local-rag-llamaindex/docker-compose.yml at master · Otman404/local-rag-llamaindex · 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
services:
  # Base image for the application
  # This image is used to build the other services
  # and contains the common dependencies
  base:
    build:
      context: .
      dockerfile: Dockerfile.base
    image: rag-base-image

  # FastAPI application
  api:
    build:
      context: .
      dockerfile: api/Dockerfile
    ports:
      - "8000:80"
    depends_on:
      - ollama
      - qdrant
      - base
    environment:
      - LLM_URL=http://ollama:11434
      - LLM_NAME=research_assistant
      - EMBEDDING_MODEL=sentence-transformers/all-mpnet-base-v2
      - QDRANT_URL=http://qdrant:6333
      - COLLECTION_NAME=researchpapers
      - CHUNK_SIZE=1024
    restart: always
    networks:
      - rag-network
    volumes:
      - ./api:/api

  # Data ingestion CLI tool
  data_ingestion:
    build:
      context: .
      dockerfile: data/Dockerfile
    profiles: ["data-ingest"]
    depends_on:
      - ollama
      - qdrant
    entrypoint: ["python", "data.py"]
    environment:
      - DATA_PATH=papers/
      - LLM_URL=http://ollama:11434
      - LLM_NAME=research_assistant
      - EMBEDDING_MODEL=sentence-transformers/all-mpnet-base-v2
      - QDRANT_URL=http://qdrant:6333
      - COLLECTION_NAME=researchpapers
      - CHUNK_SIZE=1024
    networks:
      - rag-network
    volumes:
      - ./papers:/app/papers
  # Qdrant vector database
  qdrant:
    image: qdrant/qdrant
    ports:
      - "6333:6333"
    volumes:
      - ~/qdrant_storage:/qdrant/storage:z
    networks:
      - rag-network

  # Ollama for LLM serving
  ollama:
    image: ollama/ollama:latest
    pull_policy: always
    container_name: ollama
    volumes:
      - ./ollama:/model_files
      - ./ollama:/root/.ollama
    tty: true
    entrypoint: ["/bin/sh", "./model_files/run_ollama.sh"]
    environment:
      - LLM_NAME=research_assistant
    restart: always
    extra_hosts:
      - host.docker.internal:host-gateway

    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    ports:
      - "11434:11434"
    networks:
      - rag-network

networks:
  rag-network:
    driver: bridge

volumes:
  qdrant_storage:
  ollama: