-
Notifications
You must be signed in to change notification settings - Fork 3
Expand file tree
/
Copy pathdocker-compose.yml
More file actions
78 lines (73 loc) · 2.28 KB
/
docker-compose.yml
File metadata and controls
78 lines (73 loc) · 2.28 KB
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
services:
# Ollama LLM serving with GPU support
ollama:
image: ollama/ollama:latest
container_name: hedit-ollama
volumes:
- ollama_data:/root/.ollama
- ./docker/ollama-entrypoint.sh:/entrypoint.sh
ports:
- "11435:11434"
entrypoint: ["/bin/bash", "/entrypoint.sh"]
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]
restart: unless-stopped
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:11434/api/tags"]
interval: 30s
timeout: 10s
retries: 3
start_period: 120s
# HEDit API service
hedit:
build:
context: .
dockerfile: Dockerfile
container_name: hedit-api
depends_on:
- ollama
volumes:
- feedback_data:/app/feedback
- telemetry_data:/app/telemetry
environment:
# LLM Provider Configuration
- LLM_PROVIDER=${LLM_PROVIDER:-ollama}
# OpenRouter Configuration (used when LLM_PROVIDER=openrouter)
- OPENROUTER_API_KEY=${OPENROUTER_API_KEY}
- LLM_PROVIDER_PREFERENCE=${LLM_PROVIDER_PREFERENCE}
- ANNOTATION_MODEL=${ANNOTATION_MODEL:-openai/gpt-oss-120b}
- EVALUATION_MODEL=${EVALUATION_MODEL:-qwen/qwen3-235b-a22b-2507}
- ASSESSMENT_MODEL=${ASSESSMENT_MODEL:-openai/gpt-oss-120b}
- FEEDBACK_MODEL=${FEEDBACK_MODEL:-openai/gpt-oss-120b}
# Ollama Configuration (used when LLM_PROVIDER=ollama)
- LLM_BASE_URL=${LLM_BASE_URL:-http://ollama:11434}
- LLM_MODEL=${LLM_MODEL:-gpt-oss:20b}
- LLM_TEMPERATURE=${LLM_TEMPERATURE:-0.1}
- OLLAMA_HOST=http://ollama:11434
# HED Configuration
- HED_SCHEMA_VERSION=${HED_SCHEMA_VERSION:-8.4.0}
- USE_JS_VALIDATOR=${USE_JS_VALIDATOR:-true}
# HED paths are set in Dockerfile, override here if needed
# - HED_SCHEMA_DIR=/app/hed-schemas/schemas_latest_json
# - HED_VALIDATOR_PATH=/app/hed-javascript
ports:
- "38427:38427"
restart: unless-stopped
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:38427/health"]
interval: 30s
timeout: 10s
retries: 3
start_period: 10s
volumes:
ollama_data:
driver: local
feedback_data:
driver: local
telemetry_data:
driver: local