Phase 3: Gateway and Ingress

$
# Create a test function
$
curl -s -X POST "http://${GATEWAY_ADDR}/v2/nvcf/functions" \
>
  -H "Host: api.${GATEWAY_ADDR}" \
>
  -H "Content-Type: application/json" \
>
  -H "Authorization: Bearer ${NVCF_TOKEN}" \
>
  -d '{
>
    "name": "my-echo-function",
>
    "inferenceUrl": "/echo",
>
    "healthUri": "/health",
>
    "inferencePort": 8000,
>
    "containerImage": "<YOUR_REGISTRY>/<YOUR_REPO>/load_tester_supreme:0.0.8"
>
  }' | jq .
$
$
# Extract function and version IDs from the response
$
export FUNCTION_ID=<function-id-from-response>
$
export FUNCTION_VERSION_ID=<version-id-from-response>
$
$
# Deploy the function (adjust instanceType and gpu for your cluster)
$
curl -s -X POST "http://${GATEWAY_ADDR}/v2/nvcf/deployments/functions/${FUNCTION_ID}/versions/${FUNCTION_VERSION_ID}" \
>
  -H "Host: api.${GATEWAY_ADDR}" \
>
  -H "Content-Type: application/json" \
>
  -H "Authorization: Bearer ${NVCF_TOKEN}" \
>
  -d '{
>
    "deploymentSpecifications": [
>
      {
>
        "instanceType": "NCP.GPU.A10G_1x",
>
        "backend": "nvcf-default",
>
        "gpu": "A10G",
>
        "maxInstances": 1,
>
        "minInstances": 1
>
      }
>
    ]
>
  }' | jq .
$
$
# Generate an invocation API key
$
EXPIRES_AT=$(date -u -v+1d '+%Y-%m-%dT%H:%M:%SZ' 2>/dev/null || date -u -d '+1 day' '+%Y-%m-%dT%H:%M:%SZ')
$
SERVICE_ID="nvidia-cloud-functions-ncp-service-id-aketm"
$
$
export API_KEY=$(curl -s -X POST "http://${GATEWAY_ADDR}/v1/keys" \
>
  -H "Host: api-keys.${GATEWAY_ADDR}" \
>
  -H "Content-Type: application/json" \
>
  -H "Key-Issuer-Service: nvcf-api" \
>
  -H "Key-Issuer-Id: ${SERVICE_ID}" \
>
  -H "Key-Owner-Id: test@nvcf-api.local" \
>
  -d '{
>
    "description": "test invocation key",
>
    "expires_at": "'"${EXPIRES_AT}"'",
>
    "authorizations": {
>
      "policies": [{
>
        "aud": "'"${SERVICE_ID}"'",
>
        "auds": ["'"${SERVICE_ID}"'"],
>
        "product": "nv-cloud-functions",
>
        "resources": [
>
          {"id": "*", "type": "account-functions"},
>
          {"id": "*", "type": "authorized-functions"}
>
        ],
>
        "scopes": ["invoke_function", "list_functions", "queue_details", "list_functions_details"]
>
      }]
>
    },
>
    "audience_service_ids": ["'"${SERVICE_ID}"'"]
>
  }' | jq -r '.value')
$
$
echo "API Key: ${API_KEY:0:20}..."
$
$
# Wait for deployment to be ready, then invoke the function
$
curl -s -X POST "http://${GATEWAY_ADDR}/echo" \
>
  -H "Host: ${FUNCTION_ID}.invocation.${GATEWAY_ADDR}" \
>
  -H "Content-Type: application/json" \
>
  -H "Authorization: Bearer ${API_KEY}" \
>
  -d '{"message": "hello world", "repeats": 1}' | jq .