GenAIExamples/ChatQnA/docker_compose/intel/cpu/xeon/compose_qdrant.yaml

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

services:
  qdrant-vector-db:
    image: qdrant/qdrant
    container_name: qdrant-vector-db
    ports:
      - "6333:6333"
      - "6334:6334"
  dataprep-qdrant-service:
    image: ${REGISTRY:-opea}/dataprep-qdrant:${TAG:-latest}
    container_name: dataprep-qdrant-server
    depends_on:
      - qdrant-vector-db
      - tei-embedding-service
    ports:
      - "6043:6007"
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      QDRANT_HOST: ${QDRANT_HOST}
      QDRANT_PORT: 6333
      COLLECTION_NAME: ${INDEX_NAME}
      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
  tei-embedding-service:
    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
    container_name: tei-embedding-server
    ports:
      - "6040:80"
    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
  embedding:
    image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
    container_name: embedding-tei-server
    depends_on:
      - tei-embedding-service
    ports:
      - "6044:6000"
    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: ${REGISTRY:-opea}/retriever-qdrant:${TAG:-latest}
    container_name: retriever-qdrant-server
    depends_on:
      - qdrant-vector-db
    ports:
      - "6045:7000"
    ipc: host
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      QDRANT_HOST: ${QDRANT_HOST}
      QDRANT_PORT: 6333
      INDEX_NAME: ${INDEX_NAME}
    restart: unless-stopped
  tei-reranking-service:
    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
    container_name: tei-reranking-server
    ports:
      - "6041:80"
    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: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
    container_name: reranking-tei-xeon-server
    depends_on:
      - tei-reranking-service
    ports:
      - "6046:8000"
    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
  tgi-service:
    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
    container_name: tgi-service
    ports:
      - "6042:80"
    volumes:
      - "./data:/data"
    shm_size: 1g
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      HF_HUB_DISABLE_PROGRESS_BARS: 1
      HF_HUB_ENABLE_HF_TRANSFER: 0
    command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
  llm:
    image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
    container_name: llm-tgi-server
    depends_on:
      - tgi-service
    ports:
      - "6047:9000"
    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
  chaqna-xeon-backend-server:
    image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
    container_name: chatqna-xeon-backend-server
    depends_on:
      - qdrant-vector-db
      - tei-embedding-service
      - embedding
      - retriever
      - tei-reranking-service
      - reranking
      - tgi-service
      - llm
    ports:
      - "8912:8888"
    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=${EMBEDDING_SERVICE_HOST_IP}
      - EMBEDDING_SERVICE_PORT=${EMBEDDING_SERVICE_PORT}
      - RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
      - RETRIEVER_SERVICE_PORT=${RETRIEVER_SERVICE_PORT}
      - RERANK_SERVICE_HOST_IP=${RERANK_SERVICE_HOST_IP}
      - RERANK_SERVICE_PORT=${RERANK_SERVICE_PORT}
      - LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
      - LLM_SERVICE_PORT=${LLM_SERVICE_PORT}
    ipc: host
    restart: always
  chaqna-xeon-ui-server:
    image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
    container_name: chatqna-xeon-ui-server
    depends_on:
      - chaqna-xeon-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