RAG_CHATBOT/docker-compose.yml at main · Technocrat-dev/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
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
# NeuralRAG - Docker Compose Configuration
# Complete stack: Frontend, Backend, Ollama LLM

services:
  # =========================================
  # Backend - FastAPI RAG Server
  # =========================================
  backend:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: neuralrag-backend
    ports:
      - "8000:8000"
    volumes:
      # Persist vector database and uploads
      - chroma_data:/app/chroma_db
      - upload_data:/app/data
    environment:
      - RAG_DATA_DIR=/app/data
      - RAG_CHROMA_DIR=/app/chroma_db
      - RAG_LLM_MODEL=${RAG_LLM_MODEL:-llama3}
      - RAG_VISION_MODEL=${RAG_VISION_MODEL:-llava}
      - RAG_EMBED_MODEL=${RAG_EMBED_MODEL:-all-mpnet-base-v2}
      # Point to Ollama container
      - OLLAMA_HOST=http://ollama:11434
    depends_on:
      ollama:
        condition: service_healthy
    healthcheck:
      test: [ "CMD", "curl", "-f", "http://localhost:8000/health" ]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s
    networks:
      - neuralrag-network
    restart: unless-stopped

  # =========================================
  # Frontend - Next.js Web Interface
  # =========================================
  frontend:
    build:
      context: ./rag-frontend
      dockerfile: Dockerfile
    container_name: neuralrag-frontend
    ports:
      - "3000:3000"
    environment:
      # Point to backend container
      - RAG_BACKEND_URL=http://backend:8000
    depends_on:
      backend:
        condition: service_healthy
    networks:
      - neuralrag-network
    restart: unless-stopped

  # =========================================
  # Ollama - Local LLM Service
  # =========================================
  ollama:
    image: ollama/ollama:latest
    container_name: neuralrag-ollama
    ports:
      - "11434:11434"
    volumes:
      - ollama_models:/root/.ollama
    # Uncomment for GPU support (NVIDIA):
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: all
    #           capabilities: [gpu]
    healthcheck:
      test: [ "CMD", "curl", "-f", "http://localhost:11434/api/tags" ]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    networks:
      - neuralrag-network
    restart: unless-stopped

  # =========================================
  # Init - Pull required Ollama models
  # =========================================
  init:
    image: curlimages/curl:latest
    container_name: neuralrag-init
    depends_on:
      ollama:
        condition: service_healthy
    entrypoint: [ "/bin/sh", "-c" ]
    command:
      - |
        echo "Pulling LLM models..."
        curl -X POST http://ollama:11434/api/pull -d '{"name": "llama3"}'
        echo ""
        echo "Pulling Vision model..."
        curl -X POST http://ollama:11434/api/pull -d '{"name": "llava"}'
        echo ""
        echo "Model setup complete!"
    networks:
      - neuralrag-network

# =========================================
# Volumes - Persistent data storage
# =========================================
volumes:
  chroma_data:
    name: neuralrag-chroma
  upload_data:
    name: neuralrag-uploads
  ollama_models:
    name: neuralrag-ollama-models

# =========================================
# Network - Internal communication
# =========================================
networks:
  neuralrag-network:
    name: neuralrag-network
    driver: bridge