Shield360

To send OpenTelemetry metrics and traces generated by Shield360 from your AI Application to the Shield360 Platform, follow the below steps.

1. Get your Credentials

If you haven’t deployed the Shield360 Platform yet, follow the Installation Guide to set it up.

Common Shield360 Platform endpoints:

• Kubernetes cluster: http://shield360.shield360.svc.cluster.local:4318
• Local development: http://localhost:4318 (using port-forward)
• External/Ingress: Your configured external endpoint

2. Instrument your application

SDK

For direct integration into your Python applications:

Function Arguments

import shield360

shield360.init(
  otlp_endpoint="http://localhost:4318"
)

Replace http://localhost:4318 with your Shield360 Platform endpoint:

• Local development: http://localhost:4318
• Kubernetes cluster: http://shield360.shield360.svc.cluster.local:4318
• External: Your configured external endpoint

Environment Variables

import shield360

shield360.init()

Set these environment variables:

export OTEL_EXPORTER_OTLP_ENDPOINT="http://localhost:4318"
export OTEL_SERVICE_NAME="my-ai-service"
export OTEL_DEPLOYMENT_ENVIRONMENT="production"

Replace http://localhost:4318 with your Shield360 Platform endpoint.

Refer to the Shield360 SDK configuration reference for more advanced configurations and use cases.

CLI

For zero-code auto-instrumentation via command line:

CLI Arguments

# Using CLI arguments
shield360-instrument \
  --otlp-endpoint "YOUR_SHIELD360_PLATFORM_ENDPOINT" \
  --service-name "my-ai-service" \
  --deployment-environment "production" \
  python app.py

Replace:

1. YOUR_SHIELD360_PLATFORM_ENDPOINT with your Shield360 Platform endpoint from Step 1.

Environment Variables

# Set environment variables (takes precedence over CLI args)
export OTEL_EXPORTER_OTLP_ENDPOINT="YOUR_SHIELD360_PLATFORM_ENDPOINT"
export OTEL_SERVICE_NAME="my-ai-service"
export OTEL_DEPLOYMENT_ENVIRONMENT="production"

# Run your application
shield360-instrument python app.py

Replace:

1. YOUR_SHIELD360_PLATFORM_ENDPOINT with your Shield360 Platform endpoint from Step 1.

Refer to the Shield360 SDK configuration reference for more advanced configurations and use cases.

3. Access Shield360 Platform Dashboard

Once your LLM application is instrumented, you can explore the comprehensive observability data in the Shield360 Platform:

Access the Dashboard:

# Get the external service details
kubectl get svc -n shield360 shield360

# For local access via port-forwarding:
kubectl port-forward -n shield360 svc/shield360 3000:3000
# Then visit: http://localhost:3000

What You’ll See:

1. LLM Observability Dashboard: Comprehensive view of your AI applications including:
   • Real-time Metrics: Request rates, latency, and error rates
   • Cost Tracking: Token usage and cost breakdown by model and application
   • Performance Analytics: Response times, throughput, and model performance
   • Trace Visualization: Detailed execution flow with full request/response context
2. Vector Database Analytics: Monitor your vector database operations and performance
3. GPU Monitoring: Track GPU utilization and performance metrics (if enabled)
4. Custom Dashboards: Create tailored views for your specific monitoring needs

Your Shield360-instrumented AI applications will appear automatically in the Shield360 Platform with comprehensive observability including LLM costs, token usage, model performance, distributed tracing, and business intelligence - all in a single, self-hosted platform designed specifically for AI workloads.