# 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://redis-vector-db:6379
      REDIS_HOST: redis-vector-db
      INDEX_NAME: ${INDEX_NAME}
      TEI_ENDPOINT: http://tei-embedding-service:80
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
  tei-embedding-service:
    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
    container_name: tei-embedding-gaudi-server
    ports:
      - "8090:80"
    volumes:
      - "./data:/data"
    shm_size: 1g
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
  retriever:
    image: ${REGISTRY:-opea}/retriever-redis:${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://redis-vector-db:6379
      REDIS_HOST: redis-vector-db
      INDEX_NAME: ${INDEX_NAME}
      TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
    restart: unless-stopped
  tei-reranking-service:
    image: ghcr.io/huggingface/tei-gaudi:1.5.0
    container_name: tei-reranking-gaudi-server
    ports:
      - "8808:80"
    volumes:
      - "./data:/data"
    runtime: habana
    cap_add:
      - SYS_NICE
    ipc: host
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      HF_HUB_DISABLE_PROGRESS_BARS: 1
      HF_HUB_ENABLE_HF_TRANSFER: 0
      HABANA_VISIBLE_DEVICES: all
      OMPI_MCA_btl_vader_single_copy_mechanism: none
      MAX_WARMUP_SEQUENCE_LENGTH: 512
    command: --model-id ${RERANK_MODEL_ID} --auto-truncate
  tgi-service:
    image: ghcr.io/huggingface/tgi-gaudi:2.0.6
    container_name: tgi-gaudi-server
    ports:
      - "8005:80"
    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 2048 --max-total-tokens 4096
  chatqna-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
      - tgi-service
    ports:
      - "8888:8888"
    environment:
      - no_proxy=${no_proxy}
      - https_proxy=${https_proxy}
      - http_proxy=${http_proxy}
      - MEGA_SERVICE_HOST_IP=chatqna-gaudi-backend-server
      - EMBEDDING_SERVER_HOST_IP=tei-embedding-service
      - EMBEDDING_SERVER_PORT=${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}
      - LLM_MODEL=${LLM_MODEL_ID}
      - LOGFLAG=${LOGFLAG}
    ipc: host
    restart: always
  chatqna-gaudi-ui-server:
    image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
    container_name: chatqna-gaudi-ui-server
    depends_on:
      - chatqna-gaudi-backend-server
    ports:
      - "5173:5173"
    environment:
      - no_proxy=${no_proxy}
      - https_proxy=${https_proxy}
      - http_proxy=${http_proxy}
    ipc: host
    restart: always
  chatqna-gaudi-nginx-server:
    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
    container_name: chatqna-gaudi-nginx-server
    depends_on:
      - chatqna-gaudi-backend-server
      - chatqna-gaudi-ui-server
    ports:
      - "${NGINX_PORT:-80}:80"
    environment:
      - no_proxy=${no_proxy}
      - https_proxy=${https_proxy}
      - http_proxy=${http_proxy}
      - FRONTEND_SERVICE_IP=chatqna-gaudi-ui-server
      - FRONTEND_SERVICE_PORT=5173
      - BACKEND_SERVICE_NAME=chatqna
      - BACKEND_SERVICE_IP=chatqna-gaudi-backend-server
      - BACKEND_SERVICE_PORT=8888
      - DATAPREP_SERVICE_IP=dataprep-redis-service
      - DATAPREP_SERVICE_PORT=6007
    ipc: host
    restart: always

networks:
  default:
    driver: bridge