compose_openai.yaml

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


x-common-environment:
  &common-env
  no_proxy: ${NO_PROXY}
  http_proxy: ${HTTP_PROXY}
  https_proxy: ${HTTPS_PROXY}

x-common-agent-environment:
  &common-agent-env
  <<: *common-env
  llm_engine: openai
  model: ${OPENAI_LLM_MODEL_ID}
  OPENAI_API_KEY: ${OPENAI_API_KEY}
  REDIS_URL_VECTOR: ${REDIS_URL_VECTOR}
  REDIS_URL_KV: ${REDIS_URL_KV}
  TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
  ip_address: ${HOST_IP}
  strategy: react_llama
  require_human_feedback: false

services:

  tei-embedding-serving:
    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.7
    container_name: tei-embedding-serving
    entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${EMBEDDING_MODEL_ID} --auto-truncate"
    ports:
      - "${TEI_EMBEDDER_PORT:-10221}:80"
    volumes:
      - ${HF_CACHE_DIR:-./data}:/data
    shm_size: 1g
    environment:
      <<: *common-env
      HF_TOKEN: ${HF_TOKEN}
      host_ip: ${HOST_IP}
    healthcheck:
      test: ["CMD", "curl", "-f", "http://${HOST_IP}:${TEI_EMBEDDER_PORT}/health"]
      interval: 10s
      timeout: 6s
      retries: 48

  redis-vector-db:
    image: redis/redis-stack:7.2.0-v9
    container_name: redis-vector-db
    ports:
      - "${REDIS_PORT1:-6379}:6379"
      - "${REDIS_PORT2:-8001}:8001"
    environment:
      <<: *common-env
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      timeout: 10s
      retries: 3
      start_period: 10s

  redis-kv-store:
    image: redis/redis-stack:7.2.0-v9
    container_name: redis-kv-store
    ports:
      - "${REDIS_PORT3:-6380}:6379"
      - "${REDIS_PORT4:-8002}:8001"
    environment:
      <<: *common-env
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      timeout: 10s
      retries: 3
      start_period: 10s

  dataprep-redis-finance:
    image: ${REGISTRY:-opea}/dataprep:${TAG:-latest}
    container_name: dataprep-redis-server-finance
    depends_on:
      redis-vector-db:
        condition: service_healthy
      redis-kv-store:
        condition: service_healthy
      tei-embedding-serving:
        condition: service_healthy
    ports:
      - "${DATAPREP_PORT:-6007}:5000"
    environment:
      <<: *common-env
      DATAPREP_COMPONENT_NAME: ${DATAPREP_COMPONENT_NAME}
      REDIS_URL_VECTOR: ${REDIS_URL_VECTOR}
      REDIS_URL_KV: ${REDIS_URL_KV}
      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
      LLM_ENDPOINT: ${LLM_ENDPOINT}
      LLM_MODEL: ${LLM_MODEL_ID}
      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
      HF_TOKEN: ${HF_TOKEN}
      LOGFLAG: true

  worker-finqa-agent:
    image: opea/agent:latest
    container_name: finqa-agent-endpoint
    volumes:
      - ${TOOLSET_PATH}:/home/user/tools/
      - ${PROMPT_PATH}:/home/user/prompts/
    ipc: host
    ports:
      - "9095:9095"
    environment:
      <<: *common-agent-env
      with_memory: false
      recursion_limit: ${RECURSION_LIMIT_WORKER}
      temperature: ${TEMPERATURE}
      max_new_tokens: ${MAX_TOKENS}
      stream: false
      tools: /home/user/tools/finqa_agent_tools.yaml
      custom_prompt: /home/user/prompts/finqa_prompt.py
      port: 9095

  worker-research-agent:
    image: opea/agent:latest
    container_name: research-agent-endpoint
    volumes:
      - ${TOOLSET_PATH}:/home/user/tools/
      - ${PROMPT_PATH}:/home/user/prompts/
    ipc: host
    ports:
      - "9096:9096"
    environment:
      <<: *common-agent-env
      with_memory: false
      recursion_limit: ${RECURSION_LIMIT_WORKER}
      stream: false
      tools: /home/user/tools/research_agent_tools.yaml
      custom_prompt: /home/user/prompts/research_prompt.py
      FINNHUB_API_KEY: ${FINNHUB_API_KEY}
      FINANCIAL_DATASETS_API_KEY: ${FINANCIAL_DATASETS_API_KEY}
      port: 9096

  docsum-vllm-xeon:
    image: opea/llm-docsum:latest
    container_name: docsum-vllm-xeon
    ports:
      - ${DOCSUM_PORT:-9000}:9000
    ipc: host
    environment:
      <<: *common-env
      LLM_ENDPOINT: ${LLM_ENDPOINT}
      LLM_MODEL_ID: ${LLM_MODEL_ID}
      HF_TOKEN: ${HF_TOKEN}
      LOGFLAG: ${LOGFLAG:-False}
      MAX_INPUT_TOKENS: ${MAX_INPUT_TOKENS}
      MAX_TOTAL_TOKENS: ${MAX_TOTAL_TOKENS}
      DocSum_COMPONENT_NAME: ${DOCSUM_COMPONENT_NAME:-OpeaDocSumvLLM}
    restart: unless-stopped

  supervisor-react-agent:
    image: opea/agent:latest
    container_name: supervisor-agent-endpoint
    volumes:
      - ${TOOLSET_PATH}:/home/user/tools/
      - ${PROMPT_PATH}:/home/user/prompts/
    ipc: host
    depends_on:
      - worker-finqa-agent
      - worker-research-agent
    ports:
      - "9090:9090"
    environment:
      <<: *common-agent-env
      with_memory: "true"
      recursion_limit: ${RECURSION_LIMIT_SUPERVISOR}
      temperature: ${TEMPERATURE}
      max_new_tokens: ${MAX_TOKENS}
      stream: "true"
      tools: /home/user/tools/supervisor_agent_tools.yaml
      custom_prompt: /home/user/prompts/supervisor_prompt.py
      WORKER_FINQA_AGENT_URL: ${WORKER_FINQA_AGENT_URL}
      WORKER_RESEARCH_AGENT_URL: ${WORKER_RESEARCH_AGENT_URL}
      DOCSUM_ENDPOINT: ${DOCSUM_ENDPOINT}
      port: 9090

  agent-ui:
    image: opea/agent-ui:latest
    container_name: agent-ui
    environment:
      <<: *common-env
      host_ip: ${HOST_IP}
    ports:
      - "5175:8080"
    ipc: host