finrag-id/docker-compose.yml at main · KennyUMN/finrag-id · 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
services:
  qdrant:
    image: qdrant/qdrant:v1.11.3
    container_name: finrag-qdrant
    restart: unless-stopped
    ports:
      - "6333:6333"
      - "6334:6334"
    volumes:
      - ./qdrant_storage:/qdrant/storage
    healthcheck:
      test: ["CMD-SHELL", "bash -c '</dev/tcp/localhost/6333'"]
      interval: 10s
      timeout: 5s
      retries: 6

  ollama:
    image: ollama/ollama:latest
    container_name: finrag-ollama
    restart: unless-stopped
    ports:
      - "11434:11434"
    volumes:
      - ./ollama_data:/root/.ollama
    # Uncomment for GPU passthrough on Linux host w/ NVIDIA Container Toolkit:
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: all
    #           capabilities: [gpu]

  api:
    build: .
    container_name: finrag-api
    restart: unless-stopped
    depends_on:
      qdrant:
        condition: service_healthy
      ollama:
        condition: service_started
    env_file: .env
    environment:
      QDRANT_HOST: qdrant
      OLLAMA_BASE_URL: http://ollama:11434
    ports:
      - "8000:8000"
    volumes:
      - ./data/pdfs:/app/data/pdfs
      - ./qdrant_storage:/app/qdrant_storage
      - ./eval_results:/app/eval_results

  ui:
    build: .
    container_name: finrag-ui
    restart: unless-stopped
    depends_on:
      - api
    env_file: .env
    environment:
      QDRANT_HOST: qdrant
      OLLAMA_BASE_URL: http://ollama:11434
    command: >
      streamlit run app/streamlit_app.py
      --server.port=8501
      --server.address=0.0.0.0
      --server.headless=true
    ports:
      - "8501:8501"

volumes:
  qdrant_storage:
  ollama_data: