docs: endpoint.create => aiplatform.Endpoint.create

[ageron]

Fix error in code example.

[nayaknishant]

Hi @ageron thanks for opening a Pull Request, to pass the tests change the title to docs: endpoint.create => aiplatform.Endpoint.create, so it follows conventional commits :). I agree with the change. Can we also move the predict code snippet to after creating an endpoint, so the order would be

from what it is now:

To get predictions from endpoints:

endpoint.predict(instances=[[6.7, 3.1, 4.7, 1.5], [4.6, 3.1, 1.5, 0.2]])

To create an endpoint

endpoint = endpoint.create(display_name='my-endpoint') 

To deploy a model to a created endpoint:

model = aiplatform.Model('/projects/my-project/locations/us-central1/models/{MODEL_ID}')

endpoint.deploy(model,
                min_replica_count=1,
                max_replica_count=5
                machine_type='n1-standard-4',
                accelerator_type='NVIDIA_TESLA_K80',
                accelerator_count=1)

to what we want (with the change):

To create an endpoint

endpoint = aiplatform.Endpoint.create(display_name='my-endpoint') 

To deploy a model to a created endpoint:

model = aiplatform.Model('/projects/my-project/locations/us-central1/models/{MODEL_ID}')

endpoint.deploy(model,
                min_replica_count=1,
                max_replica_count=5
                machine_type='n1-standard-4',
                accelerator_type='NVIDIA_TESLA_K80',
                accelerator_count=1)

To get predictions from endpoints:

endpoint.predict(instances=[[6.7, 3.1, 4.7, 1.5], [4.6, 3.1, 1.5, 0.2]])

[ageron]

Hi @ageron thanks for opening a Pull Request, to pass the tests change the title to docs: endpoint.create => aiplatform.Endpoint.create, so it follows conventional commits :). I agree with the change. Can we also move the predict code snippet to after creating an endpoint, so the order would be [...]

Thanks for your quick feedback. Done.