Imagen: photo looking over the shoulder of a robot looking at a screen with chat messages and hand writing notes
This tutorial shows how to make a Google Chat app that responds to incidents in real time. When responding to an incident, the app creates and populates a Chat space, facilitates incident resolution with messages, slash commands, and dialogs, and uses AI to summarize the incident response in a Google Docs document.
Paraphrasing noted Google Workspace Developer Expert, Romain Vialard, GenAI has made Google Chat apps a tangible prospect. This tutorial from the Google Developers site is a great example of how you can use Google’s Vertex AI with Google Chat. The tutorial will help you create a Google Apps Script powered Chat app that is able to summaries the messages in a Google Chat space.
There is a lot to take away from this example, but here are some of the headlines:
Setting a Google Cloud Project to use the new Google Chat Advanced Service for Apps Script
Setup and code for making calls to Google’s Vertex AI PaLM API (LLM) from Google Apps Script
Using the responses from Vertex AI to generate new assets.
There is a lot more you can do from this starting point, but hopefully it gives you a great starting point.
Building a Support AI Assistant for Google Workspace using Apps Script, Gen AI, and Google Chat.
This post from Stéphane Giron highlights one approach for improving responses from LLMs by integrating Google Custom Search Engine responses into the prompt. In this example Stéphane used Google Apps Script to power the AI Assistant, integrating with Google Chat for the user interface and Cloud Functions to reformat data.
This post is another example of the ‘power of the prompt’ and how LLM prompting strategies are a very effective way to utilise LLMs without having to ground or fine tune. If you are interested in understanding more here is a useful notebook produced by Michael W. Sherman which illustrates two powerful LLM prompting strategies: Chain of Thought and ReAct (Reasoning + Acting).
This video shows how to use the Palm API with Google Apps Script to extract data from Google Analytics 4 accounts. This can be useful for a variety of purposes, such as creating custom reports, automating data analysis, and building new data-driven applications.
Following on from the last post in Pulse where we looked at using Google PaLM API and MakerSuite in Google Apps Script, here’s another example from GDE Linda Lawton. As the video in the post shows Linda has been able to engineer prompts that allow you to use natural language to extract reports from Google Analytics. This shows the emergent capabilities of LLMs as well as some clever prompt engineering. The source post contains more detail, but here is an example:
var text = "The current date is '"+ date + "'. Create a JSON object which contains five parameter's dimension, metrics, start_date, end_date and property_id. The dimension and metric parameter's will be comma separated strings they can be empty if there is no valid text for it. The value of the dimension parameter should be a comma separated string of these dimensions names 'country, eventName, city, audienceName' and the value of the metric parameter should be a comma separated string of these metric names 'activeUsers, eventCount, screenPageViews', the property_id field will also be a string it will be a large number, start date and end date must be in the following format YYYY-MM-DD, which can be found in the given this text '" + prompt + "'. If no start date is found use set it to seven days ago and if no end date is found set it to today."
A couple of highlights worth noting:
Context – The current date is included programmatically to give the LLM a reference point
Reinforcement – ‘start date and end date must be in the following format YYYY-MM-DD’
Exceptions – ‘If no start date is found use set it to seven days ago and if no end date is found set it to today’
Discover the magic of combining Palm API’s extraordinary capabilities with the limitless potential of Google Apps Script. In this blog we will be taking a look at how we use the PaLM API and Google Apps Script inside of a Google Sheet. We will be passing prompts from a Google Sheet and getting back a response.
Learn how to integrate Google Bard responses inside of Google Sheets using the PaLM API and a little bit of Google Apps Script. Using Google’s MakerSuite it is easy to create an API key which you can use with a custom function in Google Sheets. Whilst the solution focuses on creating a custom function which would automatically refresh, using it programmatically to store responses could be a quick way to collaboratively experimenting with LLM text prompts.
Aryan Irani is a Google Developer Expert for Google Workspace. He is a writer and content creator who has been working in the Google Workspace domain for three years.
When we announced MakerSuite earlier this year, we were delighted to see people from all over the world sign up for the waitlist. With MakerSuite we want to help anyone become an AI maker and easily create innovative AI applications with Google’s large generative models. We’re excited to see how it’s being used.
Today, we’re expanding access to MakerSuite to cover 179 countries and territories, including anyone with a Google Workspace account. This means that more developers than ever can sign up to create AI applications with our latest language model, PaLM 2.
We’ve recently featured a couple of posts on Pulse mostly from Aryan Irani on getting started Google GenAI tools in Google Apps Script. As part of these Google MakerSuite, a tool that lets developers start prototyping with Google’s large language models quickly and easily, is used as part of the API calls to PaLM. MakerSuite is still in private preview, but the good news in the linked announcement that the waitlist has been expanded to 179 countries. Given how Google have rolled out other GenAI tools, in particular Bard, I’m not surprised that EU countries are still not included, but find it strange at time of writing the United Kingdom is still not on the list. Despite this the announcement is worth a read to find about some other new features including automatic text prompt tips and data import/export to Google Sheets and by CSV.
Want to write better prompts? Now, you can write a text prompt and click “Prompt Suggestion” to get ideas and suggestions to get better responses – Image credit: Google
Last month, OpenAI announced Function calling, “a new way to more reliably connect GPT’s capabilities with external tools and APIs”. Super useful ❤️ and we decided to integrate that with Google Apps Script.
Following on from yesterday’s Pulse post which highlighted Ben Collins reflections on ‘What can AI do for you as a Google Sheets user? Is the hype justified?’, here is a contribution from another Apps Script expert, Romain Vialard, announcing a ChatGPT library for Google Apps Script.
The source post highlights a number of examples, including the standard ‘prompt’ calling. Where this post gets very interesting is integration with Open AI’s function calling features:
In an API call, you can describe functions to gpt-3.5-turbo-0613 and gpt-4-0613, and have the model intelligently choose to output a JSON object containing arguments to call those functions. The Chat Completions API does not call the function; instead, the model generates JSON that you can use to call the function in your code.
To illustrate this below is a screenshot of a very slightly extended example, which has a Google Sheet with the headings email, name and tip topic. The functions are described to ChatGPT and in the case of sendMessage() the parameters it requires. The ChatGPTApp library handles the functions and in the case of the getContactsList() uses it to pass the Google Sheet data for ChatGPT to format a JSON response to correctly call the sendMessage() function.
I found it took me a while to start understanding what is going on and would recommend experimenting with the library and sample code to get a sense what is possible.
See how AI tools work with Google Sheets to boost your productivity. Covers ChatGPT, Google Bard, and AI add-ons.
A very informative post from Ben Collins, discussing how AI can be used to automate tasks, identify patterns, and make predictions in the context of Google Sheets. Ben provides several examples of how Generative AI can be used to improve the way you can interact with data in spreadsheets from helping with formula to generating and improving data.
As Ben points out in the post users have benefited from AI in Google Sheets for a number of years with features like Explore. Perhaps the biggest recent change is exposing Large Language Models as a service, with users able to directly access the ‘prompt’ to generate output.
Discover the magic of combining Palm API’s extraordinary capabilities with the limitless potential of Google Apps Script. In this blog we will be taking a look at how we use the PaLM API and Google Apps Script. We will be passing basic prompts and getting the appropriate responses using Google Apps Script.
Yesterday’s Pulse contribution from Aryan Irani there was an overview on getting started with Google’s Gen AI PaLM 2 Large Language Model accessed using MakerSuite. In a follow-up post Aryan continues dives deeper into how the PaLM API can be called from Google Apps Script. The post includes instructions and sample code to help you get started. Aryan will be continuing exploring and sharing what can be done with the PaLM API and Google Workspace tools such as Google Sheets, Google Docs and more in future tutorials.
Aryan Irani is a Google Developer Expert for Google Workspace. He is a writer and content creator who has been working in the Google Workspace domain for three years.
At the Google I/O ’23, various announcements were made with respect to different AI and ML advancements Google is making as we speak. While listening to the session, I stumbled on PaLM 2. It was really interesting as to what capabilities it has with respect to generative models and machine learning.
This tutorial series will introduce you to PaLM 2, the API, MakerSuite, and Google Apps Script. We will combine these tools to do something interesting with prompts.
Editor: There are a couple of ways you can access Google’s Gen AI language models. Bard is the consumer version but for developers you might want to start exploring API access to one of the underlying foundation language model, PaLM 2, using Google’s MakerSuite. There is a waitlist for MakerSuite, but worth putting your name down if you are interested in an easy way to programmatically start prototyping applications with the PaLM using a basic API key. This video series from Aryan Irani covers everything you need to get started, particularly if you are interested in using PaLM with Google Apps Script.
If you prefer to get started straight away, you can also access the PaLM API in Vertex AI today from a Google Cloud project (more information about this on the MakerSuite site).
Aryan Irani is a Google Developer Expert for Google Workspace. He is a writer and content creator who has been working in the Google Workspace domain for three years.
Have you ever wished for a personal assistant who could give you a quick summary of your day’s events while you’re busy getting ready in the morning? I worked on a Google Apps Script that does just that! By collecting events from in Google Calendar, generating a summary using ChatGPT, and creating a voice file with Google Text to Speech, the script will send a daily summary straight to their Google Chat Spaces.
Not surprising given the current interest in generative AI to see more examples emerging from the Google Workspace developer community. This latest example comes from Stéphane Giron who shares how he is able to recreate some Google Assistant functionality with Google Apps Script and calls to the ChatGPT and Google Cloud Text to Speech services. All the main code snippets from this project are available in the source post link.
