litellm/docker-compose.yml
Claude 8fefe3a28d
fix(docker): remove spurious backend service from compose split
The backend service at port 4001 was not part of LIT-2815 (UI/gateway
split) and duplicated gateway's config without serving a defined role.
Remove it so the compose file matches the two-service architecture
described in the ticket and PR.

Also trim the seven backend-specific test cases and the unused `import
os` from test_docker_compose.py; all 17 remaining checks still pass.

Resolves LIT-2815
2026-05-23 22:33:47 +00:00

86 lines
3.1 KiB
YAML

services:
ui:
build:
context: .
dockerfile: ui/Dockerfile
image: docker.litellm.ai/berriai/litellm-ui:main-stable
ports:
- "3000:3000" # Map the container port to the host, change the host port if necessary
healthcheck:
test: ["CMD-SHELL", "wget -qO- http://localhost:3000/healthz || exit 1"]
interval: 30s
timeout: 10s
retries: 3
start_period: 20s
gateway:
build:
context: .
dockerfile: gateway/Dockerfile
image: docker.litellm.ai/berriai/litellm-gateway:main-stable
#########################################
## Uncomment these lines to start proxy with a config.yaml file ##
# volumes:
# - ./config.yaml:/app/config.yaml
# command:
# - "--config=/app/config.yaml"
##############################################
ports:
- "4000:4000" # Map the container port to the host, change the host port if necessary
environment:
DATABASE_URL: "postgresql://llmproxy:dbpassword9090@db:5432/litellm"
# Optional: route read-only queries (find_*, count, group_by, query_raw/_first)
# to a separate reader endpoint, e.g. an Aurora reader. Leave unset for
# single-DB deployments. With IAM_TOKEN_DB_AUTH enabled, the reader URL
# is auto-refreshed alongside the writer.
# DATABASE_URL_READ_REPLICA: "postgresql://llmproxy:dbpassword9090@db-reader:5432/litellm"
STORE_MODEL_IN_DB: "True" # allows adding models to proxy via UI
env_file:
- .env # Load local .env file
depends_on:
- db # Indicates that this service depends on the 'db' service, ensuring 'db' starts first
healthcheck: # Defines the health check configuration for the container
test:
- CMD-SHELL
- python3 -c "import urllib.request; urllib.request.urlopen('http://localhost:4000/health/liveliness')" # Command to execute for health check
interval: 30s # Perform health check every 30 seconds
timeout: 10s # Health check command times out after 10 seconds
retries: 3 # Retry up to 3 times if health check fails
start_period: 40s # Wait 40 seconds after container start before beginning health checks
db:
image: postgres:16
restart: always
container_name: litellm_db
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:
test: ["CMD-SHELL", "pg_isready -d litellm -U llmproxy"]
interval: 1s
timeout: 5s
retries: 10
prometheus:
image: prom/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: always
volumes:
prometheus_data:
driver: local
postgres_data:
name: litellm_postgres_data # Named volume for Postgres data persistence