Don't release full image (#10654)

### What problem does this PR solve? Introduced gpu profile in .env Added Dockerfile_tei fix datrie Removed LIGHTEN flag ### Type of change - [x] Documentation Update - [x] Refactoring
2025-12-06 15:29:03 +08:00 · 2025-10-23 23:02:27 +08:00
parent 92739ea804
commit 73144e278b
67 changed files with 2792 additions and 3608 deletions
--- a/docker/.env
+++ b/docker/.env
@@ -1,3 +1,8 @@
+# ------------------------------
+# 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)
@@ -5,12 +10,13 @@
 # - `opensearch` (https://github.com/opensearch-project/OpenSearch)
 DOC_ENGINE=${DOC_ENGINE:-elasticsearch}

-# ------------------------------
-# docker env var for specifying vector db type at startup
-# (based on the vector db type, the corresponding docker
-# compose profile will be used)
-# ------------------------------
-COMPOSE_PROFILES=${DOC_ENGINE}
+# Device on which deepdoc inference run.
+# Available levels:
+# - `cpu` (default)
+# - `gpu`
+DEVICE=${DEVICE:-cpu}
+
+COMPOSE_PROFILES=${DOC_ENGINE},${DEVICE}

 # The version of Elasticsearch.
 STACK_VERSION=8.11.3
@@ -38,7 +44,7 @@ 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=${DOC_ENGINE},kibana
+# 1. Ensure that COMPOSE_PROFILES includes kibana, for example: COMPOSE_PROFILES=${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
@@ -96,30 +102,47 @@ REDIS_PASSWORD=infini_rag_flow
 SVR_HTTP_PORT=9380
 ADMIN_SVR_HTTP_PORT=9381

-# The RAGFlow Docker image to download.
+# The RAGFlow Docker image to download. v0.22+ doesn't include embedding models.
 # Defaults to the v0.21.1-slim edition, which is the RAGFlow Docker image without embedding models.
 RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.1-slim
-#
-# To download the RAGFlow Docker image with embedding models, uncomment the following line instead:
 # RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.1
-#
 # The Docker image of the v0.21.1 edition includes built-in embedding models:
 #   - BAAI/bge-large-zh-v1.5
 #   - maidalun1020/bce-embedding-base_v1
 #

 # If you cannot download the RAGFlow Docker image:
-#
-# - For the `nightly-slim` edition, uncomment either of the following:
-# RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:nightly-slim
-# RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:nightly-slim
+# RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:v0.21.1
+# RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:v0.21.1
 #
 # - 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.
-TIMEZONE=Asia/Shanghai
+TZ=Asia/Shanghai

 # Uncomment the following line if you have limited access to huggingface.co:
 # HF_ENDPOINT=https://hf-mirror.com
@@ -165,8 +188,11 @@ EMBEDDING_BATCH_SIZE=${EMBEDDING_BATCH_SIZE:-16}
 # - Disable registration: 0
 REGISTER_ENABLED=1

+# Important: To enable sandbox, you need to uncomment following two lines:
+# SANDBOX_ENABLED=1
+# COMPOSE_PROFILES=${COMPOSE_PROFILES},sandbox
+
 # Sandbox settings
-# Important: To enable sandbox, you must re-declare the compose profiles. See hints at the end of file.
 # Double check if you add `sandbox-executor-manager` to your `/etc/hosts`
 # Pull the required base images before running:
 #   docker pull infiniflow/sandbox-base-nodejs:latest
@@ -175,7 +201,6 @@ REGISTER_ENABLED=1
 #   - Node.js base image: includes axios
 #   - Python base image: includes requests, numpy, and pandas
 # Specify custom executor images below if you're using non-default environments.
-# SANDBOX_ENABLED=1
 # SANDBOX_HOST=sandbox-executor-manager
 # SANDBOX_EXECUTOR_MANAGER_IMAGE=infiniflow/sandbox-executor-manager:latest
 # SANDBOX_EXECUTOR_MANAGER_POOL_SIZE=3
--- a/docker/README.md
+++ b/docker/README.md
@@ -18,7 +18,7 @@
  Sets up environment for RAGFlow's dependencies: Elasticsearch/[Infinity](https://github.com/infiniflow/infinity), MySQL, MinIO, and Redis.

 > [!CAUTION]
-> We do not actively maintain **docker-compose-CN-oc9.yml**, **docker-compose-gpu-CN-oc9.yml**, or **docker-compose-gpu.yml**, so use them at your own risk. However, you are welcome to file a pull request to improve any of them.
+> We do not actively maintain **docker-compose-CN-oc9.yml**, **docker-compose-macos.yml**, so use them at your own risk. However, you are welcome to file a pull request to improve any of them.

 ## 🐬 Docker environment variables

@@ -89,16 +89,13 @@ The [.env](./.env) file contains important environment variables for Docker.
 > [!TIP]  
 > If you cannot download the RAGFlow Docker image, try the following mirrors.  
 > 
-> - For the `nightly-slim` edition:  
->   - `RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:nightly-slim` or,
->   - `RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:nightly-slim`.
 > - For the `nightly` edition:  
 >   - `RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:nightly` or,
 >   - `RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:nightly`.

 ### Timezone

- `TIMEZONE`  
+- `TZ`  
  The local time zone. Defaults to `'Asia/Shanghai'`.

 ### Hugging Face mirror site
--- a/docker/docker-compose-CN-oc9.yml
+++ b/docker/docker-compose-CN-oc9.yml
@@ -4,12 +4,13 @@ include:
  - ./docker-compose-base.yml

 services:
-  ragflow:
+  ragflow-cpu:
    depends_on:
      mysql:
        condition: service_healthy
+    profiles:
+      - cpu
    image: edwardelric233/ragflow:oc9
-    container_name: ragflow-server
    ports:
      - ${SVR_HTTP_PORT}:9380
      - 80:80
@@ -20,10 +21,6 @@ services:
      - ./nginx/proxy.conf:/etc/nginx/proxy.conf
      - ./nginx/nginx.conf:/etc/nginx/nginx.conf
    env_file: .env
-    environment:
-      - TZ=${TIMEZONE}
-      - HF_ENDPOINT=${HF_ENDPOINT}
-      - MACOS=${MACOS}
    networks:
      - ragflow
    restart: on-failure
@@ -31,3 +28,35 @@ services:
    # 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"
+
+  ragflow-gpu:
+    depends_on:
+      mysql:
+        condition: service_healthy
+    profiles:
+      - gpu
+    image: edwardelric233/ragflow:oc9
+    ports:
+      - ${SVR_HTTP_PORT}:9380
+      - 80:80
+      - 443:443
+    volumes:
+      - ./ragflow-logs:/ragflow/logs
+      - ./nginx/ragflow.conf:/etc/nginx/conf.d/ragflow.conf
+      - ./nginx/proxy.conf:/etc/nginx/proxy.conf
+      - ./nginx/nginx.conf:/etc/nginx/nginx.conf
+    env_file: .env
+    networks:
+      - ragflow
+    restart: on-failure
+    # https://docs.docker.com/engine/daemon/prometheus/#create-a-prometheus-configuration
+    # If you're using Docker Desktop, the --add-host flag is optional. This flag makes sure that the host's internal IP gets exposed to the Prometheus container.
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
--- a/docker/docker-compose-base.yml
+++ b/docker/docker-compose-base.yml
@@ -1,6 +1,5 @@
 services:
  es01:
-    container_name: ragflow-es-01
    profiles:
      - elasticsearch
    image: elasticsearch:${STACK_VERSION}
@@ -20,7 +19,6 @@ services:
      - 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:
@@ -36,7 +34,6 @@ services:
    restart: on-failure

  opensearch01:
-    container_name: ragflow-opensearch-01
    profiles:
      - opensearch
    image: hub.icert.top/opensearchproject/opensearch:2.19.1
@@ -57,7 +54,6 @@ services:
      - cluster.routing.allocation.disk.watermark.low=5gb
      - cluster.routing.allocation.disk.watermark.high=3gb
      - cluster.routing.allocation.disk.watermark.flood_stage=2gb
-      - TZ=${TIMEZONE}
      - http.port=9201
    mem_limit: ${MEM_LIMIT}
    ulimits:
@@ -74,7 +70,6 @@ services:
    restart: on-failure

  infinity:
-    container_name: ragflow-infinity
    profiles:
      - infinity
    image: infiniflow/infinity:v0.6.1
@@ -87,8 +82,6 @@ services:
      - ${INFINITY_HTTP_PORT}:23820
      - ${INFINITY_PSQL_PORT}:5432
    env_file: .env
-    environment:
-      - TZ=${TIMEZONE}
    mem_limit: ${MEM_LIMIT}
    ulimits:
      nofile:
@@ -104,7 +97,6 @@ services:
    restart: on-failure

  sandbox-executor-manager:
-    container_name: ragflow-sandbox-executor-manager
    profiles:
      - sandbox
    image: ${SANDBOX_EXECUTOR_MANAGER_IMAGE-infiniflow/sandbox-executor-manager:latest}
@@ -119,7 +111,6 @@ services:
    security_opt:
      - no-new-privileges:true
    environment:
-      - TZ=${TIMEZONE}
      - 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=${SANDBOX_BASE_NODEJS_IMAGE:-infiniflow/sandbox-base-nodejs:latest}
@@ -136,11 +127,9 @@ services:
  mysql:
    # mysql:5.7 linux/arm64 image is unavailable.
    image: mysql:8.0.39
-    container_name: ragflow-mysql
    env_file: .env
    environment:
      - MYSQL_ROOT_PASSWORD=${MYSQL_PASSWORD}
-      - TZ=${TIMEZONE}
    command:
      --max_connections=1000
      --character-set-server=utf8mb4
@@ -165,7 +154,6 @@ services:

  minio:
    image: quay.io/minio/minio:RELEASE.2025-06-13T11-33-47Z
-    container_name: ragflow-minio
    command: server --console-address ":9001" /data
    ports:
      - ${MINIO_PORT}:9000
@@ -174,7 +162,6 @@ services:
    environment:
      - MINIO_ROOT_USER=${MINIO_USER}
      - MINIO_ROOT_PASSWORD=${MINIO_PASSWORD}
-      - TZ=${TIMEZONE}
    volumes:
      - minio_data:/data
    networks:
@@ -189,7 +176,6 @@ services:
  redis:
    # swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/valkey/valkey:8
    image: valkey/valkey:8
-    container_name: ragflow-redis
    command: redis-server --requirepass ${REDIS_PASSWORD} --maxmemory 128mb --maxmemory-policy allkeys-lru
    env_file: .env
    ports:
@@ -207,16 +193,48 @@ services:
      start_period: 10s    


+  tei-cpu:
+    profiles:
+      - tei-cpu
+    image: ${TEI_IMAGE_CPU}
+    hostname: tei
+    ports:
+      - ${TEI_PORT-6380}:80
+    env_file: .env
+    networks:
+      - ragflow
+    command: ["--model-id", "/data/${TEI_MODEL}"]
+    restart: on-failure
+
+
+  tei-gpu:
+    profiles:
+      - tei-gpu
+    image: ${TEI_IMAGE_GPU}
+    hostname: tei
+    ports:
+      - ${TEI_PORT-6380}:80
+    env_file: .env
+    networks:
+      - ragflow
+    command: ["--model-id", "/data/${TEI_MODEL}"]
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    restart: on-failure
+
+
  kibana:
-    container_name: ragflow-kibana
    profiles:
      - kibana
    image: kibana:${STACK_VERSION}
    ports:
      - ${KIBANA_PORT-5601}:5601
    env_file: .env
-    environment:
-      - TZ=${TIMEZONE}
    volumes:
      - kibana_data:/usr/share/kibana/data
    depends_on:
@@ -245,6 +263,8 @@ volumes:
    driver: local
  redis_data:
    driver: local
+  tei_data:
+    driver: local
  kibana_data:
    driver: local

--- a/docker/docker-compose-gpu-CN-oc9.yml
+++ b/docker/docker-compose-gpu-CN-oc9.yml
@@ -1,40 +0,0 @@
-# The RAGFlow team do not actively maintain docker-compose-gpu-CN-oc9.yml, so use them at your own risk. 
-# However, you are welcome to file a pull request to improve it.
-include:
-  - ./docker-compose-base.yml
-
-services:
-  ragflow:
-    depends_on:
-      mysql:
-        condition: service_healthy
-    image: edwardelric233/ragflow:oc9
-    container_name: ragflow-server
-    ports:
-      - ${SVR_HTTP_PORT}:9380
-      - 80:80
-      - 443:443
-    volumes:
-      - ./ragflow-logs:/ragflow/logs
-      - ./nginx/ragflow.conf:/etc/nginx/conf.d/ragflow.conf
-      - ./nginx/proxy.conf:/etc/nginx/proxy.conf
-      - ./nginx/nginx.conf:/etc/nginx/nginx.conf
-    env_file: .env
-    environment:
-      - TZ=${TIMEZONE}
-      - HF_ENDPOINT=${HF_ENDPOINT}
-      - MACOS=${MACOS}
-    networks:
-      - ragflow
-    restart: on-failure
-    # 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]
--- a/docker/docker-compose-gpu.yml
+++ b/docker/docker-compose-gpu.yml
@@ -1,40 +0,0 @@
-# The RAGFlow team do not actively maintain docker-compose-gpu.yml, so use them at your own risk. 
-# Pull requests to improve it are welcome.
-include:
-  - ./docker-compose-base.yml
-
-services:
-  ragflow:
-    depends_on:
-      mysql:
-        condition: service_healthy
-    image: ${RAGFLOW_IMAGE}
-    container_name: ragflow-server
-    ports:
-      - ${SVR_HTTP_PORT}:9380
-      - 80:80
-      - 443:443
-    volumes:
-      - ./ragflow-logs:/ragflow/logs
-      - ./nginx/ragflow.conf:/etc/nginx/conf.d/ragflow.conf
-      - ./nginx/proxy.conf:/etc/nginx/proxy.conf
-      - ./nginx/nginx.conf:/etc/nginx/nginx.conf
-    env_file: .env
-    environment:
-      - TZ=${TIMEZONE}
-      - HF_ENDPOINT=${HF_ENDPOINT}
-      - MACOS=${MACOS}
-    networks:
-      - ragflow
-    restart: on-failure
-    # 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]
--- a/docker/docker-compose-macos.yml
+++ b/docker/docker-compose-macos.yml
@@ -10,7 +10,6 @@ services:
    build:
      context: ../
      dockerfile: Dockerfile
-    container_name: ragflow-server
    ports:
      - ${SVR_HTTP_PORT}:9380
      - 80:80
@@ -21,11 +20,6 @@ services:
      - ./nginx/proxy.conf:/etc/nginx/proxy.conf
      - ./nginx/nginx.conf:/etc/nginx/nginx.conf
    env_file: .env
-    environment:
-      - TZ=${TIMEZONE}
-      - HF_ENDPOINT=${HF_ENDPOINT}
-      - MACOS=${MACOS:-1}
-      - LIGHTEN=${LIGHTEN:-1}
    networks:
      - ragflow
    restart: on-failure
@@ -38,15 +32,10 @@ services:
  #     mysql:
  #       condition: service_healthy
  #   image: ${RAGFLOW_IMAGE}
-  #   container_name: ragflow-executor
  #   volumes:
  #     - ./ragflow-logs:/ragflow/logs
  #     - ./nginx/ragflow.conf:/etc/nginx/conf.d/ragflow.conf
  #   env_file: .env
-  #   environment:
-  #     - TZ=${TIMEZONE}
-  #     - HF_ENDPOINT=${HF_ENDPOINT}
-  #     - MACOS=${MACOS}
  #   entrypoint: "/ragflow/entrypoint_task_executor.sh 1 3"
  #   networks:
  #     - ragflow
--- a/docker/docker-compose.yml
+++ b/docker/docker-compose.yml
@@ -2,10 +2,12 @@ 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:
-  ragflow:
+  ragflow-cpu:
    depends_on:
      mysql:
        condition: service_healthy
+    profiles:
+      - cpu
    image: ${RAGFLOW_IMAGE}
    # Example configuration to set up an MCP server:
    # command:
@@ -26,7 +28,6 @@ services:
    # Example configration to start Admin server:
    # command:
    #   - --enable-adminserver
-    container_name: ragflow-server
    ports:
      - ${SVR_HTTP_PORT}:9380
      - ${ADMIN_SVR_HTTP_PORT}:9381
@@ -44,10 +45,6 @@ services:
      - ./service_conf.yaml.template:/ragflow/conf/service_conf.yaml.template
      - ./entrypoint.sh:/ragflow/entrypoint.sh
    env_file: .env
-    environment:
-      - TZ=${TIMEZONE}
-      - HF_ENDPOINT=${HF_ENDPOINT-}
-      - MACOS=${MACOS-}
    networks:
      - ragflow
    restart: on-failure
@@ -55,20 +52,75 @@ services:
    # 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
+    profiles:
+      - gpu
+    image: ${RAGFLOW_IMAGE}
+    # 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 configration to start Admin server:
+    # command:
+    #   - --enable-adminserver
+    ports:
+      - ${SVR_HTTP_PORT}:9380
+      - ${ADMIN_SVR_HTTP_PORT}:9381
+      - 80:80
+      - 443:443
+      - 5678:5678
+      - 5679:5679
+      - 9382:9382 # 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
+      - ../history_data_agent:/ragflow/history_data_agent
+      - ./service_conf.yaml.template:/ragflow/conf/service_conf.yaml.template
+      - ./entrypoint.sh:/ragflow/entrypoint.sh
+    env_file: .env
+    networks:
+      - ragflow
+    restart: on-failure
+    # 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: ${RAGFLOW_IMAGE}
-  #   container_name: ragflow-executor
  #   volumes:
  #     - ./ragflow-logs:/ragflow/logs
  #     - ./nginx/ragflow.conf:/etc/nginx/conf.d/ragflow.conf
  #   env_file: .env
-  #   environment:
-  #     - TZ=${TIMEZONE}
-  #     - HF_ENDPOINT=${HF_ENDPOINT}
-  #     - MACOS=${MACOS}
  #   entrypoint: "/ragflow/entrypoint_task_executor.sh 1 3"
  #   networks:
  #     - ragflow
@@ -77,3 +129,10 @@ services:
  #   # 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]
--- a/docker/nginx/ragflow.conf
+++ b/docker/nginx/ragflow.conf
@@ -11,7 +11,7 @@ server {
    gzip_disable "MSIE [1-6]\.";

    location ~ ^/(v1|api) {
-        proxy_pass http://ragflow:9380;
+        proxy_pass http://localhost:9380;
        include proxy.conf;
    }

--- a/docker/service_conf.yaml.template
+++ b/docker/service_conf.yaml.template
@@ -32,6 +32,11 @@ redis:
  db: 1
  password: '${REDIS_PASSWORD:-infini_rag_flow}'
  host: '${REDIS_HOST:-redis}:6379'
+user_default_llm:
+  default_models:
+    embedding_model:
+      api_key: 'xxx'
+      base_url: 'http://${TEI_HOST}:80'
 # postgres:
 #   name: '${POSTGRES_DBNAME:-rag_flow}'
 #   user: '${POSTGRES_USER:-rag_flow}'