Step by Step Demo of Vertex AI in GCP

 This tutorial gets your started with GCP Vertex AI Generative AI service in step by step demo.

Commands Used:

gcloud services enable aiplatform.googleapis.com

gcloud iam service-accounts create <Your Service Account Name>

gcloud projects add-iam-policy-binding <Your Project ID> \

    --member=serviceAccount:<Your Service Account Name>@<Your Project ID>.iam.gserviceaccount.com \

    --role=roles/aiplatform.admin

from google.auth.transport.requests import Request

from google.oauth2.service_account import Credentials

key_path='<Your Project ID>.json'

credentials = Credentials.from_service_account_file(

    key_path,

    scopes=['https://www.googleapis.com/auth/cloud-platform'])

if credentials.expired:

    credentials.refresh(Request())

PROJECT_ID = '<Your Project ID>'

REGION = 'us-central1'

!pip install -U google-cloud-aiplatform "shapely<2"

import vertexai

# initialize vertex

vertexai.init(project = PROJECT_ID, location = REGION, credentials = credentials)

from vertexai.language_models import TextGenerationModel

generation_model = TextGenerationModel.from_pretrained("text-bison@001")

prompt = "I want to self manage a bathroom renovation project in my home. \

Please suggest me step by step plan to carry out this project."

print(generation_model.predict(prompt=prompt).text)