GenAIExamples/ChatQnA/docker/xeon/docker_compose.yaml

# Copyright (c) 2024 Intel Corporation
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

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
    ports:
      - "6007:6007"
    environment:
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      REDIS_URL: ${REDIS_URL}
      INDEX_NAME: ${INDEX_NAME}
  tei-embedding-service:
    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.2
    container_name: tei-embedding-server
    ports:
      - "6006:80"
    volumes:
      - "./data:/data"
    shm_size: 1g
    environment:
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
    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:
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
      LANGCHAIN_PROJECT: "opea-embedding-service"
    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:
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      REDIS_URL: ${REDIS_URL}
      INDEX_NAME: ${INDEX_NAME}
      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
      LANGCHAIN_PROJECT: "opea-retriever-service"
    restart: unless-stopped
  tei-xeon-service:
    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.2
    container_name: tei-xeon-server
    ports:
      - "8808:80"
    volumes:
      - "./data:/data"
    shm_size: 1g
    environment:
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
    command: --model-id ${RERANK_MODEL_ID}
  reranking:
    image: opea/reranking-tei:latest
    container_name: reranking-tei-xeon-server
    depends_on:
      - tei-xeon-service
    ports:
      - "8000:8000"
    ipc: host
    environment:
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      TEI_RERANKING_ENDPOINT: ${TEI_RERANKING_ENDPOINT}
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
      LANGCHAIN_PROJECT: "opea-reranking-service"
    restart: unless-stopped
  tgi_service:
    image: ghcr.io/huggingface/text-generation-inference:1.4
    container_name: tgi-service
    ports:
      - "9009:80"
    volumes:
      - "./data:/data"
    shm_size: 1g
    environment:
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
    command: --model-id ${LLM_MODEL_ID}
  llm:
    image: opea/llm-tgi:latest
    container_name: llm-tgi-server
    depends_on:
      - tgi_service
    ports:
      - "9000:9000"
    ipc: host
    environment:
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
      LANGCHAIN_PROJECT: "opea-llm-service"
    restart: unless-stopped
  chaqna-xeon-backend-server:
    image: opea/chatqna:latest
    container_name: chatqna-xeon-backend-server
    depends_on:
      - redis-vector-db
      - tei-embedding-service
      - embedding
      - retriever
      - tei-xeon-service
      - reranking
      - tgi_service
      - llm
    ports:
      - "8888:8888"
    environment:
      - https_proxy=${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}
    ipc: host
    restart: always
  chaqna-xeon-ui-server:
    image: opea/chatqna-ui:latest
    container_name: chatqna-xeon-ui-server
    depends_on:
      - chaqna-xeon-backend-server
    ports:
      - "5173:5173"
    environment:
      - https_proxy=${https_proxy}
      - http_proxy=${http_proxy}
      - CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
      - UPLOAD_FILE_BASE_URL=${DATAPREP_SERVICE_ENDPOINT}
    ipc: host
    restart: always

networks:
  default:
    driver: bridge