Gen-AI Developer Classroom notes 18/Aug/2025

Understanding Indexing

Scenario 1:

• I have a ayurvedic book (Every day ayurveda)
• I want a chatgpt to be my ayurvedic expert and suggest me lifesytle changes/medicines
• You can build a GPT/GEM and give a prompt and knowledge in terms of pdf files

Programatic Approach

• Data Sources:
  • pdf files
  • markdown files
  • databases
  • api calls
  • websites
• Chunking
• Embedding
• Vector databases
• Prompt Templates

Google Vertex Setup

• To use gemini models from your system
• Install gcloud cli
• To authenicate

gcloud init
gcloud auth application-default login

• To test connectivity
• create a new project
• Now create a notebook or python module Refer Here

pip install -qU "langchain[google-vertexai]"

• Code

# Ensure your VertexAI credentials are configured

from langchain.chat_models import init_chat_model

model = init_chat_model("gemini-2.5-flash", model_provider="google_vertexai")
model.invoke("Hello, world!")