rag-chatbot/docker-compose.metal.yml at main · umbertogriffo/rag-chatbot · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
# Docker Compose override for CPU-only deployment
# To use this file: docker compose -f docker-compose.metal.yml up

services:
  llama-server:
    # Use CPU-only image
    # TODO: load the image tag from an environment variable or .env file
    # https://docs.docker.com/compose/how-tos/environment-variables/variable-interpolation/
    image: ghcr.io/ggml-org/llama.cpp:server-b9501
    container_name: rag-chatbot-llama-server
    volumes:
      - ./models:/models
    ports:
      - "8080:8080"
    environment: {}
    command: >
      --models-dir /models
      --host 0.0.0.0
      --port 8080
      --cache-type-k q8_0
      --cache-type-v q8_0
      --flash-attn on
      --ctx-size 4096
    deploy:
      resources:
        limits:
          cpus: '4'
          memory: 8G
        reservations: {}

    networks:
      - service-network

    healthcheck:
      test: [ "CMD", "curl", "-f", "http://localhost:8080/health" ]
      interval: 10s
      timeout: 10s
      retries: 5
      start_period: 15s

networks:
  service-network:
    driver: bridge

volumes:
  models: