GenAIExamples/ChatQnA/docker_compose/nvidia/gpu/compose.yaml

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

services:
  redis-vector-db:
    image: redis/redis-stack:7.2.0-v9
    container_name: redis-vector-db
    ports:
      - "6379:6379"
      - "8001:8001"
  dataprep-redis-service:
    image: ${REGISTRY:-opea}/dataprep:${TAG:-latest}
    container_name: dataprep-redis-server
    depends_on:
      - redis-vector-db
      - tei-embedding-service
    ports:
      - "6007:5000"
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      REDIS_URL: redis://redis-vector-db:6379
      REDIS_HOST: redis-vector-db
      INDEX_NAME: ${INDEX_NAME}
      TEI_ENDPOINT: http://tei-embedding-service:80
      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 50
    restart: unless-stopped
  tei-embedding-service:
    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
    container_name: tei-embedding-server
    ports:
      - "8090:80"
    volumes:
      - "./data:/data"
    shm_size: 1g
    ipc: host
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
  retriever:
    image: ${REGISTRY:-opea}/retriever:${TAG:-latest}
    container_name: retriever-redis-server
    depends_on:
      - redis-vector-db
    ports:
      - "7000:7000"
    ipc: host
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      REDIS_URL: redis://redis-vector-db:6379
      REDIS_HOST: redis-vector-db
      INDEX_NAME: ${INDEX_NAME}
      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
      LOGFLAG: ${LOGFLAG}
      RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
    restart: unless-stopped
  tei-reranking-service:
    image: ghcr.io/huggingface/text-embeddings-inference:1.5
    container_name: tei-reranking-server
    ports:
      - "8808:80"
    volumes:
      - "./data:/data"
    shm_size: 1g
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
      HF_HUB_DISABLE_PROGRESS_BARS: 1
      HF_HUB_ENABLE_HF_TRANSFER: 0
    command: --model-id ${RERANK_MODEL_ID} --auto-truncate
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
  tgi-service:
    image: ghcr.io/huggingface/text-generation-inference:2.4.1
    container_name: tgi-server
    ports:
      - "8008:80"
    volumes:
      - "./data:/data"
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      HF_TOKEN: ${HF_TOKEN}
      HF_HUB_DISABLE_PROGRESS_BARS: 1
      HF_HUB_ENABLE_HF_TRANSFER: 0
    ipc: host
    command: --model-id ${LLM_MODEL_ID}
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
  chaqna-backend-server:
    image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
    container_name: chatqna-backend-server
    depends_on:
      redis-vector-db:
        condition: service_started
      tei-embedding-service:
        condition: service_started
      dataprep-redis-service:
        condition: service_healthy
      retriever:
        condition: service_started
      tei-reranking-service:
        condition: service_started
      tgi-service:
        condition: service_started
    ports:
      - "8888:8888"
    environment:
      - no_proxy=${no_proxy}
      - https_proxy=${https_proxy}
      - http_proxy=${http_proxy}
      - MEGA_SERVICE_HOST_IP=chaqna-backend-server
      - EMBEDDING_SERVER_HOST_IP=tei-embedding-service
      - EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-80}
      - RETRIEVER_SERVICE_HOST_IP=retriever
      - RERANK_SERVER_HOST_IP=tei-reranking-service
      - RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-80}
      - LLM_SERVER_HOST_IP=tgi-service
      - LLM_SERVER_PORT=${LLM_SERVER_PORT:-80}
    ipc: host
    restart: always
  chaqna-ui-server:
    image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
    container_name: chatqna-ui-server
    depends_on:
      - chaqna-backend-server
    ports:
      - "5173:5173"
    environment:
      - no_proxy=${no_proxy}
      - https_proxy=${https_proxy}
      - http_proxy=${http_proxy}
      - CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
      - UPLOAD_FILE_BASE_URL=${DATAPREP_SERVICE_ENDPOINT}
      - GET_FILE=${DATAPREP_GET_FILE_ENDPOINT}
      - DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT}
    ipc: host
    restart: always
  chaqna-nginx-server:
    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
    container_name: chaqna-nginx-server
    depends_on:
      - chaqna-backend-server
      - chaqna-ui-server
    ports:
      - "${NGINX_PORT:-80}:80"
    environment:
      - no_proxy=${no_proxy}
      - https_proxy=${https_proxy}
      - http_proxy=${http_proxy}
      - FRONTEND_SERVICE_IP=${FRONTEND_SERVICE_IP}
      - FRONTEND_SERVICE_PORT=${FRONTEND_SERVICE_PORT}
      - BACKEND_SERVICE_NAME=${BACKEND_SERVICE_NAME}
      - BACKEND_SERVICE_IP=${BACKEND_SERVICE_IP}
      - BACKEND_SERVICE_PORT=${BACKEND_SERVICE_PORT}
    ipc: host
    restart: always

networks:
  default:
    driver: bridge