alvis
c43dbaf23d
Logs one MLflow run per /recommend (params, token metrics, latency,
full prompt + tip as artifacts) and per /agents/{id}/compute and
/infer call (signals snapshot, inferred prefs, latency).
Tracing is a no-op when MLFLOW_TRACKING_URI is unset; ml-serving
starts and serves tips correctly without MLflow configured.
Refs #118 (M4: remove from production / move off critical path).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
130 lines
4.3 KiB
YAML
130 lines
4.3 KiB
YAML
name: oo
|
|
|
|
services:
|
|
# ── core profile ──────────────────────────────────────────────────────────
|
|
|
|
api:
|
|
build:
|
|
context: ../..
|
|
dockerfile: infra/docker/Dockerfile.api
|
|
profiles: [core, full]
|
|
env_file: ../../.env.local
|
|
environment:
|
|
NODE_ENV: production
|
|
ML_SERVING_URL: "http://ml-serving:8000"
|
|
MLFLOW_URL: "http://mlflow:5000"
|
|
INTERNAL_API_TOKEN: "${INTERNAL_API_TOKEN:-}"
|
|
volumes:
|
|
- /mnt/ssd/dbs/oo:/mnt/ssd/dbs/oo
|
|
ports:
|
|
- "127.0.0.1:3078:3078"
|
|
healthcheck:
|
|
test: ["CMD", "node", "-e", "fetch('http://localhost:3078/health').then(r=>process.exit(r.ok?0:1)).catch(()=>process.exit(1))"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
|
|
web:
|
|
build:
|
|
context: ../..
|
|
dockerfile: infra/docker/Dockerfile.web
|
|
profiles: [core, full]
|
|
env_file: ../../.env.local
|
|
environment:
|
|
NODE_ENV: production
|
|
PORT: "3079"
|
|
HOSTNAME: "0.0.0.0"
|
|
NEXT_PUBLIC_API_URL: "" # Caddy routes /api/* directly to the API in prod
|
|
ports:
|
|
- "127.0.0.1:3079:3079"
|
|
depends_on:
|
|
api:
|
|
condition: service_healthy
|
|
|
|
admin:
|
|
build:
|
|
context: ../..
|
|
dockerfile: infra/docker/Dockerfile.admin
|
|
profiles: [core, full]
|
|
env_file: ../../.env.local
|
|
environment:
|
|
NODE_ENV: production
|
|
PORT: "3080"
|
|
HOSTNAME: "0.0.0.0"
|
|
NEXT_PUBLIC_API_URL: ""
|
|
NEXT_PUBLIC_MLFLOW_URL: "/mlflow"
|
|
INTERNAL_API_URL: "http://api:3078"
|
|
ports:
|
|
- "127.0.0.1:3080:3080"
|
|
depends_on:
|
|
api:
|
|
condition: service_healthy
|
|
|
|
# ── full profile ──────────────────────────────────────────────────────────
|
|
|
|
ml-serving:
|
|
build:
|
|
context: ../..
|
|
dockerfile: infra/docker/Dockerfile.ml
|
|
profiles: [full]
|
|
env_file: ../../.env.local
|
|
environment:
|
|
LITELLM_URL: ${LITELLM_URL:-http://host.docker.internal:4000}
|
|
OLLAMA_URL: ${OLLAMA_URL:-http://host.docker.internal:11434}
|
|
MLFLOW_TRACKING_URI: ${MLFLOW_TRACKING_URI:-}
|
|
extra_hosts:
|
|
- "host.docker.internal:host-gateway"
|
|
ports:
|
|
- "127.0.0.1:8000:8000"
|
|
healthcheck:
|
|
test: ["CMD", "python", "-c", "import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://localhost:8000/health',timeout=3).status==200 else 1)"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
|
|
# ── mlops profile — MLflow ────────────────────────────────────────────────
|
|
# Start: docker compose --profile mlops up
|
|
# MLflow UI: http://localhost:5000 or https://o.alogins.net/mlflow
|
|
|
|
# ── events profile — NATS JetStream ─────────────────────────────────────
|
|
# Start: docker compose --profile events up
|
|
# NATS monitoring: http://localhost:8222
|
|
# Enable in the API by setting NATS_URL=nats://nats:4222 in .env.local
|
|
|
|
nats:
|
|
image: nats:2.10-alpine
|
|
profiles: [events, full]
|
|
command: ["-js", "-sd", "/data", "-m", "8222"]
|
|
volumes:
|
|
- /mnt/ssd/dbs/oo/nats:/data
|
|
ports:
|
|
- "127.0.0.1:4222:4222" # client connections
|
|
- "127.0.0.1:8222:8222" # HTTP monitoring
|
|
healthcheck:
|
|
test: ["CMD", "wget", "--spider", "-q", "http://localhost:8222/healthz"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
|
|
mlflow:
|
|
image: ghcr.io/mlflow/mlflow:v3.11.1
|
|
profiles: [mlops]
|
|
command: >
|
|
mlflow server
|
|
--backend-store-uri sqlite:////mlflow/mlflow.db
|
|
--default-artifact-root /mlflow/artifacts
|
|
--host 0.0.0.0
|
|
--port 5000
|
|
--static-prefix /mlflow
|
|
--allowed-hosts o.alogins.net,localhost
|
|
--cors-allowed-origins https://o.alogins.net
|
|
volumes:
|
|
- /mnt/ssd/dbs/oo/mlflow:/mlflow
|
|
ports:
|
|
- "127.0.0.1:5000:5000"
|
|
healthcheck:
|
|
test: ["CMD", "python", "-c", "import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://localhost:5000/mlflow/health',timeout=3).status==200 else 1)"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|