OpenCortex/docker-compose.yml at master · StardustVision/OpenCortex · 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
services:
  qdrant:
    image: qdrant/qdrant:v1.17.1
    container_name: opencortex-qdrant
    ports:
      - "6333:6333"
      - "6334:6334"
    volumes:
      - ./.cortex/qdrant:/qdrant/storage
    restart: unless-stopped

  vllm-embedding:
    image: ${VLLM_IMAGE:-vllm/vllm-openai-cpu:latest-x86_64}
    container_name: opencortex-vllm-embedding
    ports:
      - "18081:8000"
    environment:
      - HUGGING_FACE_HUB_TOKEN=${HUGGING_FACE_HUB_TOKEN:-}
      - HTTP_PROXY=${HTTP_PROXY:-}
      - HTTPS_PROXY=${HTTPS_PROXY:-}
      - NO_PROXY=${NO_PROXY:-localhost,127.0.0.1,qdrant,opencortex,vllm-embedding,vllm-reranker}
    command:
      - ${VLLM_EMBEDDING_MODEL:-Qwen/Qwen3-Embedding-0.6B}
      - --served-model-name
      - ${VLLM_EMBEDDING_MODEL_ALIAS:-qwen3-embedding-0.6b}
      - --host
      - 0.0.0.0
      - --port
      - "8000"
      - --dtype
      - auto
      - --gpu-memory-utilization
      - ${VLLM_EMBEDDING_MEMORY_UTILIZATION:-0.35}
      - --max-model-len
      - ${VLLM_EMBEDDING_MAX_MODEL_LEN:-8192}
    volumes:
      - ./.cache/huggingface:/root/.cache/huggingface
    restart: unless-stopped

  vllm-reranker:
    image: ${VLLM_IMAGE:-vllm/vllm-openai-cpu:latest-x86_64}
    container_name: opencortex-vllm-reranker
    ports:
      - "18082:8000"
    environment:
      - HUGGING_FACE_HUB_TOKEN=${HUGGING_FACE_HUB_TOKEN:-}
      - HTTP_PROXY=${HTTP_PROXY:-}
      - HTTPS_PROXY=${HTTPS_PROXY:-}
      - NO_PROXY=${NO_PROXY:-localhost,127.0.0.1,qdrant,opencortex,vllm-embedding,vllm-reranker}
    command:
      - ${VLLM_RERANK_MODEL:-Qwen/Qwen3-Reranker-0.6B}
      - --served-model-name
      - ${VLLM_RERANK_MODEL_ALIAS:-qwen3-reranker-0.6b}
      - --host
      - 0.0.0.0
      - --port
      - "8000"
      - --dtype
      - auto
      - --gpu-memory-utilization
      - ${VLLM_RERANK_MEMORY_UTILIZATION:-0.35}
      - --max-model-len
      - ${VLLM_RERANK_MAX_MODEL_LEN:-8192}
    volumes:
      - ./.cache/huggingface:/root/.cache/huggingface
    restart: unless-stopped

  opencortex:
    build: .
    container_name: opencortex-server
    ports:
      - "8921:8921"
    depends_on:
      - qdrant
    volumes:
      - ./.cortex:/data
    environment:
      # ---- Server ----
      - OPENCORTEX_APP_APP_NAME=OpenCortex
      # ---- Storage ----
      - OPENCORTEX_APP_DATA_ROOT=/data
      - OPENCORTEX_APP_QDRANT_URL=http://qdrant:6333
      - OPENCORTEX_APP_QDRANT_API_KEY=${QDRANT_API_KEY:-}
      - OPENCORTEX_APP_QDRANT_TIMEOUT=${OPENCORTEX_APP_QDRANT_TIMEOUT:-30}
      # ---- Embedding: vLLM OpenAI-compatible /v1/embeddings ----
      - OPENCORTEX_APP_VECTOR_DIMENSION=${VLLM_EMBEDDING_DIMENSION:-1024}
      - OPENCORTEX_APP_EMBEDDING_MODEL=${VLLM_EMBEDDING_MODEL_ALIAS:-qwen3-embedding-0.6b}
      - OPENCORTEX_APP_EMBEDDING_API_KEY=${VLLM_API_KEY:-opencortex-local}
      - OPENCORTEX_APP_EMBEDDING_API_BASE=${OPENCORTEX_APP_EMBEDDING_API_BASE:-http://vllm-embedding:8000/v1}
      # ---- LLM (required for insights generation) ----
      - OPENCORTEX_APP_LLM_MODEL=${OPENCORTEX_APP_LLM_MODEL:-gpt-4o-mini}
      - OPENCORTEX_APP_LLM_API_KEY=${OPENCORTEX_APP_LLM_API_KEY:-}
      - OPENCORTEX_APP_LLM_API_BASE=${OPENCORTEX_APP_LLM_API_BASE:-https://api.openai.com/v1}
      - OPENCORTEX_APP_LLM_API_STYLE=${OPENCORTEX_APP_LLM_API_STYLE:-openai}
      # ---- Rerank ----
      - OPENCORTEX_APP_RETRIEVAL_RERANK_ENABLED=${OPENCORTEX_APP_RETRIEVAL_RERANK_ENABLED:-true}
      - OPENCORTEX_APP_RETRIEVAL_RERANK_PROVIDER=${OPENCORTEX_APP_RETRIEVAL_RERANK_PROVIDER:-hosted_vllm}
      - OPENCORTEX_APP_RETRIEVAL_RERANK_MODEL=${VLLM_RERANK_MODEL_ALIAS:-qwen3-reranker-0.6b}
      - OPENCORTEX_APP_RETRIEVAL_RERANK_API_KEY=${VLLM_API_KEY:-opencortex-local}
      - OPENCORTEX_APP_RETRIEVAL_RERANK_API_BASE=${OPENCORTEX_APP_RETRIEVAL_RERANK_API_BASE:-http://vllm-reranker:8000/v1}
      - OPENCORTEX_APP_RETRIEVAL_RERANK_SEED_LIMIT=${OPENCORTEX_APP_RETRIEVAL_RERANK_SEED_LIMIT:-30}
      - OPENCORTEX_APP_RETRIEVAL_RERANK_FINAL_LIMIT=${OPENCORTEX_APP_RETRIEVAL_RERANK_FINAL_LIMIT:-30}
      # ---- Auth ----
      - OPENCORTEX_APP_ADMIN_API_TOKEN=${OPENCORTEX_APP_ADMIN_API_TOKEN:-}
    restart: unless-stopped

  opencortex-web:
    build: ./web
    container_name: opencortex-web
    ports:
      - "8080:80"
    depends_on:
      - opencortex
    restart: unless-stopped