GenAIExamples/FinanceAgent/docker_compose/intel/hpu/gaudi/compose.yaml

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

services:
  worker-finqa-agent:
    image: opea/agent:latest
    container_name: finqa-agent-endpoint
    volumes:
      - ${TOOLSET_PATH}:/home/user/tools/
      - ${PROMPT_PATH}:/home/user/prompts/
    ports:
      - "9095:9095"
    ipc: host
    environment:
      ip_address: ${ip_address}
      strategy: react_llama
      with_memory: false
      recursion_limit: ${recursion_limit_worker}
      llm_engine: vllm
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      llm_endpoint_url: ${LLM_ENDPOINT_URL}
      model: ${LLM_MODEL_ID}
      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
      require_human_feedback: false
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      REDIS_URL_VECTOR: $REDIS_URL_VECTOR
      REDIS_URL_KV: $REDIS_URL_KV
      TEI_EMBEDDING_ENDPOINT: $TEI_EMBEDDING_ENDPOINT
      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/
    ports:
      - "9096:9096"
    ipc: host
    environment:
      ip_address: ${ip_address}
      strategy: react_llama
      with_memory: false
      recursion_limit: 25
      llm_engine: vllm
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      llm_endpoint_url: ${LLM_ENDPOINT_URL}
      model: ${LLM_MODEL_ID}
      stream: false
      tools: /home/user/tools/research_agent_tools.yaml
      custom_prompt: /home/user/prompts/research_prompt.py
      require_human_feedback: false
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      FINNHUB_API_KEY: ${FINNHUB_API_KEY}
      FINANCIAL_DATASETS_API_KEY: ${FINANCIAL_DATASETS_API_KEY}
      port: 9096

  supervisor-react-agent:
    image: opea/agent:latest
    container_name: supervisor-agent-endpoint
    depends_on:
      - worker-finqa-agent
      - worker-research-agent
    volumes:
      - ${TOOLSET_PATH}:/home/user/tools/
      - ${PROMPT_PATH}:/home/user/prompts/
    ports:
      - "9090:9090"
    ipc: host
    environment:
      ip_address: ${ip_address}
      strategy: react_llama
      with_memory: true
      recursion_limit: ${recursion_limit_supervisor}
      llm_engine: vllm
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      llm_endpoint_url: ${LLM_ENDPOINT_URL}
      model: ${LLM_MODEL_ID}
      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
      require_human_feedback: false
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      WORKER_FINQA_AGENT_URL: $WORKER_FINQA_AGENT_URL
      WORKER_RESEARCH_AGENT_URL: $WORKER_RESEARCH_AGENT_URL
      DOCSUM_ENDPOINT: $DOCSUM_ENDPOINT
      REDIS_URL_VECTOR: $REDIS_URL_VECTOR
      REDIS_URL_KV: $REDIS_URL_KV
      TEI_EMBEDDING_ENDPOINT: $TEI_EMBEDDING_ENDPOINT
      port: 9090

  docsum-vllm-gaudi:
    image: opea/llm-docsum:latest
    container_name: docsum-vllm-gaudi
    ports:
      - ${DOCSUM_PORT:-9000}:9000
    ipc: host
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      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

  agent-ui:
    image: opea/agent-ui:latest
    container_name: agent-ui
    environment:
      host_ip: ${host_ip}
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
    ports:
      - "5175:8080"
    ipc: host