Gen-AI Developer Classroom notes 28/Mar/2026

Configure System to use LLMs

Common softwares

• git
• python
• uv
• VScode
• VSCode extensions (python and jupyter from microsoft)
• GCP SDK (GCP CLI)

• AWS CLI

• Prompt

I want to install the following sofwares on windows 11, give me a command line approach to install them 
* git 
* python
* uv
* VScode
* GCP SDK (GCP CLI)
* AWS CLI
* Azure CLI

• Winget

winget install --id Git.Git -e --source winget
winget install -e --id Python.Python.3.13
winget install -e --id astral-sh.uv
winget install --id Microsoft.VisualStudioCode -e --source winget
winget install --id Google.CloudSDK -e --source winget
winget install --id Amazon.AWSCLI -e --source winget
winget install Microsoft.AzureCLI

• Verify

git --version
python --version
uv --version
gcloud --version
aws --version
az --version

• cheaper models
  • GCP: gemini-flash-lite
  • AWS: Amazon Nova Micro
  • Azure: Phi-4-mini

GCP

• Prompt for enabling vertex

Give me steps to enable Vertex AI on my GCP account using console

• Prompt for configuring access to vertex on your laptop

Give me steps to configure accessing vertex from langchain using  langchain-google-genai

* GCloud sdk is installed, needs to be configured
* Give me steps to create a folder using uv give me steps to add necessary packages and using `flash-lite` model to ask what is capital of france to model

• Steps

gcloud auth login
gcloud config set project <YOUR_PROJECT_ID>
gcloud auth application-default login

• COnfigure sample code

mkdir vertex-langchain-demo
cd vertex-langchain-demo
uv init
uv sync
uv add langchain langchain-google-genai python-dotenv

• Pyproject.toml

[project]
name = "gcp-vertex-test"
version = "0.1.0"
description = "Add your description here"
readme = "README.md"
requires-python = ">=3.13"
dependencies = [
    "google-cloud-aiplatform>=1.143.0",
    "langchain>=1.2.13",
    "langchain-google-genai>=4.2.1",
    "python-dotenv>=1.2.2",
]

• .env

GOOGLE_CLOUD_PROJECT='<your-project-id>'

• main.py

from langchain_google_genai import ChatGoogleGenerativeAI
from dotenv import load_dotenv

load_dotenv()
import os
project = os.getenv('GOOGLE_CLOUD_PROJECT')

def main():  
    # Initialize model
    llm = ChatGoogleGenerativeAI(
        model="gemini-2.5-flash-lite",
        temperature=0,
        vertexai=True,
        project=project
    )

    # Ask a question
    response = llm.invoke("What is the capital of France?")

    print(response.content)


if __name__ == "__main__":
    main()

• Run uv run main.py => The capital of France is **Paris**.