GenAIExamples/SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml

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

services:
  tei-embedding-service:
    image: ghcr.io/huggingface/tei-gaudi:latest
    container_name: tei-embedding-gaudi-server
    ports:
      - "3001:80"
    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
      INIT_HCCL_ON_ACQUIRE: 0
      ENABLE_EXPERIMENTAL_FLAGS: true
    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
  embedding:
    image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
    container_name: embedding-tei-server
    depends_on:
      - tei-embedding-service
    ports:
      - "3002:6000"
    ipc: host
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
    restart: unless-stopped
  web-retriever:
    image: ${REGISTRY:-opea}/web-retriever-chroma:${TAG:-latest}
    container_name: web-retriever-chroma-server
    ports:
      - "3003:7077"
    ipc: host
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
      GOOGLE_API_KEY: ${GOOGLE_API_KEY}
      GOOGLE_CSE_ID: ${GOOGLE_CSE_ID}
    restart: unless-stopped
  tei-reranking-service:
    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
    container_name: tei-reranking-server
    ports:
      - "3004:80"
    volumes:
      - "./data:/data"
    shm_size: 1g
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
    command: --model-id ${RERANK_MODEL_ID} --auto-truncate
  reranking:
    image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
    container_name: reranking-tei-xeon-server
    depends_on:
      - tei-reranking-service
    ports:
      - "3005:8000"
    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}
    restart: unless-stopped
  tgi-service:
    image: ghcr.io/huggingface/tgi-gaudi:2.0.6
    container_name: tgi-gaudi-server
    ports:
      - "3006:80"
    volumes:
      - "./data:/data"
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      HF_HUB_DISABLE_PROGRESS_BARS: 1
      HF_HUB_ENABLE_HF_TRANSFER: 0
      HABANA_VISIBLE_DEVICES: all
      OMPI_MCA_btl_vader_single_copy_mechanism: none
      ENABLE_HPU_GRAPH: true
      LIMIT_HPU_GRAPH: true
      USE_FLASH_ATTENTION: true
      FLASH_ATTENTION_RECOMPUTE: true
    runtime: habana
    cap_add:
      - SYS_NICE
    ipc: host
    command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
  llm:
    image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
    container_name: llm-tgi-gaudi-server
    depends_on:
      - tgi-service
    ports:
      - "3007:9000"
    ipc: host
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      HF_HUB_DISABLE_PROGRESS_BARS: 1
      HF_HUB_ENABLE_HF_TRANSFER: 0
    restart: unless-stopped
  searchqna-gaudi-backend-server:
    image: ${REGISTRY:-opea}/searchqna:${TAG:-latest}
    container_name: searchqna-gaudi-backend-server
    depends_on:
      - tei-embedding-service
      - embedding
      - web-retriever
      - tei-reranking-service
      - reranking
      - tgi-service
      - llm
    ports:
      - "3008:8888"
    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=${EMBEDDING_SERVICE_HOST_IP}
      - WEB_RETRIEVER_SERVICE_HOST_IP=${WEB_RETRIEVER_SERVICE_HOST_IP}
      - RERANK_SERVICE_HOST_IP=${RERANK_SERVICE_HOST_IP}
      - LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
      - EMBEDDING_SERVICE_PORT=${EMBEDDING_SERVICE_PORT}
      - WEB_RETRIEVER_SERVICE_PORT=${WEB_RETRIEVER_SERVICE_PORT}
      - RERANK_SERVICE_PORT=${RERANK_SERVICE_PORT}
      - LLM_SERVICE_PORT=${LLM_SERVICE_PORT}
    ipc: host
    restart: always
  searchqna-gaudi-ui-server:
    image: ${REGISTRY:-opea}/searchqna-ui:${TAG:-latest}
    container_name: searchqna-gaudi-ui-server
    depends_on:
      - searchqna-gaudi-backend-server
    ports:
      - "5173:5173"
    environment:
      - no_proxy=${no_proxy}
      - https_proxy=${https_proxy}
      - http_proxy=${http_proxy}
      - BACKEND_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
    ipc: host
    restart: always

networks:
  default:
    driver: bridge