pluto
74e12eca60
FastAPI service that loads ViT-L-14 model and exposes /embed, /similarity, and /batch-similarity endpoints. Runs on RTX 3090 with NVIDIA GPU reservation. Includes 9 cosine similarity tests. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
28 lines
602 B
YAML
28 lines
602 B
YAML
services:
|
|
clip-service:
|
|
build: .
|
|
container_name: clip-service
|
|
restart: unless-stopped
|
|
ports:
|
|
- "5200:5200"
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: 1
|
|
capabilities: [gpu]
|
|
mem_limit: 4G
|
|
memswap_limit: 4G
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "curl -sf http://localhost:5200/health || exit 1"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 120s
|
|
logging:
|
|
driver: "json-file"
|
|
options:
|
|
max-size: "50m"
|
|
max-file: "3"
|