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

services:
  tgi-server:
    image: ghcr.io/huggingface/tgi-gaudi:2.0.4
    container_name: tgi-server
    ports:
      - "8085:80"
    volumes:
      - ${HF_CACHE_DIR}:/data
    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
      HABANA_VISIBLE_DEVICES: all
      OMPI_MCA_btl_vader_single_copy_mechanism: none
      PT_HPU_ENABLE_LAZY_COLLECTIVES: true
    runtime: habana
    cap_add:
      - SYS_NICE
    ipc: host
    command: --model-id ${LLM_MODEL_ID} --max-input-length 4096 --max-total-tokens 8192 --sharded true --num-shard ${NUM_SHARDS}
  worker-docgrader-agent:
    image: opea/agent-langchain:latest
    container_name: docgrader-agent-endpoint
    depends_on:
      - tgi-server
    volumes:
      # - ${WORKDIR}/GenAIExamples/AgentQnA/docker_image_build/GenAIComps/comps/agent/langchain/:/home/user/comps/agent/langchain/
      - ${TOOLSET_PATH}:/home/user/tools/
    ports:
      - "9095:9095"
    ipc: host
    environment:
      ip_address: ${ip_address}
      strategy: rag_agent
      recursion_limit: ${recursion_limit_worker}
      llm_engine: tgi
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      llm_endpoint_url: ${LLM_ENDPOINT_URL}
      model: ${LLM_MODEL_ID}
      temperature: ${temperature}
      max_new_tokens: ${max_new_tokens}
      streaming: false
      tools: /home/user/tools/worker_agent_tools.yaml
      require_human_feedback: false
      RETRIEVAL_TOOL_URL: ${RETRIEVAL_TOOL_URL}
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
      LANGCHAIN_PROJECT: "opea-worker-agent-service"
      port: 9095


  supervisor-react-agent:
    image: opea/agent-langchain:latest
    container_name: react-agent-endpoint
    depends_on:
      - tgi-server
      - worker-docgrader-agent
    volumes:
      # - ${WORKDIR}/GenAIExamples/AgentQnA/docker_image_build/GenAIComps/comps/agent/langchain/:/home/user/comps/agent/langchain/
      - ${TOOLSET_PATH}:/home/user/tools/
    ports:
      - "9090:9090"
    ipc: host
    environment:
      ip_address: ${ip_address}
      strategy: react_langgraph
      recursion_limit: ${recursion_limit_supervisor}
      llm_engine: tgi
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      llm_endpoint_url: ${LLM_ENDPOINT_URL}
      model: ${LLM_MODEL_ID}
      temperature: ${temperature}
      max_new_tokens: ${max_new_tokens}
      streaming: false
      tools: /home/user/tools/supervisor_agent_tools.yaml
      require_human_feedback: false
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
      LANGCHAIN_PROJECT: "opea-supervisor-agent-service"
      CRAG_SERVER: $CRAG_SERVER
      WORKER_AGENT_URL: $WORKER_AGENT_URL
      port: 9090