Generative AI Leader Business Strategies for Generative AI Solutions — All Questions With Answers

Refer to the exhibit.

```
{
  "policy": {
    "bindings": [
      {
        "role": "roles/aiplatform.user",
        "members": ["user:analyst@example.com", "user:engineer@example.com"]
      },
      {
        "role": "roles/aiplatform.admin",
        "members": ["user:admin@example.com"]
      }
    ],
    "auditConfigs": [
      {
        "service": "aiplatform.googleapis.com",
        "auditLogConfigs": [
          {"logType": "ADMIN_READ", "exemptedMembers": []},
          {"logType": "DATA_READ", "exemptedMembers": []},
          {"logType": "DATA_WRITE", "exemptedMembers": []}
        ]
      }
    ]
  }
}
```

Refer to the exhibit.

```
Model Evaluation Metrics:
- Accuracy: 0.92
- Precision: 0.88
- Recall: 0.95
- F1 Score: 0.91
- Latency (p95): 450ms
- Cost per 1K requests: $0.12

Business Requirements:
- Latency must be <500ms for p95
- Cost target: <$0.10 per 1K requests
- Accuracy must be >90%
```

Refer to the exhibit.

```
ERROR: Prediction failed: model 'projects/my-project/locations/us-central1/models/123' is not deployed to endpoint 'projects/my-project/locations/us-central1/endpoints/456'. Deploy the model to the endpoint before sending prediction requests.
```

Refer to the exhibit.

```
{
  "displayName": "my-pipeline",
  "pipelineSpec": {
    "root": {
      "inputDefinitions": {},
      "task": {
        "componentRef": {
          "name": "comp-model-eval"
        },
        "inputs": {
          "project": {
            "runtimeValue": {
              "constantValue": "my-project"
            }
          },
          "location": {
            "runtimeValue": {
              "constantValue": "us-central1"
            }
          },
          "model_name": {
            "componentInput": "model_name"
          },
          "eval_dataset": {
            "componentInput": "eval_dataset"
          }
        }
      }
    }
  },
  "runtimeConfig": {
    "parameterValues": {
      "model_name": "text-bison@001",
      "eval_dataset": "projects/my-project/datasets/eval"
    }
  }
}
```

gcloud ai models upload \
  --region=us-central1 \
  --display-name=my-model \
  --artifact-uri=gs://my-bucket/model \
  --container-image-uri=us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/pytorch:latest

{
  "name": "projects/my-project/locations/us-central1/endpoints/123456",
  "displayName": "my-endpoint",
  "deployedModels": [
    {
      "id": "789",
      "model": "projects/my-project/locations/us-central1/models/456",
      "dedicatedResources": {
        "machineSpec": {
          "machineType": "n1-standard-2",
          "acceleratorType": "NVIDIA_TESLA_T4",
          "acceleratorCount": 1
        },
        "minReplicaCount": 1,
        "maxReplicaCount": 3
      },
      "automaticResources": null
    }
  ]
}

ERROR: (gcloud.ai.platform.predict) PERMISSION_DENIED: Permission 'aiplatform.endpoints.predict' denied on resource 'projects/my-project/locations/us-central1/endpoints/123456' (or resource may not exist).

Refer to the exhibit.

```
$ gcloud ai endpoints deploy-model \
  --endpoint=projects/123/locations/us-central1/endpoints/456 \
  --model=projects/123/locations/us-central1/models/789 \
  --machine-type=n1-highmem-2 \
  --traffic-split=0=100

Deployed model: projects/123/locations/us-central1/endpoints/456/deployedModels/789
Machine type: n1-highmem-2
Traffic split: 100%
```

Refer to the exhibit.

```json
{
  "bindings": [
    {
      "role": "roles/aiplatform.user",
      "members": ["user:admin@example.com"]
    }
  ]
}
```

Refer to the exhibit.

```
[ERROR] 401 Unauthorized - API key not valid. Please pass a valid API key.
```

{
  "bindings": [
    {
      "role": "roles/aiplatform.user",
      "members": ["user:developer@example.com"]
    }
  ],
  "etag": "BwWl3Z8="
}

displayName: customer-support-endpoint
dedicatedEndpoint: false
machineType: n1-standard-4
minReplicaCount: 2
maxReplicaCount: 10
trafficSplit:
  - modelId: support-v1
    percentage: 100

{
  "error": {
    "code": 403,
    "message": "Permission 'aiplatform.models.predict' denied on resource 'projects/my-project/locations/us-central1/models/456'"
  }
}

Refer to the exhibit.
```
{
  "budgetDisplayName": "genai-budget",
  "alertThresholdExceeded": 1.0,
  "costAmount": 12500,
  "budgetAmount": 10000,
  "alertName": "projects/123456789/budgets/12345"
}
```

Refer to the exhibit.
```json
{
  "deployment": {
    "machineType": "n1-highmem-16",
    "minReplicaCount": 1,
    "maxReplicaCount": 5,
    "accelerator": {
      "acceleratorType": "NVIDIA_TESLA_T4",
      "acceleratorCount": 1
    },
    "trafficSplit": {"default": 100}
  }
}
```