👀 Views: 37 💬 Answers: 1 📅 Created: 2025-06-09

gcp vertex-ai tensorflow Python

I'm sure I'm missing something obvious here, but I'm trying to deploy a model to an endpoint in Vertex AI but I'm working with a 'NotFound' behavior... After training my model using TensorFlow 2.7 and exporting it correctly to Google Cloud Storage, I followed the documentation to create an endpoint. The code I used to deploy the model looks like this: ```python from google.cloud import aiplatform aiplatform.init(project='my-gcp-project', location='us-central1') endpoint = aiplatform.Endpoint.create(display_name='my-endpoint') model = aiplatform.Model('projects/my-gcp-project/locations/us-central1/models/my-model-id') # Attempt to deploy the model to the endpoint endpoint.deploy(model=model, deployed_model_display_name='my-deployed-model', traffic_split={'0': 100}) ``` However, when I run this code, I get the behavior: `google.api_core.exceptions.NotFound: 404 Not Found: Model with ID 'my-model-id' not found.` I've double-checked that the model ID is correct and that the model exists in the specified project and region. I've also tried using the full resource name instead of just the model ID: ```python model = aiplatform.Model('projects/my-gcp-project/locations/us-central1/models/my-model-id') ``` Yet, the behavior continues. I confirmed that the service account I'm using has the necessary permissions (`Vertex AI Admin`) and that the model is indeed in the project. I'm not sure what's going wrong here, and any insights would be greatly appreciated! My development environment is Debian. Any ideas what could be causing this?