version: '3.8'

services:
  watsonx-openai-proxy:
    build: .
    ports:
      - "8000:8000"
    environment:
      - IBM_CLOUD_API_KEY=${IBM_CLOUD_API_KEY}
      - WATSONX_PROJECT_ID=${WATSONX_PROJECT_ID}
      - WATSONX_CLUSTER=${WATSONX_CLUSTER:-us-south}
      - HOST=0.0.0.0
      - PORT=8000
      - LOG_LEVEL=${LOG_LEVEL:-info}
      - API_KEY=${API_KEY:-}
      - ALLOWED_ORIGINS=${ALLOWED_ORIGINS:-*}
      - MODEL_MAP_GPT4=${MODEL_MAP_GPT4:-ibm/granite-4-h-small}
      - MODEL_MAP_GPT35=${MODEL_MAP_GPT35:-ibm/granite-3-8b-instruct}
      - MODEL_MAP_GPT4_TURBO=${MODEL_MAP_GPT4_TURBO:-meta-llama/llama-3-3-70b-instruct}
      - MODEL_MAP_TEXT_EMBEDDING_ADA_002=${MODEL_MAP_TEXT_EMBEDDING_ADA_002:-ibm/slate-125m-english-rtrvr}
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "python", "-c", "import httpx; httpx.get('http://localhost:8000/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 5s