Category Archives: Google Developers Blog

News and insights on Google platforms, tools and events

MakerSuite expands to 179 countries and territories, and adds helpful features for AI makers

Posted by Simon Tokumine, Director of Product Management

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’re also introducing three helpful features:

  • Automatically optimize your text prompts
    •
    Image showing prompt suggestion in MakerSuite
    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 
  • Enable dark mode
    •
    Image showing light mode and dark mode UX in MakerSuite
    In MakerSuite, you can now switch from light mode to dark mode in the settings.
  • Import and export your data with Google sheets and CSV to save time and collaborate effectively
    •
    Image showing import data function in MakeSuite
    Import and export your data to and from Google Sheets or CSV files easily. This can save you time by eliminating the need to recreate data that you have already created. It can also help you collaborate more effectively with others by allowing you to share your results easily.

Easily go from MakerSuite to code

Since the PaLM API is integrated into MakerSuite, it’s easy to quickly try different prompts from your browser, and then incorporate them into your code—no machine learning expertise required.

Moving image showing how users can copy their code with one click to integrate it into their project
Once your prompt is ready, simply copy your code in just one click and integrate it into your project

Get started

Sign up and learn more on our Generative AI for Developers website. Be sure to check out our quick-start guide, browse our prompt gallery, and explore sample apps for inspiration. We can't wait to see what you build with MakerSuite!

#WeArePlay | Meet Ayushi & Nikhil from India. More stories from around the world.

Posted by Leticia Lago, Developer Marketing

This month, we’re sharing new #WeArePlay stories from inspiring founders creating apps which help people improve their quality of life. From a diabetes management tracker to an upskilling platform for women, hear the stories behind some groundbreaking apps on Google Play.



Firstly, meet Nikhil and Ayushi from Bengaluru, India. During the Covid-19 lockdowns, Nikhil watched as his mother picked up new hobbies and tried making different dishes in the kitchen. Seeing his mom researching new recipes and cooking resources, it struck him that there was a lack of educational platforms in India specifically targeted at women. This gave him and his wife, Ayushi, the idea to create Alippo: an upskilling app for women that provides classes and training materials. It also has resources to help women launch and manage their own businesses using their newly acquired expertise. In the future, they want to add more learning materials, business guides and even financing options.


Image of Ed, Ken, and Erin of Health2Sync, located in Taipei City, Taiwan g.co/play/weareplay Google Play

Next up we have Ed, Ken and Erin from Taiwan. Ed comes from a family with a history of diabetes. But his grandma always stayed on top of her condition thanks to her habit of regularly noting down her blood sugar levels and sharing them with her doctor. Partnering with product manager Ken, whose mother also has diabetes, and former colleague Erin, he launched Health2Sync: a digital blood sugar tracker with a range of other features for tracking and managing diets, exercise and medication. Thanks to the app’s new AI-based food recognition feature, people can now track the contents and nutrients of their meals just by uploading a picture of their food.


Image of César and Lorenzo of WeCancer, located in Sao Paulo, Brazil g.co/play/weareplay Google Play

Now, Lorenzo and César from Brazil. Growing up, they both had personal experiences with cancer having lost their mothers to the disease. When they met some time later, via a mutual friend, they discussed their experiences, both agreeing that the hospital visits were tiring for their moms, and often unnecessary when measures could be taken to provide care at home. This inspired them to partner up and create WeCancer, a cancer treatment support platform where patients can receive support and medical care from the comfort of their own home, with monitoring and advice from doctors. In Lorenzo's own words, the app provides "qualified care outside of hospital walls to make life easier for patients”.


Image of John, Laura and Erich of Curable, located in Denver (CO), USA g.co/play/weareplay Google Play

Last but not least, Laura, Erich and John from the US. When they were colleagues, it was sharing their experiences around chronic pain that bonded them and brought them together as friends. When John began to teach the others some alternative methods he’d learnt for managing his pain, all three began to see huge improvements in their various conditions. Elated by how much these techniques and practices had helped them, they wanted to share the practices with others, inspiring them to team up to create Curable. On the app, chronic pain sufferers can follow a guided recovery program with a range of science-backed methods, including cognitive behavioral therapy and soothing meditation.


Discover more #WeArePlay stories from across the globe and stay tuned for more.



How useful did you find this blog post?

★ ★ ★ ★ ★

How it’s Made: TextFX is a suite of AI tools inspired by Lupe Fiasco’s lyrical and linguistic techniques

Posted by Aaron Wade, Creative Technologist

Google Lab Sessions is a series of experimental AI collaborations with innovators. In our latest Lab Session we wanted to explore specifically how AI could expand human creativity. So we turned to GRAMMY® Award-winning rapper and MIT Visiting Scholar Lupe Fiasco to build an AI experiment called TextFX.



The discovery process

We started by spending time with Lupe to observe and learn about his creative process. This process was invariably marked by a sort of linguistic “tinkering”—that is, deconstructing language and then reassembling it in novel and innovative ways. Some of Lupe’s techniques, such as simile and alliteration, draw from the canon of traditional literary devices. But many of his tactics are entirely unique. Among them was a clever way of creating phrases that sound identical to a given word but have different meanings, which he demonstrated for us using the word “expressway”:

express whey (speedy delivery of dairy byproduct)

express sway (to demonstrate influence)

ex-press way (path without news media)

These sorts of operations played a critical role in Lupe’s writing. In light of this, we began to wonder: How might we use AI to help Lupe explore creative possibilities with text and language?

When it comes to language-related applications, large language models (LLMs) are the obvious choice from an AI perspective. LLMs are a category of machine learning models that are specially designed to perform language-related tasks, and one of the things we can use them for is generating text. But the question still remained as to how LLMs would actually fit into Lupe’s lyric-writing workflow.

Some LLMs such as Google’s Bard are fine-tuned to function as conversational agents. Others such as the PaLM API’s Text Bison model lack this conversational element and instead generate text by extending or fulfilling a given input text. One of the great things about this latter type of LLM is their capacity for few-shot learning. In other words, they can recognize patterns that occur in a small set of training examples and then replicate those patterns for novel inputs.

As an initial experiment, we had Lupe provide more examples of his same-sounding phrase technique. We then used those examples to construct a prompt, which is a carefully crafted string of text that primes the LLM to behave in a certain way. Our initial prompt for the same-sounding phrase task looked like this:

Word: defeat
Same-sounding phrase: da feet (as in "the feet")

Word: surprise
Same-sounding phrase: Sir Prize (a knight whose name is Prize)

Word: expressway
Same-sounding phrase: express whey (speedy delivery of dairy byproduct)

(...additional examples...)

Word: [INPUT WORD]
Same-sounding phrase:


This prompt yielded passable outputs some of the time, but we felt that there was still room for improvement. We actually found that factors beyond just the content and quantity of examples could influence the output—for example, how the task is framed, how inputs and outputs are represented, etc. After several iterations, we finally arrived at the following:

A same-sounding phrase is a phrase that sounds like another word or phrase.


Here is a same-sounding phrase for the word "defeat":

da feet (as in "the feet")


Here is a same-sounding phrase for the word "surprise":

Sir Prize (a knight whose name is Prize)


Here is a same-sounding phrase for the word "expressway":

express whey (speedy delivery of dairy byproduct)


(...additional examples...)


Here is a same-sounding phrase for the word "[INPUT WORD]":

After successfully codifying the same-sounding word task into a few-shot prompt, we worked with Lupe to identify additional creative tasks that we might be able to accomplish using the same few-shot prompting strategy. In the end, we devised ten prompts, each uniquely designed to explore creative possibilities that may arise from a given word, phrase, or concept:

SIMILE - Create a simile about a thing or concept.

EXPLODE - Break a word into similar-sounding phrases.

UNEXPECT - Make a scene more unexpected and imaginative.

CHAIN - Build a chain of semantically related items.

POV - Evaluate a topic through different points of view.

ALLITERATION - Curate topic-specific words that start with a chosen letter.

ACRONYM - Create an acronym using the letters of a word.

FUSE - Create an acronym using the letters of a word.

SCENE - Create an acronym using the letters of a word.

UNFOLD - Slot a word into other existing words or phrases.

We were able to quickly prototype each of these ideas using MakerSuite, which is a platform that lets users easily build and experiment with LLM prompts via an interactive interface.

Moving image showing a few-shot prompt in MakerSuite

How we made it: building using the PaLM API

After we finalized the few-shot prompts, we built an app to house them. We decided to call it TextFX, drawing from the idea that each tool has a different “effect” on its input text. Like a sound effect, but for text.

Moving image showing the TextFX user interface

We save our prompts as strings in the source code and send them to Google’s PaLM 2 model using the PaLM API, which serves as an entry point to Google’s large language models.

All of our prompts are designed to terminate with an incomplete input-output pair. When a user submits an input, we append that input to the prompt before sending it to the model. The model predicts the corresponding output(s) for that input, and then we parse each result from the model response and do some post-processing before finally surfacing the result in the frontend.

Diagram of information flow between TextFX and Google's PaLM 2 large language models

Users may optionally adjust the model temperature, which is a hyperparameter that roughly corresponds to the amount of creativity allowed in the model outputs.

Try it yourself

You can try TextFX for yourself at textfx.withgoogle.com.

We’ve also made all of the LLM prompts available in MakerSuite. If you have access to the public preview for the PaLM API and MakerSuite, you can create your own copies of the prompts using the links below. Otherwise, you can join the waitlist.


And in case you’d like to take a closer look at how we built TextFX, we’ve open-sourced the code here.

If you want to try building with the PaLM API and MakerSuite, join the waitlist.

A final word

TextFX is an example of how you can experiment with the PaLM API and build applications that leverage Google’s state of the art large language models. More broadly, this exploration speaks to the potential of AI to augment human creativity. TextFX targets creative writing, but what might it mean for AI to enter other creative domains as a collaborator? Creators play a crucial role in helping us imagine what these collaborations might look like. Our hope is that this Lab Session gives you a glimpse of what’s possible using the PaLM API and inspires you to use Google’s AI offerings to bring your own ideas to life, in whatever your craft may be.

If you’d like to explore more Lab Sessions like this one, head over to labs.google.com.

Indie Games Fund: Apply for support from Google Play’s $2M fund in Latin America

Posted by Daniel Trócoli Head of Play Partnerships for Games - LATAM

In 2022, we first launched the Indie Games Fund in Latin America as part of our commitment to helping developers of all sizes grow on Google Play. Check out the 10 selected studios who received a share of the fund last year.

Today, we’re bringing back the Indie Games Fund for 2023. We will award $2 million dollars in non-dilutive cash awards in addition to hands-on support, to selected small games studios based in Latin America, helping them build and grow their businesses on our platform.

The program is open to indie game developers who have already launched a game - whether it’s on Google Play or another mobile platform, PC or console. Each selected recipient will get between $150,000 and $200,000 dollars to help them take their game to the next level, and build successful businesses.

Check out all eligibility criteria and apply now. Applications close at 12:00pm BRT September 1, 2023. Priority will be given to applications received by 12:00pm BRT August 16, 2023.

For more updates about all our programs, resources and tools for indie game developers visit our website, and follow us on Twitter @GooglePlayBiz and Google Play business community on LinkedIn.



How useful did you find this blog post?

★ ★ ★ ★ ★

Champion Innovator David Cardozo, based in Victoriaville, Quebec

Posted by Max Saltonstall, Developer Relations Engineer

Google Cloud Champion Innovators are a global network of more than 500 non-Google professionals, who are technical experts in Google Cloud products and services. Each Champion specializes in one of nine different technical categories: cloud AI/ML, data analytics, hybrid multi-cloud, modern architecture, security and networking, serverless app development, storage, Workspace and databases.

In our ongoing interview series we sit down with Champion Innovators across the world to learn more about their journeys, their technology focus, and what excites them.

Today we're talking to David Cardozo, a Machine Learning Scientist, Kubeflow Community member and ML GDE.

Headshot of David Cardozo, smiling

What tech area has you most fascinated right now, and why?

I love all the creative ways people are using Machine Learning (ML) to solve problems. There are a ton of cool applications that I see through my consulting work – counting cranberries from drone footage, tallying fish in fish farms, classifying plastics for recycling – and there's great stuff going on in both the public and private sector.

I'm also digging into the Kubeflow community right now, learning from that group. It's a melting pot of languages: Go, Python, etc. By participating in the working group and meetings I'm understanding so much more about current issues, blockers to progress, and get a deeper understanding of the technology itself. I love gaining that insight.

How do you like to learn new services, tools, and applications?

I read a lot: engineering blogs, books, documentation. Right now I'm learning system design from a variety of Google blogs, which helps me learn how to scale up the things I design. I'm also learning how to make ML models, and how to improve the ones I've deployed.

I'm passionate about contributing to the open source community and actively participate in various projects. Right now with friends in the community we developed Elegy – a high level API for Deep Learning in JAX.

Writing about a topic also helps me learn. Right now, I am working on blogs focused on Kubeflow pipelines in version 2.0 and Vertex AI in Google Cloud.

When I'm diving into a brand new technology I try to join the working groups that are furthering its development, so I get an inside look at how things are moving. Those working groups, their discussions and notes, teach me a ton. I also use the Google Cloud Forum and StackOverflow communities to deepen my knowledge.

What are some exciting projects you have in flight right now?

Getting to play with Generative AI within Vertex (on Google Cloud) has been very fun. I like hearing about what the other Innovators are making; it's a very smart, creative group with cool projects. Learning more about the cutting edge of ML is very exciting.

I'm doing a bit more with Open Source in my free time, trying to understand more around Kubernetes and Kubeflow.

What engages you outside of the technology world?

I stay active: swimming, lots of soccer. I also have been learning about option trading, testing out the waters of active investing. The complexity of those economic systems stimulates my curiosity. I really want to understand how it works, and how to make it useful.

My background is in the social sciences, I'm a bit of a frustrated historian. My interest in school was history, but my family said that I shouldn't focus on social science, so I majored in Math and Physics, but never finished my degree. Right now, after a few life and career pivots, I'm working on completing my Bachelor's through Coursera via the University of London, and earning a history degree requires a lot of reading. This has inspired me to make an AI project that summarizes the knowledge from very long documents, making history research more accessible by giving people a format that's easier to consume.

What brought you into the Innovators program?

I started as one of the Google Developer Experts, but I always wanted more opportunities to talk with Google engineers and get more feedback on the cloud architectures I was building, for myself or my clients. I also wanted to be more involved in the Cloud community.

When I see members of the community encountering challenges, struggling as I did, I feel the pull to help them. As a native Spanish speaker I wanted to make more content in Spanish for folks like myself. I didn't have a mentor as I was learning, and I'd like to fill that gap for others.

So I began organizing meetups in Latin America, and in Spanish speaking communities. I sought out more data scientists. And I went through Qwiklabs and Cloud Skills Boost to learn to improve my own skills.

After I joined the Innovators program, I've had the chance to play with new AI technologies, work more closely with Google experts and received credits for more Cloud experimentation.

What's one thing our readers should do next?

I recommend using some of the open, public teaching resources in Computer Science (CS), especially if you're like me and didn't focus on CS in school. For me, computers came very late to Colombia and I didn't have a chance to major in CS as a student, so I got into it via Math, then information security.

I also suggest taking a look at Elegy, and being involved in solving first issues, providing feedback and also some pull requests :)

I've liked Stanford's course on Neural Networks (CS 231n), as well as MIT's open courseware classes and ML videos on YouTube by Joel Grus.


Each Champion Innovator is not affiliated with Google nor do they offer services on behalf of Google.

What’s new for developers building solutions on Google Workspace – mid-year recap

Posted by Chanel Greco, Developer Advocate Google Workspace

Google Workspace offers tools for productivity and collaboration for the ways we work. It also offers a rich set of APIs, SDKs, and no-code/low-code tools to create apps and integrate workflows that integrate directly into the surfaces across Google Workspace.

Leading software makers like Atlassian, Asana, LumApps and Miro are building integrations with Google Workspace apps—like Google Docs, Meet, and Chat—to make it easier than ever to access data and act right in the tools relied on by more than 3 billion users and 9 million paying customers.

At I/O’23 we had some exciting announcements for new features that give developers more options when integrating apps with Google Workspace.


Third-party smart chips in Google Docs

We announced the opening up of smart chips functionality to our partners. Smart chips allow you to tag and see critical information to linked resources, such as projects, customer records, and more. This preview information provides users with context and critical information right in the flow of their work. These capabilities are now generally available to developers to build their own smart chips.

Some of our partners have built and launched integrations using this new smart chips functionality. For example, Figma is integrated into Docs with smart chips, allowing users to tag Figma projects which allows readers to hover over a Figma link in a doc to see a preview of the design project. Atlassian is leveraging smart chips so users can seamlessly access Jira issues and Confluence pages within Google Docs.

Tableau uses smart chips to show the user the Tableau Viz's name, last updated date, and a preview image. With the Miro smart chip solution users have an easy way to get context, request access and open a Miro board from any document. The Whimsical smart chip integration allows users to see up-to-date previews of their Whimsical boards.

Moving image showing functionality of Figma smart chips in Google docs, allowing users to tag and preview projects in docs.

Google Chat REST API and Chat apps

Developers and solution builders can use the Google Chat REST API to create Chat apps and automate workflows to send alerts, create spaces, and share critical data right in the flow of the conversation. For instance, LumApps is integrating with the Chat APIs to allow users to start conversations in Chat right from within the employee experience platform.

The Chat REST API is now generally available.

Using the Chat API and the Google Workspace UI-kit, developers can build Chat apps that bring information and workflows right into the conversation. Developers can also build low code Chat apps using AppSheet.

Moving image showing interactive Google Meet add-ons by partner Jira

There are already Chat apps available from partners like Atlassian’s Jira, Asana, PagerDuty and Zendesk. Jira for Google Chat to collaborate on projects, create issues, and update tickets – all without having to switch context.

Google Workspace UI-kit

We are continuing to evolve the Workspace UI-kit to provide a more seamless experience across Google Workspace surfaces with easy to use widgets and visual optimizations.

For example, there is a new date and time picker widget for Google Chat apps and there is the new two-column layout to optimize space and organize information.

Google Meet SDKs and APIs

There are exciting new capabilities which will soon be launched in preview for Google Meet.

For example, the Google Meet Live Sharing SDK allows for the building of new shared experiences for users on Android, iOS, and web. Developers will be able to synchronize media content across participant’s devices in real-time and offer shared content controls for everyone in the meeting.

The Google Meet Add-ons SDK enables developers to embed their app into Meet via an iframe, and choose between the main stage or the side panel. This integration can be published on the Google Workspace Marketplace for discoverability.

Partners such as Atlassian, Figma, Lucid Software, Miro and Polly.ai, are already building Meet add-ons, and we’re excited to see what apps and workflows developers will build into Meet’s highly-interactive surfaces.

Image of interactive Google Meet add-on by partner Miro

With the Google Meet APIs developers can add the power of Google Meet to their applications by pre-configuring and launching video calls right from their apps. Developers will also be able to pull data and artifacts such as attendance reporting, recordings, and transcripts to make them available for their users post-meeting.

Google Calendar API

The ability to programmatically read and write the working location from Calendar is now available in preview. In the second half of this year, we plan to make these two capabilities, along with the writing of sub-day working locations, generally available.

These new capabilities can be used for integrating with desk booking systems and coordinating in-offices days, to mention just a few use cases. This information will help organizations adapt their setup to meet the needs of hybrid work.

Google Workspace API Dashboard and APIs Explorer

Two new tools were released to assist developers: the Google Workspace API Dashboard and the APIs Explorer.

The API Dashboard is a unified way to access Google Workspace APIs through the Google Cloud Console—APIs for Gmail, Google Drive, Docs, Sheets, Chat, Slides, Calendar, and many more. From there, you now have a central location to manage all your Google Workspace APIs and view all of the aggregated metrics, quotas, credentials, and more for the APIs in use.

The APIs Explorer allows you to explore and test Google Workspace APIs without having to write any code. It's a great way to get familiar with the capabilities of the many Google Workspace APIs.

Apps Script

The eagerly awaited project history capability for Google Apps Script will soon be generally available. This feature allows users to view the list of versions created for the script, their content, and different changes between the selected version and the current version.

It was also announced that admins will be able to add an allowlist for URLs per domain to help safer access controls and control where their data can be sent externally.

The V8 runtime for Apps Script was launched back in 2020 and it enables developers to use modern JavaScript syntax and features. If you still have legacy scripts on the old Rhino runtime, now is the time to migrate them to V8.

AppSheet

We have been further improving AppSheet, our no-code solution builder, and announced multiple new features at I/O.

Later this year we will be launching Duet AI in AppSheet to make it easier than ever to create no-code apps for Google Workspace. Using a natural-language and conversational interface, users can build an app in AppSheet by simply describing their needs as a step-by-step conversation in chat.

Moving image of no-code app creation in AppSheet

The no-code Chat apps feature for AppSheet is generally available which can be used to quickly create Google Chat apps and publish them with 1-click.

AppSheet databases are also generally available. With this native database feature, you can organize data with structured columns and references directly in AppSheet.

Check out the Build a no-code app using the native AppSheet database and Add Chat to your AppSheet apps codelabs to get you started with these two new capabilities.

Google Workspace Marketplace

The Google Workspace Marketplace is where developers can distribute their Workspace integrations for users to find, install, and use. We launched the Intelligent Apps category which spotlights the AI-enabled apps developers build and helps users discover tools to work smarter and be more productive (eligibility criteria here).

Image of Intelligent Apps in Google Workspace

Start building today

If you want early access to the features in preview, sign up for the Developer Preview Program. Subscribe to the Google Workspace Developers YouTube channel for the latest news and video tutorials to kickstart your Workspace development journey.

We can’t wait to see what you will build on the Google Workspace platform.

Machine Learning Communities: Q2 ‘23 highlights and achievements

Posted by Nari Yoon, Bitnoori Keum, Hee Jung, DevRel Community Manager / Soonson Kwon, DevRel Program Manager

Let’s explore highlights and accomplishments of vast Google Machine Learning communities over the second quarter of 2023. We are enthusiastic and grateful about all the activities by the global network of ML communities. Here are the highlights!

ML Training Campaigns Summary

More than 35 communities around the world have hosted ML Campaigns distributed by the ML Developer Programs team during the first half of the year. Thank you all for your training efforts for the entire ML community!


Community Highlights


Keras

Screengrab of Tensorflow & Deep Learning Malaysia June 2023 Webinar - 'KerasCV for the Young and Restless'

Image Segmentation using Composable Fully-Convolutional Networks by ML GDE Suvaditya Mukherjee (India) is a Kears.io example explaining how to implement a fully-convolutional network with a VGG-16 backend and how to use it for performing image segmentation. His presentation, KerasCV for the Young and Restless (slides | video) at TFUG Malaysia and TFUG Kolkata was an introduction to KerasCV. He discussed how basic computer vision components work, why Keras is an important tool, and how KerasCV builds on top of the established TFX and Keras ecosystem.

[ML Story] My Keras Chronicles by ML GDE Aritra Roy Gosthipaty (India) summarized his story of getting into deep learning with Keras. He included pointers as to how one could get into the open source community. Plus, his Kaggle notebook, [0.11] keras starter: unet + tf data pipeline is a starter guide for Vesuvius Challenge. He and Subvaditya also shared Keras implementation of Temporal Latent Bottleneck Networks, proposed in the paper.

KerasFuse by ML GDE Ayse Ayyuce Demirbas (Portugal) is a Python library that combines the power of TensorFlow and Keras with various computer vision techniques for medical image analysis tasks. It provides a collection of modules and functions to facilitate the development of deep learning models in TensorFlow & Keras for tasks such as image segmentation, classification, and more.

TensorFlow at Google I/O 23: A Preview of the New Features and Tools by TFUG Ibadan explored the preview of the latest features and tools in TensorFlow. They covered a wide range of topics including Dtensor, KerasCV & KerasNLP, TF quantization API, and JAX2TF.

StableDiffusion- Textual Inversion app

StableDiffusion - Textual-Inversion implementation app by ML GDE Dimitre Oliveira (Brazil) is an example of how to implement code from research and fine-tunes it using the Textual Inversion process. It also provides relevant use cases for valuable tools and frameworks such as HuggingFace, Gradio, TensorFlow serving, and KerasCV.

In Understanding Gradient Descent and Building an Image Classifier in TF From Scratch, ML GDE Tanmay Bakshi (Canada) talked about how to develop a solid intuition for the fundamentals backing ML tech, and actually built a real image classification system for dogs and cats, from scratch in TF.Keras.

TensorFlow and Keras Implementation of the CVPR 2023 paper by Usha Rengaraju (India) is a research paper implementation of BiFormer: Vision Transformer with Bi-Level Routing Attention.

Smile Detection with Python, OpenCV, and Deep Learning by Rouizi Yacine is a tutorial explaining how to use deep learning to build a more robust smile detector using TensorFlow, Keras, and OpenCV.


Kaggle

Screengrab of ML Olympiad for Students - TopVistos USA

ML Olympiad for Students by GDSC UNINTER was for students and aspiring ML practitioners who want to improve their ML skills. It consisted of a challenge of predicting US working visa applications. 320+ attendees registered for the opening event, 700+ views on YouTube, 66 teams competed, and the winner got a 71% F1-score.

ICR | EDA & Baseline by ML GDE Ertuğrul Demir (Turkey) is a starter notebook for newcomers interested in the latest featured code competition on Kaggle. It got 200+ Upvotes and 490+ forks.

Screengrab of Compete More Effectively on Kaggle using Weights and Biases showing participants in the video call

Compete More Effectively on Kaggle using Weights and Biases by TFUG Hajipur was a meetup to explore techniques using Weights and Biases to improve model performance in Kaggle competitions. Usha Rengaraju (India) joined as a speaker and delivered her insights on Kaggle and strategies to win competitions. She shared tips and tricks and demonstrated how to set up a W&B account and how to integrate with Google Colab and Kaggle.

Skeleton Based Action Recognition: A failed attempt by ML GDE Ayush Thakur (India) is a discussion post about documenting his learnings from competing in the Kaggle competition, Google - Isolated Sign Language Recognition. He shared his repository, training logs, and ideas he approached in the competition. Plus, his article Keras Dense Layer: How to Use It Correctly) explored what the dense layer in Keras is and how it works in practice.


On-device ML

Google for developers Edu Program Tech Talks for Educators Add Machine Learning to your Android App June 22, 2023 12:00pm - 01:00 pm goo.gle/techtalksforedu with headshot of Pankaj Rai GDE - Android, Firebase, Machine Learning

Add Machine Learning to your Android App by ML GDE Pankaj Rai (India) at Tech Talks for Educators was a session on on-device ML and how to add ML capabilities to Android apps such as object detection and gesture detection. He explained capabilities of ML Kit, MediaPipe, TF Lite and how to use these tools. 700+ people registered for his talk.

In MediaPipe with a bit of Bard at I/O Extended Singapore 2023, ML GDE Martin Andrews (Singapore) shared how MediaPipe fits into the ecosystem, and showed 4 different demonstrations of MediaPipe functionality: audio classification, facial landmarks, interactive segmentation, and text classification.

Adding ML to our apps with Google ML Kit and MediaPipe by ML GDE Juan Guillermo Gomez Torres (Bolivia) introduced ML Kit & MediaPipe, and the benefits of on-device ML. In Startup Academy México (Google for Startups), he shared how to increase the value for clients with ML and MediaPipe.


LLM

Introduction to Google's PaLM 2 API by ML GDE Hannes Hapke (United States) introduced how to use PaLM2 and summarized major advantages of it. His another article The role of ML Engineering in the time of GPT-4 & PaLM 2 explains the role of ML experts in finding the right balance and alignment among stakeholders to optimally navigate the opportunities and challenges posed by this emerging technology. He did presentations under the same title at North America Connect 2023 and the GDG Portland event.

Image of a cellphone with ChatBard on the display in front of a computer display with Firebase PaLM in Cloud Firestore

ChatBard : An Intelligent Customer Service Center App by ML GDE Ruqiya Bin Safi (Saudi Arabia) is an intelligent customer service center app powered by generative AI and LLMs using PaLM2 APIs.

Bard can now code and put that code in Colab for you by ML GDE Sam Witteveen (Singapore) showed how Bard makes code. He runs a Youtube channel exploring ML and AI, with playlists such as Generative AI, Paper Reviews, LLMs, and LangChain.

Google’s Bard Can Write Code by ML GDE Bhavesh Bhatt (India) shows the coding capabilities of Bard, how to create a 2048 game with it, and how to add some basic features to the game. He also uploaded videos about LangChain in a playlist and introduced Google Cloud’s new course on Generative AI in this video.

Screengrab of GDG Deep Learning Course Attention Mechanisms and Transformers led by Ruqiya Bin Safi ML GDE & WTM Ambassador, @Ru0Sa

Attention Mechanisms and Transformers by GDG Cloud Saudi talked about Attention and Transformer in NLP and ML GDE Ruqiya Bin Safi (Saudi Arabia) participated as a speaker. Another event, Hands-on with the PaLM2 API to create smart apps(Jeddah) explored what LLMs, PaLM2, and Bard are, how to use PaLM2 API, and how to create smart apps using PaLM2 API.

Hands-on with Generative AI: Google I/O Extended [Virtual] by ML GDE Henry Ruiz (United States) and Web GDE Rabimba Karanjai (United States) was a workshop on generative AI showing hands-on demons of how to get started using tools such as PaLM API, Hugging Face Transformers, and LangChain framework.

Generative AI with Google PaLM and MakerSuite by ML GDE Kuan Hoong (Malaysia) at Google I/O Extended George Town 2023 was a talk about LLMs with Google PaLM and MakerSuite. The event hosted by GDG George Town and also included ML topics such as LLMs, responsible AI, and MLOps.

Intor to Gen AI with PaLM API and MakerSuite led by GUS Luis Gustavo and Tensorflow User Group Sao Paolo

Intro to Gen AI with PaLM API and MakerSuite by TFUG São Paulo was for people who want to learn generative AI and how Google tools can help with adoption and value creation. They covered how to start prototyping Gen AI ideas with MakerSuite and how to access advanced features of PaLM2 and PaLM API. The group also hosted Opening Pandora's box: Understanding the paper that revolutionized the field of NLP (video) and ML GDE Pedro Gengo (Brazil) and ML GDE Vinicius Caridá (Brazil) shared the secret behind the famous LLM and other Gen AI models.The group members studied Attention Is All You Need paper together and learned the full potential that the technology can offer.

Language models which PaLM can speak, see, move, and understand by GDG Cloud Taipei was for those who want to understand the concept and application of PaLM. ML GED Jerry Wu (Taiwan) shared the PaLM’s main characteristics, functions, and etc.

Flow chart illustrating flexible serving structure of stable diffusion

Serving With TF and GKE: Stable Diffusion by ML GDE Chansung Park (Korea) and ML GDE Sayak Paul (India) discusses how TF Serving and Kubernetes Engine can serve a system with online deployment. They broke down Stable Diffusion into main components and how they influence the subsequent consideration for deployment. Then they also covered the deployment-specific bits such as TF Serving deployment and k8s cluster configuration.

TFX + W&B Integration by ML GDE Chansung Park (Korea) shows how KerasTuner can be used with W&B’s experiment tracking feature within the TFX Tuner component. He developed a custom TFX component to push a full-trained model to the W&B Artifact store and publish a working application on Hugging Face Space with the current version of the model. Also, his talk titled, ML Infra and High Level Framework in Google Cloud Platform, delivered what MLOps is, why it is hard, why cloud + TFX is a good starter, and how TFX is seamlessly integrated with Vertex AI and Dataflow. He shared use cases from the past projects that he and ML GDE Sayak Paul (India) have done in the last 2 years.

Open and Collaborative MLOps by ML GDE Sayak Paul (India) was a talk about why openness and collaboration are two important aspects of MLOps. He gave an overview of Hugging Face Hub and how it integrates well with TFX to promote openness and collaboration in MLOps workflows.


ML Research

Paper review: PaLM 2 Technical Report by ML GDE Grigory Sapunov (UK) looked into the details of PaLM2 and the paper. He shares reviews of papers related to Google and DeepMind through his social channels and here are some of them: Model evaluation for extreme risks (paper), Faster sorting algorithms discovered using deep reinforcement learning (paper), Power-seeking can be probable and predictive for trained agents (paper).

Learning JAX in 2023: Part 3 — A Step-by-Step Guide to Training Your First Machine Learning Model with JAX by ML GDE Aritra Roy Gosthipaty (India) and ML GDE Ritwik Raha (India) shows how JAX can train linear and nonlinear regression models and the usage of PyTrees library to train a multilayer perceptron model. In addition, at May 2023 Meetup hosted by TFUG Mumbai, they gave a talk titled Decoding End to End Object Detection with Transformers and covered the architecture of the mode and the various components that led to DETR’s inception.

20 steps to train a deployed version of the GPT model on TPU by ML GDE Jerry Wu (Taiwan) shared how to use JAX and TPU to train and infer Chinese question-answering data.

Photo of the audience from the back of the room at Developer Space @Google Singapore during Multimodal Transformers - Custom LLMs, ViTs & BLIPs

Multimodal Transformers - Custom LLMs, ViTs & BLIPs by TFUG Singapore looked at what models, systems, and techniques have come out recently related to multimodal tasks. ML GDE Sam Witteveen (Singapore) looked into various multimodal models and systems and how you can build your own with the PaLM2 Model. In June, this group invited Blaise Agüera y Arcas (VP and Fellow at Google Research) and shared the Cerebra project and the research going on at Google DeepMind including the current and future developments in generative AI and emerging trends.


TensorFlow

Training a recommendation model with dynamic embeddings by ML GDE Thushan Ganegedara (Australia) explains how to build a movie recommender model by leveraging TensorFlow Recommenders (TFRS) and TensorFlow Recommenders Addons (TFRA). The primary focus was to show how the dynamic embeddings provided in the TFRA library can be used to dynamically grow and shrink the size of the embedding tables in the recommendation setting.

Screengrab of a tweet by Mathis Hammel showcasing his talk, 'How I built the most efficient deepfake detector in the world for $100'

How I built the most efficient deepfake detector in the world for $100 by ML GDE Mathis Hammel (France) was a talk exploring a method to detect images generated via ThisPersonDoesNotExist.com and even a way to know the exact time the photo was produced. Plus, his Twitter thread, OSINT Investigation on LinkedIn, investigated a network of fake companies on LinkedIn. He used a homemade tool based on a TensorFlow model and hosted it on Google Cloud. Technical explanations of generative neural networks were also included. More than 701K people viewed this thread and it got 1200+ RTs and 3100+ Likes.

Screengrab of Few-shot learning: Creating a real-time object detection using TensorFlow and python by ML GDE Hugo Zanini

Few-shot learning: Creating a real-time object detection using TensorFlow and Python by ML GDE Hugo Zanini (Brazil) shows how to take pictures of an object using a webcam, label the images, and train a few-shot learning model to run in real-time. Also, his article, Custom YOLOv7 Object Detection with TensorFlow.js explains how he trained a custom YOLOv7 model to run it directly in the browser in real time and offline with TensorFlow.js.

The Lord of the Words Transformation of a Sequence Encoder/Decoder Attention

The Lord of the Words : The Return of the experiments with DVC (slides) by ML GDE Gema Parreno Piqueras (Spain) was a talk explaining Transformers in the neural machine learning scenario, and how to use Tensorflow and DVC. In the project, she used Tensorflow Datasets translation catalog to load data from various languages, and TensorFlow Transformers library to train several models.

Accelerate your TensorFlow models with XLA (slides) and Ship faster TensorFlow models with XLA by ML GDE Sayak Paul (India) shared how to accelerate TensorFlow models with XLA in Cloud Community Days Kolkata 2023 and Cloud Community Days Pune 2023.

Setup of NVIDIA Merlin and Tensorflow for Recommendation Models by ML GDE Rubens Zimbres (Brazil) presented a review of recommendation algorithms as well as the Two Towers algorithm, and setup of NVIDIA Merlin on premises and on Vertex AI.


Cloud

AutoML pipeline for tabular data on VertexAI in Go by ML GDE Paolo Galeone (Italy) delved into the development and deployment of tabular models using VertexAI and AutoML with Go, showcasing the actual Go code and sharing insights gained through trial & error and extensive Google research to overcome documentation limitations.

Search engine architecture

Beyond images: searching information in videos using AI (slides) by ML GDE Pedro Gengo (Brazil) and ML GDE Vinicius Caridá (Brazil) showed how to create a search engine where you can search for information in videos. They presented an architecture where they transcribe the audio and caption the frames, convert this text into embeddings, and save them in a vector DB to be able to search given a user query.

The secret sauce to creating amazing ML experiences for developers by ML GDE Gant Laborde (United States) was a podcast sharing his “aha” moment, 20 years of experience in ML, and the secret to creating enjoyable and meaningful experiences for developers.

What's inside Google’s Generative AI Studio? by ML GDE Gad Benram (Portugal) shared the preview of the new features and what you can expect from it. Additionally, in How to pitch Vertex AI in 2023, he shared the six simple and honest sales pitch points for Google Cloud representatives on how to convince customers that Vertex AI is the right platform.

In How to build a conversational AI Augmented Reality Experience with Sachin Kumar, ML GDE Sachin Kumar (Qatar) talked about how to build an AR app combining multiple technologies like Google Cloud AI, Unity, and etc. The session walked through the step-by-step process of building the app from scratch.

Machine Learning on Google Cloud Platform led by Nitin Tiwari, Google Developer Expert - Machine Learning, Software Engineer @LTMIMindtree

Machine Learning on Google Cloud Platform by ML GDE Nitin Tiwari (India) was a mentoring aiming to provide students with an in-depth understanding of the processes involved in training an ML model and deploying it using GCP. In Building robust ML solutions with TensorFlow and GCP, he shared how to leverage the capabilities of GCP and TensorFlow for ML solutions and deploy custom ML models.

Data to AI on Google cloud: Auto ML, Gen AI, and more by TFUG Prayagraj educated students on how to leverage Google Cloud’s advanced AI technologies, including AutoML and generative AI.

What’s new in Google Wallet

Posted by Jose Ugia – Developer Relations Engineer

During Google I/O 2023, and in our recent blog post, we shared some new pass types and features we’re adding to Google Wallet and discussed how you can use them to build and protect your passes more easily, and enhance the experience for your customers.

Read on for a summary of what we covered during the event, or check out the recording of our session on YouTube: What's new in Google Pay and Google Wallet.


Secure pass information with private passes

We’re glad to expand Generic Passes, adding support for sensitive data with the new generic private pass API. Generic private passes on Google Wallet are one more way we’re protecting users’ information, keeping their sensitive digital items safe. These types of passes require you to verify it’s you to view private passes. To do that, they can use the fingerprint sensor, a passcode, or other authentication methods. This is helpful when you create a pass with sensitive information, for example in the healthcare industry.

The Google Wallet Developer Documentation contains detailed steps to help you add a private pass to Google Wallet.

image showing the definition for a private pass in JSON format.
Figure 1: The definition for a private pass in JSON format.

Enable fast pass development with Demo Mode

With Demo mode, you can go to the Google Pay & Wallet Console, sign up for API access, and integrate it with your code immediately after following the prerequisites available in the Google Wallet developer documentation.

When you sign up for a Google Wallet Issuer account for the first time, your account is automatically in Demo Mode. Demo mode includes the same features and functionality as publishing mode. To better differentiate between the demo and publish environments, passes created by issuers in Demo Mode contain visual elements to indicate their test nature. This distinction is removed when the issuer is approved to operate in publishing mode.

When you’re done with your tests and you’re ready to start issuing passes to your users, complete your business information and request publishing access from the Wallet API section in the console. Our console team will get in touch via email with additional instructions.

image illustrating Demo Mode in Google Pay & Wallet console.
Figure 2: Demo Mode in Google Pay & Wallet console.

Enhance security with rotating barcodes and Account-restricted passes

We are increasing the security of your passes with the introduction of a new API to rotate barcodes. With rotating barcodes you can pre-create a batch of barcodes and sync them with Google Wallet. The barcodes you create will rotate at a predefined interval and will be shown and updated in your user’s wallet. Rotating barcodes enable a range of use cases where issuers need to protect their passes, such as long duration transit tickets, events tickets, and more.

We’ve also announced Account Restricted passes, a new feature that lets issuers associate some pass objects with Google accounts. To use this feature, simply include the user’s email address in the pass object when you issue the pass. This triggers an additional check when a user attempts to add the pass to Google Wallet, which only succeeds if the email address specified in the pass matches the account of the currently logged-in user. Account Restricted passes let you protect your passes from theft, reselling, transfer or other restricted uses.

Design your passes using the pass builder

Making your passes consistent with your brand and design guidelines is a process that requires becoming acquainted with the Google Wallet API. During last year’s Google I/O, we introduced a dynamic template that accepts configuration to generate an approximate preview of your pass.

This year, we introduced the new generation of this tool, and graduate it into a fully functional pass builder. You can now configure and style your passes using a real-time preview to help you understand how passes are styled, and connect each visual element with their respective property in the API. The new pass builder also generates classes and objects in JSON format that you can use to make calls directly against the API, making it easier to configure your passes and removing the visual uncertainty of working with text-based configuration to style your passes. The new pass builder is available today for generic passes, tickets and pass types under retail.

image showing a demo of the new pass builder for the Google Wallet API.
Figure 3: A demo of the new pass builder for the Google Wallet API.

Get started with the Google Wallet API

Take a look at the documentation to start integrating Google Wallet today.

Learn more about the integration by taking a look at our sample source application in GitHub.

When you are ready, head over to the Google Pay & Wallet console and submit your integration for production access.

What’s next?

Shortly after Google I/O we announced 5 new ways to add more to Google Wallet. One of them is to save your ID to Google Wallet. And soon, you’ll be able to accept IDs from Google Wallet to securely and seamlessly verify a person's information. Some use cases include:

  • Age Verification: Request age to verify before purchasing age-restricted items or access to age-restricted venues.
  • Identity Verification: Request name to verify the person associated with an account.
  • Driving Privileges: Verify a person's ability to drive (e.g. when renting a car).

If you’re interested in using Google Wallet's in-app verification APIs, please fill out this form.

Google Chat APIs now generally available to all Workspace developers

Posted by Mike Rhemtulla, Product Manager

Programmatically manage spaces, memberships, messages, reactions and attachments


Last year, we announced new APIs in Developer Preview that enabled developers to programmatically create Chat spaces and add members on behalf of users. These APIs, in addition to the message, reaction, and attachments APIs are now generally available to all Workspace developers.

Google Chat has become a critical connectivity tool for hybrid organizations as well as a powerful tool for streamlining workflows. The Google Chat API allows developers to build user facing apps that integrate workflows into Chat and provide contextual information right into the conversation. Chat apps let users receive details and link previews directly from connected internal and third-party systems, and allows users to get up to speed asynchronously and solve issues quickly. For example, users can create or manage issues in Jira for Google Chat, all without leaving Chat.

Composite image of a Google Workspace user surrounded by mock ups of PagerDuty, AODocs, and Jira APIs in Google Workspace

Some developers are already leveraging the new APIs to encourage collaboration for their customers. LumApps, a leading intranet platform, enables its users to start a direct message in Google Chat from their user directory so those who are trying to find others based on job titles, roles, departments, or other attributes, can quickly start messaging each other.

Moving image of lumapps API being used in in Google Chat

New Google Chat APIs in the Developer Preview Program

In addition to the above Chat APIs now being generally available for all Workspace developers, existing Developer Preview participants can now access our newest feature: Developing Google Chat apps to import user data. If you currently use other enterprise messaging platforms and would like to bring your data into Google Chat, you can now create a Chat app to import existing messages, attachments, reactions, memberships, and more.

The key feature of the Developer Preview functionality are “import mode” spaces, which allow Chat apps to maintain historical timestamps for spaces and messages, to keep the context and ordering of the imported data as users expect. As well, import mode spaces suppress notifications and do not allow end users to access these spaces while legacy data is being imported.

As more users look to get things done within Google Chat, extending the capabilities of the product with apps will help users save time and get things done quicker. We encourage you to explore what you can do today with these resources: