${DEVICE},deepdoc
+
+# DEEPDOC_URL=http://deepdoc:9390
+
+# Docker image for the OSS deepdoc service.  CPU-only; uses ONNX Runtime.
+# DEEPDOC_IMAGE=deepdoc_oss:latest

docker/docker-compose-go.yml

@@ -0,0 +1,167 @@
+include:
+  - ./docker-compose-base.yml
+# To ensure that the container processes the locally modified `service_conf.yaml.template` instead of the one included in its image, you need to mount the local `service_conf.yaml.template` to the container.
+services:
+  deepdoc:
+    image: ${DEEPDOC_IMAGE:-deepdoc_oss:latest}
+    profiles:
+      - deepdoc
+    build:
+      context: ..
+      dockerfile: Dockerfile_deepdoc_oss
+    networks:
+      - ragflow
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:9390/health"]
+      interval: 10s
+      timeout: 10s
+      retries: 60
+
+  ragflow-cpu:
+    depends_on:
+      mysql:
+        condition: service_healthy
+        required: false
+    profiles:
+      - cpu
+    image: ${RAGFLOW_IMAGE}
+    ulimits:
+      nofile:
+        soft: 65535
+        hard: 65535
+      nproc:
+        soft: 65535
+        hard: 65535
+    # Example configuration to set up an MCP server:
+    # command:
+    #   - --enable-mcpserver
+    #   - --mcp-host=0.0.0.0
+    #   - --mcp-port=9382
+    #   - --mcp-base-url=http://127.0.0.1:9380
+    #   - --mcp-script-path=/ragflow/mcp/server/server.py
+    #   - --mcp-mode=self-host
+    #   - --mcp-host-api-key=ragflow-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
+    # Optional transport flags for MCP (customize if needed).
+    # Host mode need to combined with --no-transport-streamable-http-enabled flag, namely, host+streamable-http is not supported yet.
+    # The following are enabled by default unless explicitly disabled with --no-<flag>.
+    #   - --no-transport-sse-enabled # Disable legacy SSE endpoints (/sse and /messages/)
+    #   - --no-transport-streamable-http-enabled #  Disable Streamable HTTP transport (/mcp endpoint)
+    #   - --no-json-response # Disable JSON response mode in Streamable HTTP transport (instead of SSE over HTTP)
+
+    # Example configuration to start Admin server:
+    command:
+      - --enable-adminserver
+      #- --init-model-provider-tables
+    ports:
+      - ${SVR_WEB_HTTP_PORT}:80
+      - ${SVR_WEB_HTTPS_PORT}:443
+      - ${SVR_HTTP_PORT}:9380
+      - ${ADMIN_SVR_HTTP_PORT}:9381
+      - ${SVR_MCP_PORT}:9382 # entry for MCP (host_port:docker_port). The docker_port must match the value you set for `mcp-port` above.
+      - ${GO_HTTP_PORT}:9384
+      - ${GO_ADMIN_PORT}:9383
+    volumes:
+      - ./ragflow-logs:/ragflow/logs
+      # - ./nginx/ragflow.conf:/etc/nginx/conf.d/ragflow.conf
+      # - ./nginx/proxy.conf:/etc/nginx/proxy.conf
+      # - ./nginx/nginx.conf:/etc/nginx/nginx.conf
+      - ./service_conf.yaml.template:/ragflow/conf/service_conf.yaml.template
+      - ./entrypoint-go.sh:/ragflow/entrypoint.sh
+    env_file: .env-go
+    networks:
+      - ragflow
+    restart: unless-stopped
+    # https://docs.docker.com/engine/daemon/prometheus/#create-a-prometheus-configuration
+    # If you use Docker Desktop, the --add-host flag is optional. This flag ensures that the host's internal IP is exposed to the Prometheus container.
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+
+  ragflow-gpu:
+    depends_on:
+      mysql:
+        condition: service_healthy
+        required: false
+    profiles:
+      - gpu
+    image: ${RAGFLOW_IMAGE}
+    ulimits:
+      nofile:
+        soft: 65535
+        hard: 65535
+      nproc:
+        soft: 65535
+        hard: 65535
+    # Example configuration to set up an MCP server:
+    # command:
+    #   - --enable-mcpserver
+    #   - --mcp-host=0.0.0.0
+    #   - --mcp-port=9382
+    #   - --mcp-base-url=http://127.0.0.1:9380
+    #   - --mcp-script-path=/ragflow/mcp/server/server.py
+    #   - --mcp-mode=self-host
+    #   - --mcp-host-api-key=ragflow-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
+    # Optional transport flags for MCP (customize if needed).
+    # Host mode need to combined with --no-transport-streamable-http-enabled flag, namely, host+streamable-http is not supported yet.
+    # The following are enabled by default unless explicitly disabled with --no-<flag>.
+    #   - --no-transport-sse-enabled # Disable legacy SSE endpoints (/sse and /messages/)
+    #   - --no-transport-streamable-http-enabled #  Disable Streamable HTTP transport (/mcp endpoint)
+    #   - --no-json-response # Disable JSON response mode in Streamable HTTP transport (instead of SSE over HTTP)
+
+    # Example configuration to start Admin server:
+    command:
+      - --enable-adminserver
+    ports:
+      - ${SVR_WEB_HTTP_PORT}:80
+      - ${SVR_WEB_HTTPS_PORT}:443
+      - ${SVR_HTTP_PORT}:9380
+      - ${ADMIN_SVR_HTTP_PORT}:9381
+      - ${SVR_MCP_PORT}:9382 # entry for MCP (host_port:docker_port). The docker_port must match the value you set for `mcp-port` above.
+    volumes:
+      - ./ragflow-logs:/ragflow/logs
+      # - ./nginx/ragflow.conf:/etc/nginx/conf.d/ragflow.conf
+      # - ./nginx/proxy.conf:/etc/nginx/proxy.conf
+      # - ./nginx/nginx.conf:/etc/nginx/nginx.conf
+      - ./service_conf.yaml.template:/ragflow/conf/service_conf.yaml.template
+      - ./entrypoint.sh:/ragflow/entrypoint.sh
+    env_file: .env-go
+    networks:
+      - ragflow
+    restart: unless-stopped
+    # https://docs.docker.com/engine/daemon/prometheus/#create-a-prometheus-configuration
+    # If you use Docker Desktop, the --add-host flag is optional. This flag ensures that the host's internal IP is exposed to the Prometheus container.
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+
+
+  # executor:
+  #   depends_on:
+  #     mysql:
+  #       condition: service_healthy
+  #   image: ${RAGFLOW_IMAGE}
+  #   volumes:
+  #     - ./ragflow-logs:/ragflow/logs
+  #     - ./nginx/ragflow.conf:/etc/nginx/conf.d/ragflow.conf
+  #   env_file: .env
+  #   entrypoint: "/ragflow/entrypoint_task_executor.sh 1 3"
+  #   networks:
+  #     - ragflow
+  #   restart: unless-stopped
+  #   # https://docs.docker.com/engine/daemon/prometheus/#create-a-prometheus-configuration
+  #   # If you're using Docker Desktop, the --add-host flag is optional. This flag makes sure that the host's internal IP gets exposed to the Prometheus container.
+  #   extra_hosts:
+  #     - "host.docker.internal:host-gateway"
+  #   deploy:
+  #     resources:
+  #       reservations:
+  #         devices:
+  #           - driver: nvidia
+  #             count: all
+  #             capabilities: [gpu]

docker/entrypoint-go.sh

@@ -0,0 +1,366 @@
+#!/usr/bin/env bash
+
+set -e
+
+echo "Start RAGFlow cluster, version: "
+cat /ragflow/VERSION
+
+# -----------------------------------------------------------------------------
+# Usage and command-line argument parsing
+# -----------------------------------------------------------------------------
+function usage() {
+    echo "Usage: $0 [OPTIONS]"
+    echo
+    echo "  --disable-webserver                     Disables the web server (nginx + ragflow_server)."
+    echo "  --disable-taskexecutor                  Disables task executor workers."
+    echo "  --disable-datasync                      Disables synchronization of datasource workers."
+    echo "  --enable-mcpserver                      Enables the MCP server."
+    echo "  --enable-adminserver                    Enables the Admin server."
+    echo "  --init-model-provider-tables            Run model provider table migrations and exit."
+    echo "  --init-superuser                        Initializes the superuser."
+    echo "  --consumer-no-beg=<num>                 Start range for consumers (if using range-based)."
+    echo "  --consumer-no-end=<num>                 End range for consumers (if using range-based)."
+    echo "  --workers=<num>                         Number of task executors to run (if range is not used)."
+    echo "  --host-id=<string>                      Unique ID for the host (defaults to \`hostname\`)."
+    echo "  --mcp-host=<string>                     Address the MCP server binds to (default: 127.0.0.1)."
+    echo "  --mcp-port=<num>                        Port the MCP server listens on (default: 9382)."
+    echo "  --mcp-base-url=<string>                 RAGFlow base URL the MCP server calls (default: http://127.0.0.1:9380)."
+    echo "  --mcp-script-path=<path>                MCP server entry script (default: /ragflow/mcp/server/server.py)."
+    echo "  --mcp-mode=<self-host|host>             MCP server mode (default: self-host)."
+    echo "  --mcp-host-api-key=<string>             API key required when --mcp-mode=self-host."
+    echo "  --no-transport-sse-enabled              Disables the MCP SSE transport."
+    echo "  --no-transport-streamable-http-enabled  Disables the MCP streamable HTTP transport. Disabling"
+    echo "                                          both transports re-enables this one, since the server"
+    echo "                                          requires at least one."
+    echo "  --no-json-response                      Disables JSON responses from the MCP server."
+    echo
+    echo "Examples:"
+    echo "  $0 --disable-taskexecutor"
+    echo "  $0 --disable-webserver --consumer-no-beg=0 --consumer-no-end=5"
+    echo "  $0 --disable-webserver --workers=2 --host-id=myhost123"
+    echo "  $0 --enable-mcpserver"
+    echo "  $0 --enable-adminserver"
+    echo "  $0 --init-superuser"
+    exit 1
+}
+
+ENABLE_WEBSERVER=1 # Default to enable web server
+ENABLE_TASKEXECUTOR=1  # Default to enable task executor
+ENABLE_DATASYNC=1
+ENABLE_MCP_SERVER=0
+ENABLE_ADMIN_SERVER=0 # Default close admin server
+INIT_SUPERUSER_ARGS="" # Default to not initialize superuser
+INIT_MODEL_PROVIDER_TABLES=0
+CONSUMER_NO_BEG=0
+CONSUMER_NO_END=0
+WORKERS=1
+
+MCP_HOST="127.0.0.1"
+MCP_PORT=9382
+MCP_BASE_URL="http://127.0.0.1:9380"
+MCP_SCRIPT_PATH="/ragflow/mcp/server/server.py"
+MCP_MODE="self-host"
+MCP_HOST_API_KEY=""
+MCP_TRANSPORT_SSE_FLAG="--transport-sse-enabled"
+MCP_TRANSPORT_STREAMABLE_HTTP_FLAG="--transport-streamable-http-enabled"
+MCP_JSON_RESPONSE_FLAG="--json-response"
+
+# -----------------------------------------------------------------------------
+# Host ID logic:
+#   1. By default, use the system hostname if length <= 32
+#   2. Otherwise, use the full MD5 hash of the hostname (32 hex chars)
+# -----------------------------------------------------------------------------
+CURRENT_HOSTNAME="$(hostname)"
+if [ ${#CURRENT_HOSTNAME} -le 32 ]; then
+  DEFAULT_HOST_ID="$CURRENT_HOSTNAME"
+else
+  DEFAULT_HOST_ID="$(echo -n "$CURRENT_HOSTNAME" | md5sum | cut -d ' ' -f 1)"
+fi
+
+HOST_ID="$DEFAULT_HOST_ID"
+
+# Parse arguments
+for arg in "$@"; do
+  case $arg in
+    --disable-webserver)
+      ENABLE_WEBSERVER=0
+      shift
+      ;;
+    --disable-taskexecutor)
+      ENABLE_TASKEXECUTOR=0
+      shift
+      ;;
+    --disable-datasync)
+      ENABLE_DATASYNC=0
+      shift
+      ;;
+    --enable-mcpserver)
+      ENABLE_MCP_SERVER=1
+      shift
+      ;;
+    --enable-adminserver)
+      ENABLE_ADMIN_SERVER=1
+      shift
+      ;;
+    --init-model-provider-tables)
+      INIT_MODEL_PROVIDER_TABLES=1
+      shift
+      ;;
+    --init-superuser)
+      INIT_SUPERUSER_ARGS="--init-superuser"
+      shift
+      ;;
+    --mcp-host=*)
+      MCP_HOST="${arg#*=}"
+      shift
+      ;;
+    --mcp-port=*)
+      MCP_PORT="${arg#*=}"
+      shift
+      ;;
+    --mcp-base-url=*)
+      MCP_BASE_URL="${arg#*=}"
+      shift
+      ;;
+    --mcp-mode=*)
+      MCP_MODE="${arg#*=}"
+      shift
+      ;;
+    --mcp-host-api-key=*)
+      MCP_HOST_API_KEY="${arg#*=}"
+      shift
+      ;;
+    --mcp-script-path=*)
+      MCP_SCRIPT_PATH="${arg#*=}"
+      shift
+      ;;
+    --no-transport-sse-enabled)
+      MCP_TRANSPORT_SSE_FLAG="--no-transport-sse-enabled"
+      shift
+      ;;
+    --no-transport-streamable-http-enabled)
+      MCP_TRANSPORT_STREAMABLE_HTTP_FLAG="--no-transport-streamable-http-enabled"
+      shift
+      ;;
+    --no-json-response)
+      MCP_JSON_RESPONSE_FLAG="--no-json-response"
+      shift
+      ;;
+    --consumer-no-beg=*)
+      CONSUMER_NO_BEG="${arg#*=}"
+      shift
+      ;;
+    --consumer-no-end=*)
+      CONSUMER_NO_END="${arg#*=}"
+      shift
+      ;;
+    --workers=*)
+      WORKERS="${arg#*=}"
+      shift
+      ;;
+    --host-id=*)
+      HOST_ID="${arg#*=}"
+      shift
+      ;;
+    *)
+      usage
+      ;;
+  esac
+done
+
+# -----------------------------------------------------------------------------
+# Replace env variables in the service_conf.yaml file
+# -----------------------------------------------------------------------------
+CONF_DIR="/ragflow/conf"
+TEMPLATE_FILE="${CONF_DIR}/service_conf.yaml.template"
+CONF_FILE="${CONF_DIR}/service_conf.yaml"
+
+rm -f "${CONF_FILE}"
+DEF_ENV_VALUE_PATTERN="\$\{([^:]+):-([^}]+)\}"
+while IFS= read -r line || [[ -n "$line" ]]; do
+    if [[ "$line" =~ DEF_ENV_VALUE_PATTERN ]]; then
+        varname="${BASH_REMATCH[1]}"
+        default="${BASH_REMATCH[2]}"
+
+        if [ -n "${!varname}" ]; then
+            eval "echo \"$line"\" >> "${CONF_FILE}"
+        else
+            echo "$line" | sed -E "s/\\\$\{[^:]+:-([^}]+)\}/\1/g" >> "${CONF_FILE}"
+        fi
+    else
+        eval "echo \"$line\"" >> "${CONF_FILE}"
+    fi
+done < "${TEMPLATE_FILE}"
+
+export LD_LIBRARY_PATH="/usr/lib/x86_64-linux-gnu/"
+PY=python3
+
+# -----------------------------------------------------------------------------
+# Select Nginx Configuration based on API_PROXY_SCHEME
+# -----------------------------------------------------------------------------
+NGINX_CONF_DIR="/etc/nginx/conf.d"
+if [ -n "$API_PROXY_SCHEME" ]; then
+    if [[ "${API_PROXY_SCHEME}" == "hybrid" ]]; then
+        cp -f "$NGINX_CONF_DIR/ragflow.conf.hybrid" "$NGINX_CONF_DIR/ragflow.conf"
+        echo "Applied nginx config: ragflow.conf.hybrid"
+    elif [[ "${API_PROXY_SCHEME}" == "go" ]]; then
+        cp -f "$NGINX_CONF_DIR/ragflow.conf.golang" "$NGINX_CONF_DIR/ragflow.conf"
+        echo "Applied nginx config: ragflow.conf.golang (default)"
+    else
+        cp -f "$NGINX_CONF_DIR/ragflow.conf.python" "$NGINX_CONF_DIR/ragflow.conf"
+        echo "Applied nginx config: ragflow.conf.python"
+    fi
+else
+    # Default to python backend
+    cp -f "$NGINX_CONF_DIR/ragflow.conf.python" "$NGINX_CONF_DIR/ragflow.conf"
+    echo "Default: applied nginx config: ragflow.conf.python"
+fi
+
+# -----------------------------------------------------------------------------
+# Function(s)
+# -----------------------------------------------------------------------------
+
+function task_exe() {
+    local consumer_id="$1"
+    local host_id="$2"
+
+    JEMALLOC_PATH="$(pkg-config --variable=libdir jemalloc)/libjemalloc.so"
+    while true; do
+        LD_PRELOAD="$JEMALLOC_PATH" \
+        "$PY" rag/svr/task_executor.py -i "${host_id}_${consumer_id}" -t "common" &
+        wait;
+        sleep 1;
+    done
+}
+
+function start_mcp_server() {
+    echo "Starting MCP Server on ${MCP_HOST}:${MCP_PORT} with base URL ${MCP_BASE_URL}..."
+    "$PY" "${MCP_SCRIPT_PATH}" \
+        --host="${MCP_HOST}" \
+        --port="${MCP_PORT}" \
+        --base-url="${MCP_BASE_URL}" \
+        --mode="${MCP_MODE}" \
+        --api-key="${MCP_HOST_API_KEY}" \
+        "${MCP_TRANSPORT_SSE_FLAG}" \
+        "${MCP_TRANSPORT_STREAMABLE_HTTP_FLAG}" \
+        "${MCP_JSON_RESPONSE_FLAG}" &
+}
+
+function ensure_docling() {
+    [[ "${USE_DOCLING}" == "true" ]] || { echo "[docling] disabled by USE_DOCLING"; return 0; }
+    DOCLING_PIN="${DOCLING_VERSION:-==2.71.0}"
+    "$PY" -c "import importlib.util,sys; sys.exit(0 if importlib.util.find_spec('docling') else 1)" \
+      || uv pip install -i https://pypi.tuna.tsinghua.edu.cn/simple --extra-index-url https://pypi.org/simple --no-cache-dir "docling${DOCLING_PIN}"
+}
+
+function ensure_db_init() {
+    echo "Initializing database tables..."
+    "$PY" -c "from api.db.db_models import init_database_tables as init_web_db; init_web_db()"
+    echo "Database tables initialized."
+}
+
+# -----------------------------------------------------------------------------
+# Start components based on flags
+# -----------------------------------------------------------------------------
+#ensure_docling
+#ensure_db_init
+
+run_with_restart() {
+  local process_name="$1"
+  shift
+
+  while true; do
+    echo "Attempt to start ${process_name}..."
+    set +e
+    "$@"
+    local exit_code=$?
+    set -e
+    echo "${process_name} exited with code ${exit_code}. Restarting in 1 second..."
+    sleep 1
+  done
+}
+
+if [[ "${INIT_MODEL_PROVIDER_TABLES}" -eq 1 ]]; then
+    DB_TYPE_NORMALIZED="${DB_TYPE:-mysql}"
+    DB_TYPE_NORMALIZED="${DB_TYPE_NORMALIZED,,}"
+    if [[ "${DB_TYPE_NORMALIZED}" == "gaussdb" || "${DB_TYPE_NORMALIZED}" == "gauss" ]]; then
+        # This migration script contains MySQL-only SQL and cannot run against
+        # a GaussDB metadata database.
+        echo "Skipping MySQL-specific model provider table migrations for DB_TYPE=${DB_TYPE:-mysql}."
+    else
+        tools/scripts/run_migrations.sh
+    fi
+fi
+
+if [[ "${ENABLE_ADMIN_SERVER}" -eq 1 ]]; then
+
+    if [[ "${API_PROXY_SCHEME}" == "hybrid" ]] || [[ "${API_PROXY_SCHEME}" == "python" ]]; then
+        echo "Attempt to start Admin python server..."
+        run_with_restart "Admin python server" "$PY" admin/server/admin_server.py &
+    fi
+
+    if [[ "${API_PROXY_SCHEME}" == "hybrid" ]] || [[ "${API_PROXY_SCHEME}" == "go" ]]; then
+        echo "Starting Admin go server..."
+        run_with_restart "Admin go server" bin/ragflow_server --admin &
+    fi
+fi
+
+if [[ "${ENABLE_WEBSERVER}" -eq 1 ]]; then
+    echo "Starting nginx..."
+    /usr/sbin/nginx -c /etc/nginx/nginx.conf
+
+   if [[ "${API_PROXY_SCHEME}" == "hybrid" ]] || [[ "${API_PROXY_SCHEME}" == "python" ]]; then
+        echo "Attempt to start RAGFlow python server..."
+        run_with_restart "RAGFlow python server" "$PY" api/ragflow_server.py ${INIT_SUPERUSER_ARGS} &
+    fi
+
+    if [[ "${API_PROXY_SCHEME}" == "hybrid" ]] || [[ "${API_PROXY_SCHEME}" == "go" ]]; then
+        echo "Starting RAGFlow go server..."
+        run_with_restart "RAGFlow go server" bin/ragflow_server --api &
+    fi
+fi
+
+if [[ "${ENABLE_DATASYNC}" -eq 1 ]]; then
+    echo "Starting data sync..."
+    run_with_restart "RAGFlow go server" bin/ragflow_server --syncer &
+fi
+
+#if [[ "${ENABLE_MCP_SERVER}" -eq 1 ]]; then
+#    start_mcp_server
+#fi
+
+
+if [[ "${ENABLE_TASKEXECUTOR}" -eq 1 ]]; then
+    if [[ "${CONSUMER_NO_END}" -gt "${CONSUMER_NO_BEG}" ]]; then
+        if [[ "${API_PROXY_SCHEME}" == "hybrid" ]] || [[ "${API_PROXY_SCHEME}" == "python" ]]; then
+            echo "Starting python task executors on host '${HOST_ID}' for IDs in [${CONSUMER_NO_BEG}, ${CONSUMER_NO_END})..."
+            for (( i=CONSUMER_NO_BEG; i<CONSUMER_NO_END; i++ ))
+            do
+              task_exe "${i}" "${HOST_ID}" &
+            done
+        fi
+
+        if [[ "${API_PROXY_SCHEME}" == "hybrid" ]] || [[ "${API_PROXY_SCHEME}" == "go" ]]; then
+            echo "Starting go ingestor..."
+            run_with_restart "ingestor" bin/ragflow_server --ingestor &
+        fi
+    else
+        # Otherwise, start a fixed number of workers
+        echo "Starting ${WORKERS} task executor(s) on host '${HOST_ID}'..."
+        for (( i=0; i<WORKERS; i++ ))
+        do
+            if [[ "${API_PROXY_SCHEME}" == "hybrid" ]] || [[ "${API_PROXY_SCHEME}" == "python" ]]; then
+                echo "Starting python task executor..."
+                task_exe "${i}" "${HOST_ID}" &
+                sleep 1;
+            fi
+
+            if [[ "${API_PROXY_SCHEME}" == "hybrid" ]] || [[ "${API_PROXY_SCHEME}" == "go" ]]; then
+                echo "Starting go ingestor..."
+                run_with_restart "ingestor" bin/ragflow_server --ingestor &
+            fi
+        done
+    fi
+fi
+
+wait