prellm/docker-compose.yaml at main · wronai/prellm · 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
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
version: '3.8'

# ─────────────────────────────────────────────
# preLLM — zero-config deployment
# ─────────────────────────────────────────────
# 1. cp .env.example .env
# 2. Fill in your API keys (OPENAI_API_KEY, ANTHROPIC_API_KEY, etc.)
# 3. docker-compose up -d

services:
  # ─────────────────────────────────────────────
  # preLLM API Server
  # ─────────────────────────────────────────────
  prellm:
    build: .
    image: prellm/prellm:latest
    ports:
      - "${PRELLM_PORT:-8080}:8080"
    env_file:
      - .env
    environment:
      # Override Ollama base to point to the container
      - OLLAMA_API_BASE=http://ollama:11434
    volumes:
      - ./configs:/app/configs:ro
    command: ["serve", "--host", "0.0.0.0", "--port", "8080"]
    depends_on:
      - ollama
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 3

  # ─────────────────────────────────────────────
  # Ollama (local small LLM — no API key needed)
  # ─────────────────────────────────────────────
  ollama:
    image: ollama/ollama:latest
    ports:
      - "11434:11434"
    volumes:
      - ollama_models:/root/.ollama
    environment:
      - OLLAMA_HOST=0.0.0.0
    restart: unless-stopped

  # ─────────────────────────────────────────────
  # Pull default small model on first startup
  # ─────────────────────────────────────────────
  ollama-pull:
    image: ollama/ollama:latest
    depends_on:
      - ollama
    entrypoint: >
      sh -c "sleep 5 && ollama pull qwen2.5:3b"
    environment:
      - OLLAMA_HOST=ollama:11434
    restart: "no"

volumes:
  ollama_models: