PeterBot/compose.sidecar.yml at main · Computer-Hardware-Club/PeterBot · 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
47
48
services:
  llama-cpp:
    image: ghcr.io/ggml-org/llama.cpp:server
    command:
      - --model
      - /models/peterbot.gguf
      - --alias
      - peterbot-gguf
      - --host
      - 0.0.0.0
      - --port
      - "8080"
      - --ctx-size
      - "4096"
      - --batch-size
      - "512"
      - --parallel
      - "1"
      - --cont-batching
    restart: unless-stopped
    volumes:
      - ./models:/models:ro
    ports:
      - "8080:8080"

  peterbot:
    build:
      context: .
      target: bot
    depends_on:
      - llama-cpp
    env_file:
      - path: ./.env
        required: false
    volumes:
      - ./docker/config.sidecar.json:/app/config.json:ro
      - ./peterbot-data:/app/peterbot-data
    healthcheck:
      test:
        - CMD
        - python3
        - -c
        - import socket; socket.create_connection(("llama-cpp", 8080), 2).close()
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 15s
    restart: unless-stopped