version: '3.6'

services:
  llama-gpt-api-7b:
    image: ghcr.io/abetlen/llama-cpp-python:latest
    restart: on-failure
    volumes:
      - './models:/models'
      - './api:/api'
    ports:
      - 3001:8000
    environment:
      MODEL: '/models/llama-2-7b-chat.bin'
      MODEL_DOWNLOAD_URL: 'https://huggingface.co/TheBloke/Nous-Hermes-Llama-2-7B-GGML/resolve/main/nous-hermes-llama-2-7b.ggmlv3.q4_0.bin'
    command: '/bin/sh /api/run.sh'

  llama-gpt-ui:
    image: 'ghcr.io/getumbrel/llama-gpt-ui:latest'
    ports:
      - 3000:3000
    restart: on-failure
    environment:
      - 'OPENAI_API_KEY=sk-XXXXXXXXXXXXXXXXXXXX'
      - 'OPENAI_API_HOST=http://llama-gpt-api-7b:8000'
      - 'DEFAULT_MODEL=/models/llama-2-7b-chat.bin'
      - 'WAIT_HOSTS=llama-gpt-api-7b:8000'
      - 'WAIT_TIMEOUT=3600'