Drift/docker-compose.yml at main · muneeb-anjum0/Drift · 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
name: Drift

services:
  frontend:
    container_name: drift-frontend
    build:
      context: .
      dockerfile: client/Dockerfile
      args:
        VITE_API_BASE_URL: /api/v1
        VITE_DRIFT_MODEL_LABEL: ${VITE_DRIFT_MODEL_LABEL:-Qwen2.5-7B + DriftLedger LoRA (GGUF Q4_K_M)}
    depends_on:
      backend:
        condition: service_started
    ports:
      - "5173:80"
    restart: unless-stopped

  backend:
    container_name: drift-backend
    build:
      context: .
      dockerfile: server-go/Dockerfile
    environment:
      APP_ENV: production
      PORT: 5000
      MONGO_URI: mongodb://db:27017
      MONGO_DATABASE: driftledger
      JWT_SECRET: ${JWT_SECRET:-replace_with_strong_secret}
      JWT_EXPIRES_IN_HOURS: ${JWT_EXPIRES_IN_HOURS:-168}
      CLIENT_URL: http://localhost:5173
      DRIFT_INFERENCE_ENABLED: "true"
      DRIFT_INFERENCE_URL: http://inference:8000
      DRIFT_INFERENCE_TIMEOUT_MS: ${DRIFT_INFERENCE_TIMEOUT_MS:-65000}
      DRIFT_RELEVANCE_THRESHOLD: ${DRIFT_RELEVANCE_THRESHOLD:-0.25}
      DRIFT_MAX_ANALYZED_REQUIREMENTS: ${DRIFT_MAX_ANALYZED_REQUIREMENTS:-3}
      FIREBASE_STORAGE_ENABLED: ${FIREBASE_STORAGE_ENABLED:-false}
      FIREBASE_STORAGE_BUCKET: ${FIREBASE_STORAGE_BUCKET:-}
      GOOGLE_APPLICATION_CREDENTIALS: ${GOOGLE_APPLICATION_CREDENTIALS:-}
      MAX_UPLOAD_SIZE_MB: ${MAX_UPLOAD_SIZE_MB:-10}
      DRIFT_EVALUATION_REPORT_DIR: /app/reports/evaluation
    volumes:
      - ./reports:/app/reports
    depends_on:
      db:
        condition: service_started
      inference:
        condition: service_started
      llama:
        condition: service_started
    ports:
      - "5000:5000"
    restart: unless-stopped

  inference:
    container_name: drift-inference
    build:
      context: .
      dockerfile: services/inference/Dockerfile
    environment:
      DRIFT_MODEL_MODE: local
      DRIFT_LOCAL_ENGINE: ${DRIFT_LOCAL_ENGINE:-gguf}
      DRIFT_ADAPTER_ZIP_PATH: /app/models/adapters/DriftLedger_v5_qwen2.5_7b_LoRA.zip
      DRIFT_ADAPTER_DIR: /app/models/adapters/DriftLedger_v5_qwen2.5_7b_LoRA
      DRIFT_GGUF_MODEL_PATH: ${DRIFT_GGUF_MODEL_PATH:-/app/models/gguf/DriftLedger-Qwen2.5-7B-Q4_K_M.gguf}
      DRIFT_LLAMA_SERVER_URL: http://llama:8080
      DRIFT_LLAMA_CTX_SIZE: ${DRIFT_LLAMA_CTX_SIZE:-768}
      DRIFT_LLAMA_GPU_LAYERS: ${DRIFT_LLAMA_GPU_LAYERS:-0}
      DRIFT_LLAMA_THREADS: ${DRIFT_LLAMA_THREADS:-6}
      DRIFT_LLAMA_MAX_TOKENS: ${DRIFT_LLAMA_MAX_TOKENS:-120}
      DRIFT_MAX_NEW_TOKENS: ${DRIFT_MAX_NEW_TOKENS:-224}
      DRIFT_ALLOW_CPU: ${DRIFT_ALLOW_CPU:-false}
    volumes:
      - ./models:/app/models
    ports:
      - "127.0.0.1:8000:8000"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    restart: unless-stopped

  llama:
    image: ghcr.io/ggml-org/llama.cpp:full-cuda
    container_name: drift-llama
    command:
      - --server
      - --model
      - ${DRIFT_GGUF_MODEL_PATH:-/app/models/gguf/DriftLedger-Qwen2.5-7B-Q4_K_M.gguf}
      - --host
      - 0.0.0.0
      - --port
      - "8080"
      - --ctx-size
      - ${DRIFT_LLAMA_CTX_SIZE:-768}
      - --n-gpu-layers
      - ${DRIFT_LLAMA_GPU_LAYERS:-0}
      - --threads
      - ${DRIFT_LLAMA_THREADS:-6}
    volumes:
      - ./models:/app/models
    ports:
      - "127.0.0.1:8080:8080"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    restart: unless-stopped

  db:
    image: mongo:7
    container_name: drift-db
    volumes:
      - mongo-data:/data/db
    ports:
      - "127.0.0.1:27017:27017"
    restart: unless-stopped

volumes:
  mongo-data: