GenAIExamples/ChatQnA/docker_compose/intel/hpu/gaudi/compose_vllm.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: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
    container_name: dataprep-redis-server
    depends_on:
      - redis-vector-db
      - tei-embedding-service
    ports:
      - "6007:6007"
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      REDIS_URL: ${REDIS_URL}
      INDEX_NAME: ${INDEX_NAME}
      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
  tei-embedding-service:
    image: ghcr.io/huggingface/tei-gaudi:latest
    container_name: tei-embedding-gaudi-server
    ports:
      - "8090:80"
    volumes:
      - "./data:/data"
    runtime: habana
    cap_add:
      - SYS_NICE
    ipc: host
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      HABANA_VISIBLE_DEVICES: all
      OMPI_MCA_btl_vader_single_copy_mechanism: none
      MAX_WARMUP_SEQUENCE_LENGTH: 512
    command: --model-id ${EMBEDDING_MODEL_ID}
  retriever:
    image: ${REGISTRY:-opea}/retriever-redis:${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_URL}
      INDEX_NAME: ${INDEX_NAME}
      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
    restart: unless-stopped
  tei-reranking-service:
    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
    container_name: tei-reranking-gaudi-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: ${HUGGINGFACEHUB_API_TOKEN}
      HF_HUB_DISABLE_PROGRESS_BARS: 1
      HF_HUB_ENABLE_HF_TRANSFER: 0
    command: --model-id ${RERANK_MODEL_ID} --auto-truncate
  vllm-service:
    image: ${REGISTRY:-opea}/llm-vllm-hpu:${TAG:-latest}
    container_name: vllm-gaudi-server
    ports:
      - "8007:80"
    volumes:
      - "./data:/data"
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      HABANA_VISIBLE_DEVICES: all
      OMPI_MCA_btl_vader_single_copy_mechanism: none
      LLM_MODEL_ID: ${LLM_MODEL_ID}
    runtime: habana
    cap_add:
      - SYS_NICE
    ipc: host
    command: /bin/bash -c "export VLLM_CPU_KVCACHE_SPACE=40 && python3 -m vllm.entrypoints.openai.api_server --enforce-eager --model $LLM_MODEL_ID --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048"
  chaqna-gaudi-backend-server:
    image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
    container_name: chatqna-gaudi-backend-server
    depends_on:
      - redis-vector-db
      - tei-embedding-service
      - retriever
      - tei-reranking-service
      - vllm-service
    ports:
      - "8888:8888"
    environment:
      - no_proxy=${no_proxy}
      - https_proxy=${https_proxy}
      - http_proxy=${http_proxy}
      - MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
      - EMBEDDING_SERVER_HOST_IP=${EMBEDDING_SERVER_HOST_IP}
      - EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-8090}
      - RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
      - RERANK_SERVER_HOST_IP=${RERANK_SERVER_HOST_IP}
      - RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-8808}
      - LLM_SERVER_HOST_IP=${LLM_SERVER_HOST_IP}
      - LLM_SERVER_PORT=${LLM_SERVER_PORT:-8007}
      - LOGFLAG=${LOGFLAG}
    ipc: host
    restart: always
  chaqna-gaudi-ui-server:
    image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
    container_name: chatqna-gaudi-ui-server
    depends_on:
      - chaqna-gaudi-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-gaudi-nginx-server:
    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
    container_name: chaqna-gaudi-nginx-server
    depends_on:
      - chaqna-gaudi-backend-server
      - chaqna-gaudi-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