Deploy NeMo Auditor Using Docker Compose#
You can deploy the NeMo Auditor microservice using Docker Compose for local development, testing, and quickstart scenarios. This deployment method provides a simple way to get Data Designer running quickly without complex Kubernetes configurations.
Prerequisites#
Docker and Docker Compose installed on your system
NGC API Key for accessing NGC Catalog
At least 4GB of available RAM
Sufficient disk space for generated artifacts (recommended: 10GB+)
Access to LLM endpoints (NVIDIA API, local NIM, or other compatible endpoints)
Procedure#
Set up environment variables:
export NGC_CLI_API_KEY="<your-ngc-api-key>" export NIM_API_KEY="<your-nvidia-api-key>" # Optional, for accessing models from build.nvidia.com.
Log in to NVIDIA NGC container registry:
docker login nvcr.io -u '$oauthtoken' -p $NGC_CLI_API_KEY
Create a file, such as
docker-compose.yml
, with contents like the following example:services: app: image: nvcr.io/nvidia/nemo-microservices/auditor:25.08 environment: - POSTGRES_URI=postgresql://nemo:nemo@postgres:5432/auditor - NIM_API_KEY - REST_API_KEY - OPENAI_API_KEY - OPENAICOMPATIBLE_API_KEY ports: - 127.0.0.1:5000:5000 depends_on: postgres: condition: service_healthy postgres: image: postgres:16.2 restart: always environment: - POSTGRES_USER=nemo - POSTGRES_PASSWORD=nemo - POSTGRES_DB=auditor - POSTGRES_PORT=5432 ports: - 127.0.0.1:5432:5432 healthcheck: test: ["CMD-SHELL", "sh -c 'pg_isready -U nemo -d auditor'"] interval: 10s timeout: 3s retries: 3
Start NeMo Auditor:
docker compose up
The command starts the Auditor microservice on port
5000
and an instance of PostgreSQL for persistent storage of targets and configs.
Verifying the Deployment#
After starting the services, verify everything is working:
Check service status:
$ docker compose ps
Set
AUDITOR_BASE_URL
:$ export AUDITOR_BASE_URL=http://localhost:5000
Test the readiness endpoint:
$ curl "${AUDITOR_BASE_URL}/health/ready
Read the API documentation by accessing http://localhost:5000/docs in your browser.
Stopping the Service#
To stop the microservice:
docker compose down
Next Steps#
Refer to Typical Audit Workflow to get started.