-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathdocker-compose.yml
More file actions
157 lines (145 loc) · 3.88 KB
/
docker-compose.yml
File metadata and controls
157 lines (145 loc) · 3.88 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
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
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
#version: "3.11"
#
services:
proxy:
build:
context: .
args:
target: runtime
image: ghcr.io/berriai/litellm:main-stable
restart: unless-stopped
container_name: litellm
ports:
- "4000:4000"
env_file:
- .env
volumes:
- ./litellm_config.yaml:/app/config.yaml
- ./proxy_config.yaml:/app/litellm/proxy/proxy_config.yaml
- /home/lukas/ai_stack/wget/src/wget2:/bin/wget:ro
command:
- "--config=/app/config.yaml"
- "--drop_params"
depends_on:
- db
healthcheck:
test: [ "CMD-SHELL", "wget --no-verbose --tries=1 http://localhost:4000/health/liveliness || exit 1" ]
interval: 30s
timeout: 10s
retries: 3
start_period: 40s
db:
image: postgres:16
restart: unless-stopped
container_name: litellm_postgres
environment:
POSTGRES_DB: litellm
POSTGRES_USER: llmproxy
POSTGRES_PASSWORD: dbpassword9090
ports:
- "5432:5432"
volumes:
- postgres_data:/var/lib/postgresql/data # Persists Postgres data across container restarts
# healthcheck: #this always fail because there is no wget
# test: ["CMD-SHELL", "pg_isready -d litellm -U llmproxy"]
# interval: 1s
# timeout: 5s
# retries: 10
# prometheus:
# image: prom/prometheus
# container_name: litellm_prometheus
# volumes:
# - prometheus_data:/prometheus
# - ./prometheus.yml:/etc/prometheus/prometheus.yml
# ports:
# - "9090:9090"
# command:
# - "--config.file=/etc/prometheus/prometheus.yml"
# - "--storage.tsdb.path=/prometheus"
# - "--storage.tsdb.retention.time=15d"
# restart: unless-stopped
open-webui:
image: ghcr.io/open-webui/open-webui:main
container_name: open-webui
restart: unless-stopped
ports:
- "3000:8080"
volumes:
- ./data/open-webui:/app/backend/data
ollama:
image: docker.io/ollama/ollama:latest
ports:
- 11434:11434
volumes:
- ./ollama/code:/code
- ./ollama/ollama:/root/.ollama
container_name: ollama
pull_policy: always
tty: true
restart: unless-stopped
environment:
#- OLLAMA_KEEP_ALIVE=24h
- OLLAMA_HOST=0.0.0.0
- OLLAMA_VULKAN=1
# Add device access for AMD/Intel GPUs
devices:
- /dev/dri:/dev/dri
group_add:
- video
#- render
# deploy:
# resources:
# reservations:
# devices:
# # NVIDIA GPUs
# - driver: nvidia
# count: all
# capabilities: [gpu]
#
# # AMD GPUs
# - driver: amd
# count: all
# capabilities: [gpu]
#
# # Intel GPUs
# - driver: intel
# count: all
# capabilities: [gpu]
qdrant:
image: qdrant/qdrant:latest
restart: unless-stopped
container_name: qdrant
ports:
- 6333:6333
- 6334:6334
expose:
- 6333
- 6334
- 6335
configs:
- source: qdrant_config
target: /qdrant/config/production.yaml
volumes:
- ./qdrant_data:/qdrant/storage
chromadb:
image: chromadb/chroma
container_name: chromadb
volumes:
- chroma_data:/data
ports:
- "8001:8000"
#networks:
#- chroma_network
#environment:
# - CHROMA_OPEN_TELEMETRY__ENDPOINT=http://otel-collector:4317/
# - CHROMA_OPEN_TELEMETRY__SERVICE_NAME=chroma
restart: unless-stopped
configs:
qdrant_config:
content: |
log_level: INFO
volumes:
postgres_data:
name: litellm_postgres_data
chroma_data:
driver: local