Introduction to Function Calling with Gemini - GSP1227

Introduction to Function Calling with Gemini - GSP1227

Overview

Gemini is a family of generative AI models developed by Google DeepMind that is designed for multimodal use cases. The Gemini API gives you access to the Gemini Pro Vision and Gemini Pro models. In this lab, you learn how to use the Vertex AI Gemini API to generate function calls from text prompts.

Calling functions from Gemini

Function calling lets developers create a description of a function in their code, then pass that description to a language model in a request. The response from the model includes the name of a function that matches the description and the arguments to call it with.

Function calling is similar to Vertex AI Extensions in that they both generate information about functions. The difference between them is that function calling returns JSON data with the name of a function and the arguments to use in your code, whereas Vertex AI Extensions returns the function and calls it for you.

Objectives

In this lab, you learn how to:

  • Install the Vertex AI SDK for Python.

  • Use the Vertex AI Gemini API to interact with the Gemini Pro (gemini-pro) model:

    • Generate function calls from a text prompt to help customers get information about products in the Google Store.

    • Generate function calls from a text prompt and call an external API to geocode addresses.

    • Generate function calls from a text prompt to extract entities from log data.

Setup and requirements

Before you click the Start Lab button

Read these instructions. Labs are timed and you cannot pause them. The timer, which starts when you click Start Lab, shows how long Google Cloud resources will be made available to you.

This hands-on lab lets you do the lab activities yourself in a real cloud environment, not in a simulation or demo environment. It does so by giving you new, temporary credentials that you use to sign in and access Google Cloud for the duration of the lab.

To complete this lab, you need:

  • Access to a standard internet browser (Chrome browser recommended).

Note: Use an Incognito or private browser window to run this lab. This prevents any conflicts between your personal account and the Student account, which may cause extra charges incurred to your personal account.

  • Time to complete the lab---remember, once you start, you cannot pause a lab.

Note: If you already have your own personal Google Cloud account or project, do not use it for this lab to avoid extra charges to your account.

How to start your lab and sign in to the Google Cloud console

  1. Click the Start Lab button. If you need to pay for the lab, a pop-up opens for you to select your payment method. On the left is the Lab Details panel with the following:

    • The Open Google Cloud console button

    • Time remaining

    • The temporary credentials that you must use for this lab

    • Other information, if needed, to step through this lab

  2. Click Open Google Cloud console (or right-click and select Open Link in Incognito Window if you are running the Chrome browser).

    The lab spins up resources, and then opens another tab that shows the Sign in page.

    Tip: Arrange the tabs in separate windows, side-by-side.

    Note: If you see the Choose an account dialog, click Use Another Account.

  3. If necessary, copy the Username below and paste it into the Sign in dialog.

     student-02-ebf7e6c6e45d@qwiklabs.net
    

    You can also find the Username in the Lab Details panel.

  4. Click Next.

  5. Copy the Password below and paste it into the Welcome dialog.

     fQ6JmAuZJrL4
    

    You can also find the Password in the Lab Details panel.

  6. Click Next.

    Important: You must use the credentials the lab provides you. Do not use your Google Cloud account credentials.

    Note: Using your own Google Cloud account for this lab may incur extra charges.

  7. Click through the subsequent pages:

    • Accept the terms and conditions.

    • Do not add recovery options or two-factor authentication (because this is a temporary account).

    • Do not sign up for free trials.

After a few moments, the Google Cloud console opens in this tab.

Note: To view a menu with a list of Google Cloud products and services, click the Navigation menu at the top-left.

Navigation menu icon

Task 1. Open the notebook in Vertex AI Workbench

  1. In the Google Cloud Console, on the Navigation menu, click Vertex AI > Workbench.

  2. On the User-Managed Notebooks page, find the generative-ai-jupyterlab notebook and click on the Open JupyterLab button.

The JupyterLab interface opens in a new browser tab.

Task 2. Open the generative-ai folder

  1. Navigate to the generative-ai folder on the left hand side of the notebook.

  2. Navigate to the /gemini/function-calling folder.

  3. Click on the intro_function_calling.ipynb file.

  4. Run through the Getting Started, Set Google Cloud project information and Import libraries sections of the notebook.

    • For Project ID, use qwiklabs-gcp-02-ce30d653be08, and for the Location, use europe-west4.

Note: you can skip any notebook cells that are noted. Colab only.

In the following sections, you run through the notebook cells to see how to use the Vertex AI Gemini API with the Vertex AI SDK for Python.

Click Check my progress to verify the objective.

Install Vertex AI SDK for Python and import libraries.

Check my progress

Task 3. Using function calling for structured Google Store queries

When working with a generative text model, it can be difficult to coerce the LLM to give consistent responses in a structured format such as JSON. Function calling makes it easy to work with LLMs via prompts and unstructured inputs, and have the LLM return a structured response that can be used to call an external function.

You can think of function calling as a way to get structured output from user prompts and function definitions, use that structured output to make an API request to an external system, then return the function response to the LLM to generate a response to the user. In other words, function calling in Gemini extracts structured parameters from unstructured text or messages from users. In this example, you'll use function calling along with the chat modality in the Gemini model to help customers get information about products in the Google Store.

  1. In this task, run through the notebook cells to see how to use the Gemini model to help customers get information about products in the Google Store.

Click Check my progress to verify the objective.

Generate a simple weather function call.

Check my progress

Task 4. Using function calling to geocode addresses with a maps API

In this example, you'll use the text modality in the Gemini API to define a function that takes multiple parameters as inputs. You'll use the function call response to then make a live API call to convert an address to latitude and longitude coordinates.

  1. In this task, run through the notebook cells to see how to use the Gemini Pro model to generate a function call to geocode an address.

Here we used the OpenStreetMap Nominatim API to geocode an address to make it easy to use and learn in this notebook. If you're working with large amounts of maps or geolocation data, you can use the Google Maps Geocoding API.

Click Check my progress to verify the objective.

Generate a complex function call.

Check my progress

Task 5. Using function calling for entity extraction

In the previous examples, you made use of the entity extraction functionality within Gemini Function Calling so that you could pass the resulting parameters to a REST API or client library. However, you might want to only perform the entity extraction step with Gemini Function Calling and stop there without actually calling an API. You can think of this functionality as a convenient way to transform unstructured text data into structured fields.

In this example, you'll build a log extractor that takes raw log data and transforms it into structured data with details about error messages.

  1. In this task, run through the notebook cells to see how to use the Gemini Pro model to generate function calls to extract entities from log data.

Click Check my progress to verify the objective.

Generate function calls from a chat prompt.


Solution of Lab