litellm/docker-compose.yml
mateo-berri 6378f9b470
chore: clean up repo root, first safe slice of the src layout migration
Remove files that should never have been at the root: a stale litellm-1.79.1
sdist under dist/ (now gitignored), qa_sticky_session.sh which leaked in with
an unrelated commit, and the dead flake8 toolchain (.flake8 plus the dev
dependency; ruff replaced it and nothing invokes it), along with the unused
[tool.isort] section in pyproject.toml

Fold ruff.toml into pyproject.toml [tool.ruff], move codecov.yaml to .github/
and prometheus.yml to docker/, and merge the two divergent license_cache.json
copies into tests/code_coverage_tests/ with the cache path resolved relative
to check_licenses.py instead of the CWD, which is what created the duplicate
in the first place
2026-07-02 18:32:43 +00:00

73 lines
2.7 KiB
YAML

services:
litellm:
build:
context: .
args:
target: runtime
image: docker.litellm.ai/berriai/litellm: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
- ./docker/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