GenAIExamples/ChatQnA/docker/gaudi/compose_vllm_ray.yaml

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

version: "3.8"

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: opea/dataprep-redis: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: opea/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}
  embedding:
    image: opea/embedding-tei:latest
    container_name: embedding-tei-server
    depends_on:
      - tei-embedding-service
    ports:
      - "6000:6000"
    ipc: host
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
    restart: unless-stopped
  retriever:
    image: opea/retriever-redis: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}
    restart: unless-stopped
  tei-reranking-service:
    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.2
    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
  reranking:
    image: opea/reranking-tei:latest
    container_name: reranking-tei-gaudi-server
    depends_on:
      - tei-reranking-service
    ports:
      - "8000:8000"
    ipc: host
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      TEI_RERANKING_ENDPOINT: ${TEI_RERANKING_ENDPOINT}
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      HF_HUB_DISABLE_PROGRESS_BARS: 1
      HF_HUB_ENABLE_HF_TRANSFER: 0
    restart: unless-stopped
  vllm-ray-service:
    image: opea/llm-vllm-ray-hpu:latest
    container_name: vllm-ray-gaudi-server
    ports:
      - "8006:8000"
    volumes:
      - "./data:/data"
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      HUGGINGFACEHUB_API_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 "ray start --head && python vllm_ray_openai.py --port_number 8000 --model_id_or_path $LLM_MODEL_ID --tensor_parallel_size 2 --enforce_eager True"
  llm:
    image: opea/llm-vllm-ray:latest
    container_name: llm-vllm-ray-gaudi-server
    depends_on:
      - vllm-ray-service
    ports:
      - "9000:9000"
    ipc: host
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      vLLM_RAY_ENDPOINT: ${vLLM_RAY_LLM_ENDPOINT}
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      LLM_MODEL: ${LLM_MODEL_ID}
    restart: unless-stopped
  chaqna-gaudi-backend-server:
    image: opea/chatqna:latest
    container_name: chatqna-gaudi-backend-server
    depends_on:
      - redis-vector-db
      - tei-embedding-service
      - embedding
      - retriever
      - tei-reranking-service
      - reranking
      - vllm-ray-service
      - llm
    ports:
      - "8888:8888"
    environment:
      - no_proxy=${no_proxy}
      - https_proxy=${https_proxy}
      - http_proxy=${http_proxy}
      - MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
      - EMBEDDING_SERVICE_HOST_IP=${EMBEDDING_SERVICE_HOST_IP}
      - RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
      - RERANK_SERVICE_HOST_IP=${RERANK_SERVICE_HOST_IP}
      - LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
      - LLM_SERVICE_PORT=${LLM_SERVICE_PORT}
    ipc: host
    restart: always
  chaqna-gaudi-ui-server:
    image: opea/chatqna-ui: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

networks:
  default:
    driver: bridge