google.api_core.exceptions.PermissionDenied: 403 Permission denied on resource project YOUR_PROJECT_ID. reason: "CONSUMER_INVALID"

Question

I am trying to use the PredictionServiceClient from aiplatform package. But I am getting this error:

google.api_core.exceptions.PermissionDenied: 403 Permission denied on resource project YOUR_PROJECT_ID. [links {
  description: "Google developers console"
  url: "https://console.developers.google.com"
}
, reason: "CONSUMER_INVALID"
domain: "googleapis.com"
metadata {
  key: "consumer"
  value: "projects/YOUR_PROJECT_ID"
}
metadata {
  key: "service"
  value: "aiplatform.googleapis.com"
}
]

Code snippet:

project_id = "positive-tempo-405405"model_id = "textembedding-gecko@latest"  # or another model IDlocation = "us-central1"instance_id = 'YOUR_INSTANCE_ID'database_id = 'YOUR_DATABASE_ID'
def create_vector_represenation(text):  # Initialize the client  text_to_text_client = vertex_ai.gapic.PredictionServiceClient(client_options={"api_endpoint": "us-central1-aiplatform.googleapis.com"})
  # Get Vector Representation  # Create the endpoint for the model  endpoint = f"projects/{project_id}/locations/{location}/models/{model_id}"  # Create the request payload  instances = [{"content": text}]  # Make the prediction request  response = text_to_text_client.predict(endpoint=endpoint, instances=instances)  # The response contains the embeddings in the `predictions` field  vector_representation = response.predictions[0]["embeddings"]["values"]  st.write('vector_representation: ', vector_representation)
  return vector_representation

I checked the followings:

I have added the required policies:

{
  "bindings": [
    {
      "members": [
        "serviceAccount:[email protected]",
        "user:***@gmail.com"
      ],
      "role": "roles/aiplatform.admin"
    },
    {
      "members": [
        "serviceAccount:[email protected]"
      ],
      "role": "roles/compute.serviceAgent"
    },
    {
      "members": [
        "serviceAccount:service-630332944972@dataflow-service-producer-prod.iam.gserviceaccount.com"
      ],
      "role": "roles/dataflow.serviceAgent"
    },
    {
      "members": [
        "serviceAccount:[email protected]",
        "serviceAccount:[email protected]"
      ],
      "role": "roles/editor"
    },
    {
      "members": [
        "serviceAccount:[email protected]",
        "user:***@gmail.com"
      ],
      "role": "roles/ml.admin"
    },
    {
      "members": [
        "serviceAccount:[email protected]",
        "user:***@gmail.com"
      ],
      "role": "roles/ml.developer"
    },
    {
      "members": [
        "serviceAccount:[email protected]"
      ],
      "role": "roles/notebooks.serviceAgent"
    },
    {
      "members": [
        "user:***@gmail.com"
      ],
      "role": "roles/owner"
    }
  ],
  "etag": "BwYKdso-i10=",
  "version": 1
}

Set the path of application_default_credentials.json to GOOGLE_APPLICATION_CREDENTIALS environment variable.

Have provided the correct project ID:

Project info
-------------
Project name: RAG-Vertex-AI-Chatbot
Project number: 630332944972
Project ID: positive-tempo-405405

Not sure what I am missing here. How to mitigate this issue?