compose_remote.yaml

# Copyright (C) 2025 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

services:
  agent-vllm-service:
    image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
    container_name: vllm-service
    ports:
      - "9009:80"
    volumes:
      - "${MODEL_CACHE:-./data}:/root/.cache/huggingface/hub"
    shm_size: 128g
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      HF_TOKEN: ${HF_TOKEN}
      LLM_MODEL_ID: ${model}
      VLLM_TORCH_PROFILER_DIR: "/mnt"
      VLLM_CPU_KVCACHE_SPACE: 40
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
      interval: 10s
      timeout: 10s
      retries: 100
    command: --model $model --host 0.0.0.0 --port 80

  worker-rag-agent:
    depends_on:
      agent-vllm-service:
        condition: service_healthy
    environment:
      llm_engine: vllm
      llm_endpoint_url: ${LLM_ENDPOINT_URL}

  worker-sql-agent:
    depends_on:
      agent-vllm-service:
        condition: service_healthy
    environment:
      llm_engine: vllm
      llm_endpoint_url: ${LLM_ENDPOINT_URL}

  supervisor-react-agent:
    depends_on:
      agent-vllm-service:
        condition: service_healthy
    environment:
      llm_engine: vllm
      llm_endpoint_url: ${LLM_ENDPOINT_URL}