3  Part 1 Exercise

We’ll now practice what we have learned today. Try the following:

• Use an LLM to make some data (eg customer service query categories, a small product catalogue).

• Write prompts and contexts to interact with the data: try classifying a customer request, or returning relevant product details.

• Make at least one output (category, product details etc) into a Python data structure that can be used for further backend tasks.

• Write evaluation prompts and contexts to check the quality of outputs.

This notebook offers a simple template.

# Install the packages
! pip install --upgrade google-cloud-aiplatform
! pip install shapely<2.0.0

# Automatically restart kernel after installs so that your environment can access the new packages
import IPython

app = IPython.Application.instance()
app.kernel.do_shutdown(True)

from google.colab import auth
auth.authenticate_user()

# Add your project id and region
PROJECT_ID = "<...>"
REGION = "<...>"

import vertexai

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

4 TODO: Use an LLM to make some data

(eg customer service query categories, a small product catalogue).

# Your code here

4.0.1 TODO:

Write prompts and contexts to interact with the data: try classifying a customer request, or returning relevant product details.

# Your code here

4.0.2 TODO:

Make at least one output (category, product details etc) into a Python data structure that can be used for further backend tasks.

# Your code here

4.0.3 TODO:

Write evaluation prompts and contexts to check the quality of outputs.

# Your code here