Tag Archives: beginner

Meet the inaugural cohort of our Google for Startups Accelerator: AI First North America

Posted by Matt Ridenour, Head of Startup Developer Ecosystem - USA

Startups are at the forefront of developing solutions for some of humanity's most pressing challenges by using AI, driving breakthroughs across industries from healthcare to cybersecurity.

To help AI-focused startups scale quickly while building responsibly, we’re thrilled to introduce the inaugural class of the Google for Startups Accelerator: AI-First program in North America. This new program is for startups building AI solutions based in the U.S. and Canada. This is the first of several AI-focused programs we'll offer throughout the year in Europe, India and Brazil.

This equity-free program provides 10 weeks of hands-on mentorship and technical project support to startups using AI in their core service or product. Selected startups will collaborate with a cohort of top peer founders and engage with leaders across Google. The curriculum will give founders access to the latest AI tools (including Google’s own Gemini), and will also include workshops on tech and infrastructure, UX and product, growth, sales, leadership and OKRs.

Meet the inaugural class of Google for Startups Accelerator: AI-First, North America

We’re thrilled to introduce the 15 AI startups selected for this accelerator:

Aptori, San Jose, CA. Aptori assists developers and security engineers to build secure, high-quality software.

Augmend, Seattle, WA. Augmend is an AI native Loom made for developers, making it possible to share expertise, not just videos.

Backpack Healthcare, Elkridge, MA. Backpack Healthcare is a pediatric mental health company utilizing proprietary AI technology, an engagement platform, and live therapists to offer personalized care to patients.

BrainLogic AI, Menlo Park, CA. BrainLogic AI has built a localized AI agent that connects users and businesses through whatsapp.

Cicerai, The Woodlands, TX. Cicerai is an AI-native Legal Practice Management Platform, boosting productivity and enhancing quality.

CLIKA, San Jose, CA. CLIKA simplifies deploying AI models on diverse hardware by offering automated model compression and format compilation.

Easel AI, Inc., Los Angeles, CA. Easel AI is an AI avatar-based social chat app that runs on iMessage.

Findly, San Francisco, CA. Findly is a data visualization integrator using a natural language chat interface.

Glass Health, San Francisco, CA. Glass Health empowers clinicians with the best-in-class AI platform for clinical decision support.

Kodif, Sunnyvale, CA. Kodif is a low-code AI-powered automation platform for support agent workflows to resolve customer issues.

Liminal, Indianapolis, IN. Liminal empowers regulated enterprises to securely deploy and use generative AI, horizontally covering every interaction and use case.

Mbue, Austin, TX. Mbue leverages AI to instantly review architectural drawings, catching errors earlier and streamlining the process.

Modulo Bio, San Diego, CA. Modulo Bio is building a platform to discover therapeutics that prevent or reverse neurodegenerative diseases.

Rocket Doctor, Toronto, ON, Canada. Rocket Doctor is a digital health platform and marketplace that intelligently matches patients and clinicians in a telemedicine 2.0 approach.

Sibli, Montreal, QC, Canada. Sibli is a fintech platform that processes unstructured data and identifies key insights for financial analysts.

The program kicks off at Cloud Next 2024 and culminates with a high profile Demo Day in June for potential partners, customers and investors.

After graduation, startups join the dynamic Google for Startups accelerator community, where they receive ongoing support and have the opportunity to build lasting connections with like-minded founders, mentors and investors.

We are honored to partner with this cohort of companies through this accelerator and beyond, to advance their AI technologies. Register your interest to get updates on the program, and join us in celebrating these exceptional startups!

Gemma Family Expands with Models Tailored for Developers and Researchers

Posted by Tris Warkentin – Director, Product Management and Jane Fine - Senior Product Manager

In February we announced Gemma, our family of lightweight, state-of-the-art open models built from the same research and technology used to create the Gemini models. The community's incredible response – including impressive fine-tuned variants, Kaggle notebooks, integration into tools and services, recipes for RAG using databases like MongoDB, and lots more – has been truly inspiring.

Today, we're excited to announce our first round of additions to the Gemma family, expanding the possibilities for ML developers to innovate responsibly: CodeGemma for code completion and generation tasks as well as instruction following, and RecurrentGemma, an efficiency-optimized architecture for research experimentation. Plus, we're sharing some updates to Gemma and our terms aimed at improvements based on invaluable feedback we've heard from the community and our partners.


Introducing the first two Gemma variants


CodeGemma: Code completion, generation, and chat for developers and businesses

Harnessing the foundation of our Gemma models, CodeGemma brings powerful yet lightweight coding capabilities to the community. CodeGemma models are available as a 7B pretrained variant that specializes in code completion and code generation tasks, a 7B instruction-tuned variant for code chat and instruction-following, and a 2B pretrained variant for fast code completion that fits on your local computer. CodeGemma models have several advantages:

  • Intelligent code completion and generation: Complete lines, functions, and even generate entire blocks of code – whether you're working locally or leveraging cloud resources. 
  • Enhanced accuracy: Trained on 500 billion tokens of primarily English language data from web documents, mathematics, and code, CodeGemma models generate code that's not only more syntactically correct but also semantically meaningful, helping reduce errors and debugging time. 
  • Multi-language proficiency: Your invaluable coding assistant for Python, JavaScript, Java, and other popular languages. 
  • Streamlined workflows: Integrate a CodeGemma model into your development environment to write less boilerplate, and focus on interesting and differentiated code that matters – faster.
image of streamlined workflows within an exisitng AI dev project with CodeGemma integrated
This table compares the performance of CodeGemma with other similar models on both single and multi-line code completion tasks. Learn more in the technical report.

Learn more about CodeGemma in our report or try it in this quickstart guide.


RecurrentGemma: Efficient, faster inference at higher batch sizes for researchers

RecurrentGemma is a technically distinct model that leverages recurrent neural networks and local attention to improve memory efficiency. While achieving similar benchmark score performance to the Gemma 2B model, RecurrentGemma's unique architecture results in several advantages:

  • Reduced memory usage: Lower memory requirements allow for the generation of longer samples on devices with limited memory, such as single GPUs or CPUs. 
  • Higher throughput: Because of its reduced memory usage, RecurrentGemma can perform inference at significantly higher batch sizes, thus generating substantially more tokens per second (especially when generating long sequences). 
  • Research innovation: RecurrentGemma showcases a non-transformer model that achieves high performance, highlighting advancements in deep learning research. 
graph showing maximum thoughput when sampling from a prompt of 2k tokens on TPUv5e
This chart reveals how RecurrentGemma maintains its sampling speed regardless of sequence length, while Transformer-based models like Gemma slow down as sequences get longer.

To understand the underlying technology, check out our paper. For practical exploration, try the notebook, which demonstrates how to finetune the model.


Built upon Gemma foundations, expanding capabilities

Guided by the same principles of the original Gemma models, the new model variants offer:

  • Open availability: Encourages innovation and collaboration with its availability to everyone and flexible terms of use. 
  • High-performance and efficient capabilities: Advances the capabilities of open models with code-specific domain expertise and optimized design for exceptionally fast completion and generation. 
  • Responsible design: Our commitment to responsible AI helps ensure the models deliver safe and reliable results. 
  • Flexibility for diverse software and hardware:  
    • Both CodeGemma and RecurrentGemma: Built with JAX and compatible with JAX, PyTorch, , Hugging Face Transformers, and Gemma.cpp. Enable local experimentation and cost-effective deployment across various hardware, including laptops, desktops, NVIDIA GPUs, and Google Cloud TPUs.  
    • CodeGemma: Additionally compatible with Keras, NVIDIA NeMo, TensorRT-LLM, Optimum-NVIDIA, MediaPipe, and availability on Vertex AI. 
    • RecurrentGemma: Support for all the aforementioned products will be available in the coming weeks.

Gemma 1.1 update

Alongside the new model variants, we're releasing Gemma 1.1, which includes performance improvements. Additionally, we've listened to developer feedback, fixed bugs, and updated our terms to provide more flexibility.


Get started today

These first Gemma model variants are available in various places worldwide, starting today on Kaggle, Hugging Face, and Vertex AI Model Garden. Here's how to get started:

We invite you to try the CodeGemma and RecurrentGemma models and share your feedback on Kaggle. Together, let's shape the future of AI-powered content creation and understanding.

Battling Impersonation Scams: Monzo’s Innovative Approach

Posted by Todd Burner – Developer Relations Engineer

Cybercriminals continue to invest in advanced financial fraud scams, costing consumers more than $1 trillion in losses. According to the 2023 Global State of Scams Report by the Global Anti-Scam Alliance, 78 percent of mobile users surveyed experienced at least one scam in the last year. Of those surveyed, 45 percent said they’re experiencing more scams in the last 12 months.

ALT TEXT

The Global Scam Report also found that phone calls are the top method to initiate a scam. Scammers frequently employ social engineering tactics to deceive mobile users.

The key place these scammers want individuals to take action are in the tools that give access to their money. This means financial services are frequently targeted. As cybercriminals push forward with more scams, and their reach extends globally, it’s important to innovate in the response.

One such innovator is Monzo, who have been able to tackle scam calls through a unique impersonation detection feature in their app.

Monzo’s Innovative Approach

Founded in 2015, Monzo is the largest digital bank in the UK with presence in the US as well. Their mission is to make money work for everyone with an ambition to become the one app customers turn to to manage their entire financial lives.

Monzo logo

Impersonation fraud is an issue that the entire industry is grappling with and Monzo decided to take action and introduce an industry-first tool. An impersonation scam is a very common social engineering tactic when a criminal pretends to be someone else so they can encourage you to send them money. These scams often involve using urgent pretenses that involve a risk to a user’s finances or an opportunity for quick wealth. With this pressure, fraudsters convince users to disable security safeguards and ignore proactive warnings for potential malware, scams, and phishing.

Call Status Feature

Android offers multiple layers of spam and phishing protection for users including call ID and spam protection in the Phone by Google app. Monzo’s team wanted to enhance that protection by leveraging their in-house telephone systems. By integrating with their mobile application infrastructure they could help their customers confirm in real time when they’re actually talking to a member of Monzo’s customer support team in a privacy preserving way.

If someone calls a Monzo customer stating they are from the bank, their users can go into the app to verify this. In the Monzo app’s Privacy & Security section, users can see the ‘Monzo Call Status’, letting them know if there is an active call ongoing with an actual Monzo team member.

“We’ve built this industry-first feature using our world-class tech to provide an additional layer of comfort and security. Our hope is that this could stop instances of impersonation scams for Monzo customers from happening in the first place and impacting customers.” 

- Priyesh Patel, Senior Staff Engineer, Monzo’s Security team

Keeping Customers Informed

If a user is not talking to a member of Monzo’s customer support team they will see that as well as some helpful information. If the ‘Monzo call status’ is showing that you are not speaking to Monzo, the call status feature tells you to hang up right away and report it to their team. Their customers can start a scam report directly from the call status feature in the app.

screen grab of Monzo call status alerting the customer that the call the customer is receiving is not coming from Monzo. The customer is being advised to end the call

If a genuine call is ongoing the customer will see the information.

screen grab of Monzo call status confirming to the customer that the call the customer is receiving is coming from Monzo.

How does it work?

Monzo has integrated a few systems together to help inform their customers. A cross functional team was put together to build a solution.

Monzo’s in-house technology stack meant that the systems that power their app and customer service phone calls can easily communicate with one another. This allowed them to link the two and share details of customer service calls with their app, accurately and in real-time.

The team then worked to identify edge cases, like when the user is offline. In this situation Monzo recommends that customers don’t speak to anyone claiming they’re from Monzo until you’re connected to the internet again and can check the call status within the app.

screen grab of Monzo call status displaying warning while the customer is offline letting the customer know the app is unable to verify whether or not the call is coming from Monzo, so it is safer not to answer.

Results and Next Steps

The feature has proven highly effective in safeguarding customers, and received universal praise from industry experts and consumer champions.

“Since we launched Call Status, we receive an average of around 700 reports of suspected fraud from our customers through the feature per month. Now that it’s live and helping protect customers, we’re always looking for ways to improve Call Status - like making it more visible and easier to find if you’re on a call and you want to quickly check that who you’re speaking to is who they say they are.” 

- Priyesh Patel, Senior Staff Engineer, Monzo’s Security team

Final Advice

Monzo continues to invest and innovate in fraud prevention. The call status feature brings together both technological innovation and customer education to achieve its success, and gives their customers a way to catch scammers in action.

A layered security approach is a great way to protect users. Android and Google Play provide layers like app sandboxing, Google Play Protect, and privacy preserving permissions, and Monzo has built an additional one in a privacy-preserving way.

To learn more about Android and Play’s protections and to further protect your app check out these resources:

Tune Gemini Pro in Google AI Studio or with the Gemini API

Posted by Cher Hu, Product Manager and Saravanan Ganesh, Software Engineer for Gemini API

The following post was originally published in October 2023. Today, we've updated the post to share how you can easily tune Gemini models in Google AI Studio or with the Gemini API.


Last year, we launched Gemini 1.0 Pro, our mid-sized multimodal model optimized for scaling across a wide range of tasks. And with 1.5 Pro this year, we demonstrated the possibilities of what large language models can do with an experimental 1M context window. Now, to quickly and easily customize the generally available Gemini 1.0 Pro model (text) for your specific needs, we’ve added Gemini Tuning to Google AI Studio and the Gemini API.


What is tuning?

Developers often require higher quality output for custom use cases than what can be achieved through few-shot prompting. Tuning improves on this technique by further training the base model on many more task-specific examples—so many that they can’t all fit in the prompt.


Fine-tuning vs. Parameter Efficient Tuning

You may have heard about classic “fine-tuning” of models. This is where a pre-trained model is adapted to a particular task by training it on a smaller set of task-specific labeled data. But with today’s LLMs and their huge number of parameters, fine-tuning is complex: it requires machine learning expertise, lots of data, and lots of compute.

Tuning in Google AI Studio uses a technique called Parameter Efficient Tuning (PET) to produce higher-quality customized models with lower latency compared to few-shot prompting and without the additional costs and complexity of traditional fine-tuning. In addition, PET produces high quality models with as little as a few hundred data points, reducing the burden of data collection for the developer.


Why tuning?

Tuning enables you to customize Gemini models with your own data to perform better for niche tasks while also reducing the context size of prompts and latency of the response. Developers can use tuning for a variety of use cases including but not limited to:

  • Classification: Run natural language tasks like classifying your data into predefined categories, without needing tons of manual work or tools.
  • Information extraction: Extract structured information from unstructured data sources to support downstream tasks within your product.
  • Structured output generation: Generate structured data, such as tables, quickly and easily.
  • Critique Models: Use tuning to create critique models to evaluate output from other models.

Get started quickly with Google AI Studio


1. Create a tuned model

It’s easy to tune models in Google AI Studio. This removes any need for engineering expertise to build custom models. Start by selecting “New tuned model” in the menu bar on the left.

moving image showing how to create a tuned model in Google AI Studio by opening 'New Tuned Model' from the menu

2. Select data for tuning

You can tune your model from an existing structured prompt or import data from Google Sheets or a CSV file. You can get started with as few as 20 examples and to get the best performance, we recommend providing a dataset of at least 100 examples.

moving image showing how to select data for tuning in Google AI Studio by importing data

3. View your tuned model

View your tuning progress in your library. Once the model has finished tuning, you can view the details by clicking on your model. Start running your tuned model through a structured or freeform prompt.

moving image showing how to view your tuned model in Google AI Studio by importing data

4. Run your tuned model anytime

You can also access your newly tuned model by creating a new structured or freeform prompt and selecting your tuned model from the list of available models.

moving image demonstrating what it looks like to run your tuned model in Google AI Studio after importing data

Tuning with the Gemini API

Google AI Studio is the fastest and easiest way to start tuning Gemini models. You can also access the feature via the Gemini API by passing the training data in the API request when creating a tuned model. Learn more about how to get started here.

We’re excited about the possibilities that tuning opens up for developers and can’t wait to see what you build with the feature. If you’ve got some ideas or use cases brewing, share them with us on X (formerly known as Twitter) or Linkedin.

Gemini 1.5: Our next-generation model, now available for Private Preview in Google AI Studio

Posted by Jaclyn Konzelmann and Wiktor Gworek – Google Labs

Last week, we released Gemini 1.0 Ultra in Gemini Advanced. You can try it out now by signing up for a Gemini Advanced subscription. The 1.0 Ultra model, accessible via the Gemini API, has seen a lot of interest and continues to roll out to select developers and partners in Google AI Studio.

Today, we’re also excited to introduce our next-generation Gemini 1.5 model, which uses a new Mixture-of-Experts (MoE) approach to improve efficiency. It routes your request to a group of smaller "expert” neural networks so responses are faster and higher quality.

Developers can sign up for our Private Preview of Gemini 1.5 Pro, our mid-sized multimodal model optimized for scaling across a wide-range of tasks. The model features a new, experimental 1 million token context window, and will be available to try out in Google AI Studio. Google AI Studio is the fastest way to build with Gemini models and enables developers to easily integrate the Gemini API in their applications. It’s available in 38 languages across 180+ countries and territories.


1,000,000 tokens: Unlocking new use cases for developers

Before today, the largest context window in the world for a publicly available large language model was 200,000 tokens. We’ve been able to significantly increase this — running up to 1 million tokens consistently, achieving the longest context window of any large-scale foundation model. Gemini 1.5 Pro will come with a 128,000 token context window by default, but today’s Private Preview will have access to the experimental 1 million token context window.

We’re excited about the new possibilities that larger context windows enable. You can directly upload large PDFs, code repositories, or even lengthy videos as prompts in Google AI Studio. Gemini 1.5 Pro will then reason across modalities and output text.

  1. Upload multiple files and ask questions

    2. We’ve added the ability for developers to upload multiple files, like PDFs, and ask questions in Google AI Studio. The larger context window allows the model to take in more information — making the output more consistent, relevant and useful. With this 1 million token context window, we’ve been able to load in over 700,000 words of text in one go.

    moving image illustrating how Gemini 1.5 Pro can find and reason from particular quotes across the Apollo 11 PDF transcript.
    Gemini 1.5 Pro can find and reason from particular quotes across the Apollo 11 PDF transcript. 
    [Video sped up for demo purposes]

  2. Query an entire code repository

    3. The large context window also enables a deep analysis of an entire codebase, helping Gemini models grasp complex relationships, patterns, and understanding of code. A developer could upload a new codebase directly from their computer or via Google Drive, and use the model to onboard quickly and gain an understanding of the code.

    moving image illustrating how Gemini 1.5 Pro can help developers boost productivity when learning a new codebase.
    Gemini 1.5 Pro can help developers boost productivity when learning a new codebase.  
    [Video sped up for demo purposes]

  3. Add a full length video

    4. Gemini 1.5 Pro can also reason across up to 1 hour of video. When you attach a video, Google AI Studio breaks it down into thousands of frames (without audio), and then you can perform highly sophisticated reasoning and problem-solving tasks since the Gemini models are multimodal.

    moving image illustrating how Gemini 1.5 Pro can perform reasoning and problem-solving tasks across video and other visual inputs.
    Gemini 1.5 Pro can perform reasoning and problem-solving tasks across video and other visual inputs.  
    [Video sped up for demo purposes]

More ways for developers to build with Gemini models

In addition to bringing you the latest model innovations, we’re also making it easier for you to build with Gemini:

  • Easy tuning. Provide a set of examples, and you can customize Gemini for your specific needs in minutes from inside Google AI Studio. This feature rolls out in the next few days. 
  • New developer surfaces. Integrate the Gemini API to build new AI-powered features today with new Firebase Extensions, across your development workspace in Project IDX, or with our newly released Google AI Dart SDK. 
  • Lower pricing for Gemini 1.0 Pro. We’re also updating the 1.0 Pro model, which offers a good balance of cost and performance for many AI tasks. Today’s stable version is priced 50% less for text inputs and 25% less for outputs than previously announced. The upcoming pay-as-you-go plans for AI Studio are coming soon.

Since December, developers of all sizes have been building with Gemini models, and we’re excited to turn cutting edge research into early developer products in Google AI Studio. Expect some latency in this preview version due to the experimental nature of the large context window feature, but we’re excited to start a phased rollout as we continue to fine-tune the model and get your feedback. We hope you enjoy experimenting with it early on, like we have.

A New Approach to Real-Money Games on Google Play

Posted by Karan Gambhir – Director, Global Trust and Safety Partnerships

As a platform, we strive to help developers responsibly build new businesses and reach wider audiences across a variety of content types and genres. In response to strong demand, in 2021 we began onboarding a wider range of real-money gaming (RMG) apps in markets with pre-existing licensing frameworks. Since then, this app category has continued to flourish with developers creating new RMG experiences for mobile.

To ensure Google Play keeps up with the pace of developer innovation, while promoting user safety, we’ve since conducted several pilot programs to determine how to support more RMG operators and game types. For example, many developers in India were eager to bring RMG apps to more Android users, so we launched a pilot program, starting with Rummy and Daily Fantasy Sports (DFS), to understand the best way to support their businesses.

Based on the learnings from the pilots and positive feedback from users and developers, Google Play will begin supporting more RMG apps this year, including game types and operators not covered by an existing licensing framework. We’ll launch this expanded RMG support in June to developers for their users in India, Mexico, and Brazil, and plan to expand to users in more countries in the future.

We’re pleased that this new approach will provide new business opportunities to developers globally while continuing to prioritize user safety. It also enables developers currently participating in RMG pilots in India and Mexico to continue offering their apps on Play.

    • India pilot: For developers in the Google Play Pilot Program for distributing DFS and Rummy apps to users in India, we are extending the grace period for pilot apps to remain on Google Play until June 30, 2024 when the new policy will take effect. After that time, developers can distribute RMG apps on Google Play to users in India, beyond DFS and Rummy, in compliance with local laws and our updated policy.
    • Mexico pilot: For developers in the Google Play Pilot Program for DFS in Mexico, the pilot will end as scheduled on June 30, 2024, at which point developers can distribute RMG apps on Google Play to users in Mexico, beyond DFS, in compliance with local laws and our updated policy.

Google Play’s existing developer policies supporting user safety, such as requiring age-gating to limit RMG experiences to adults and requiring developers use geo-gating to offer RMG apps only where legal, remain unchanged and we’ll continue to strengthen them. In addition, Google Play will continue other key user safety and transparency efforts such as our expanded developer verification mechanisms.

With this policy update, we will also be evolving our service fee model for RMG to reflect the value Google Play provides and to help sustain the Android and Play ecosystems. We are working closely with developers to ensure our new approach reflects the unique economics and various developer earning models of this industry. We will have more to share in the coming months on our new policy and future expansion plans.

For developers already involved in the real-money gaming space, or those looking to expand their involvement, we hope this helps you prepare for the upcoming policy change. As Google Play evolves our support of RMG around the world, we look forward to helping you continue to delight users, grow your businesses, and launch new game types in a safe way.

Create smart chips for link previewing in Google Docs

Posted by Chanel Greco, Developer Advocate

Earlier this year, we announced the general availability of third-party smart chips in Google Docs. This new feature lets you add, view, and engage with critical information from third party apps directly in Google Docs. Several partners, including Asana, Atlassian, Figma, Loom, Miro, Tableau, and Whimsical, have already created smart chips so users can start embedding content from their apps directly into Docs. Sourabh Choraria, a Google Developer Expert for Google Workspace and hobby developer, published a third-party smart chip solution called “Link Previews” to the Google Workspace Marketplace. This app adds information to Google Docs from multiple commonly used SaaS tools.

In this blog post you will find out how you too can create your own smart chips for Google Docs.

Example of a smart chip that was created to preview information from an event management system
Example of a smart chip that was created to preview information from an event management system


Understanding how smart chips for third-party services work

Third-party smart chips are powered by Google Workspace Add-ons and can be published to the Google Workspace Marketplace. From there, an admin or user can install the add-on and it will appear in the sidebar on the right hand side of Google Docs.

The Google Workspace Add-on detects a service's links and prompts Google Docs users to preview them. This means that you can create smart chips for any service that has a publicly accessible URL. You can configure an add-on to preview multiple URL patterns, such as links to support cases, sales leads, employee profiles, and more. This configuration is done in the add-on’s manifest file.

{
  "timeZone": "America/Los_Angeles",
  "exceptionLogging": "STACKDRIVER",
  "runtimeVersion": "V8",
  "oauthScopes": [
    "https://www.googleapis.com/auth/workspace.linkpreview",
    "https://www.googleapis.com/auth/script.external_request"
  ],
  "addOns": {
    "common": {
      "name": "Preview Books Add-on",
      "logoUrl": "https://developers.google.com/workspace/add-ons/images/library-icon.png",
      "layoutProperties": {
        "primaryColor": "#dd4b39"
      }
    },
    "docs": {
      "linkPreviewTriggers": [
        {
          "runFunction": "bookLinkPreview",
          "patterns": [
            {
              "hostPattern": "*.google.*",
              "pathPrefix": "books"
            },
            {
              "hostPattern": "*.google.*",
              "pathPrefix": "books/edition"
            }
          ],
          "labelText": "Book",
          "logoUrl": "https://developers.google.com/workspace/add-ons/images/book-icon.png",
          "localizedLabelText": {
            "es": "Libros"
          }
        }
      ]
    }
  }
}
The manifest file contains the URL pattern for the Google Books API

The smart chip displays an icon and short title or description of the link's content. When the user hovers over the chip, they see a card interface that previews more information about the file or link. You can customize the card interface that appears when the user hovers over a smart chip. To create the card interface, you use widgets to display information about the link. You can also build actions that let users open the link or modify its contents. For a list of all the supported components for preview cards check the developer documentation.

function getBook(id) {
// Code to fetch the data from the Google Books API
}

function bookLinkPreview(event) {
 if (event.docs.matchedUrl.url) {
// Through getBook(id) the relevant data is fetched and used to build the smart chip and card

    const previewHeader = CardService.newCardHeader()
      .setSubtitle('By ' + bookAuthors)
      .setTitle(bookTitle);

    const previewPages = CardService.newDecoratedText()
      .setTopLabel('Page count')
      .setText(bookPageCount);

    const previewDescription = CardService.newDecoratedText()
      .setTopLabel('About this book')
      .setText(bookDescription).setWrapText(true);

    const previewImage = CardService.newImage()
      .setAltText('Image of book cover')
      .setImageUrl(bookImage);

    const buttonBook = CardService.newTextButton()
      .setText('View book')
      .setOpenLink(CardService.newOpenLink()
        .setUrl(event.docs.matchedUrl.url));

    const cardSectionBook = CardService.newCardSection()
      .addWidget(previewImage)
      .addWidget(previewPages)
      .addWidget(CardService.newDivider())
      .addWidget(previewDescription)
      .addWidget(buttonBook);

    return CardService.newCardBuilder()
    .setHeader(previewHeader)
    .addSection(cardSectionBook)
    .build();
  }
}
This is the Apps Script code to create a smart chip.
A smart chip hovered state.
A smart chip hovered state. The data displayed is fetched from the Google for Developers blog post URL that was pasted by the user.


For a detailed walkthrough of the code used in this post, please checkout the Preview links from Google Books with smart chips sample tutorial.



How to choose the technology for your add-on

When creating smart chips for link previewing, you can choose from two different technologies to create your add-on: Google Apps Script or alternate runtime.

Apps script is a rapid application development platform that is built into Google Workspace. This fact makes Apps Script a good choice for prototyping and validating your smart chip solution as it requires no pre-existing development environment. But Apps Script isn’t only for prototyping as some developers choose to create their Google Workspace Add-on with it and even publish it to the Google Workspace Marketplace for users to install.

If you want to create your smart chip with Apps Script you can check out the video below in which you learn how to build a smart chip for link previewing in Google Docs from A - Z. Want the code used in the video tutorial? Then have a look at the Preview links from Google Books with smart chips sample page.

If you prefer to create your Google Workspace Add-on using your own development environment, programming language, hosting, packages, etc., then alternate runtime is the right choice. You can choose from different programming languages like Node.js, Java, Python, and more. The hosting of the add-on runtime code can be on any cloud or on premise infrastructure as long as runtime code can be exposed as a public HTTP(S) endpoint. You can learn more about how to create smart chips using alternate runtimes from the developer documentation.



How to share your add-on with others

You can share your add-on with others through the Google Workspace Marketplace. Let’s say you want to make your smart chip solution available to your team. In that case you can publish the add-on to your Google Workspace organization, also known as a private app. On the other hand, if you want to share your add-on with anyone who has a Google Account, you can publish it as a public app.

To find out more about publishing to the Google Workspace Marketplace, you can watch this video that will walk you through the process.



Getting started

Learn more about creating smart chips for link previewing in the developer documentation. There you will find further information and code samples you can base your solution of. We can’t wait to see what smart chip solutions you will build.

Create smart chips for link previewing in Google Docs

Posted by Chanel Greco, Developer Advocate

Earlier this year, we announced the general availability of third-party smart chips in Google Docs. This new feature lets you add, view, and engage with critical information from third party apps directly in Google Docs. Several partners, including Asana, Atlassian, Figma, Loom, Miro, Tableau, and Whimsical, have already created smart chips so users can start embedding content from their apps directly into Docs. Sourabh Choraria, a Google Developer Expert for Google Workspace and hobby developer, published a third-party smart chip solution called “Link Previews” to the Google Workspace Marketplace. This app adds information to Google Docs from multiple commonly used SaaS tools.

In this blog post you will find out how you too can create your own smart chips for Google Docs.

Example of a smart chip that was created to preview information from an event management system
Example of a smart chip that was created to preview information from an event management system


Understanding how smart chips for third-party services work

Third-party smart chips are powered by Google Workspace Add-ons and can be published to the Google Workspace Marketplace. From there, an admin or user can install the add-on and it will appear in the sidebar on the right hand side of Google Docs.

The Google Workspace Add-on detects a service's links and prompts Google Docs users to preview them. This means that you can create smart chips for any service that has a publicly accessible URL. You can configure an add-on to preview multiple URL patterns, such as links to support cases, sales leads, employee profiles, and more. This configuration is done in the add-on’s manifest file.

{
  "timeZone": "America/Los_Angeles",
  "exceptionLogging": "STACKDRIVER",
  "runtimeVersion": "V8",
  "oauthScopes": [
    "https://www.googleapis.com/auth/workspace.linkpreview",
    "https://www.googleapis.com/auth/script.external_request"
  ],
  "addOns": {
    "common": {
      "name": "Preview Books Add-on",
      "logoUrl": "https://developers.google.com/workspace/add-ons/images/library-icon.png",
      "layoutProperties": {
        "primaryColor": "#dd4b39"
      }
    },
    "docs": {
      "linkPreviewTriggers": [
        {
          "runFunction": "bookLinkPreview",
          "patterns": [
            {
              "hostPattern": "*.google.*",
              "pathPrefix": "books"
            },
            {
              "hostPattern": "*.google.*",
              "pathPrefix": "books/edition"
            }
          ],
          "labelText": "Book",
          "logoUrl": "https://developers.google.com/workspace/add-ons/images/book-icon.png",
          "localizedLabelText": {
            "es": "Libros"
          }
        }
      ]
    }
  }
}
The manifest file contains the URL pattern for the Google Books API

The smart chip displays an icon and short title or description of the link's content. When the user hovers over the chip, they see a card interface that previews more information about the file or link. You can customize the card interface that appears when the user hovers over a smart chip. To create the card interface, you use widgets to display information about the link. You can also build actions that let users open the link or modify its contents. For a list of all the supported components for preview cards check the developer documentation.

function getBook(id) {
// Code to fetch the data from the Google Books API
}

function bookLinkPreview(event) {
 if (event.docs.matchedUrl.url) {
// Through getBook(id) the relevant data is fetched and used to build the smart chip and card

    const previewHeader = CardService.newCardHeader()
      .setSubtitle('By ' + bookAuthors)
      .setTitle(bookTitle);

    const previewPages = CardService.newDecoratedText()
      .setTopLabel('Page count')
      .setText(bookPageCount);

    const previewDescription = CardService.newDecoratedText()
      .setTopLabel('About this book')
      .setText(bookDescription).setWrapText(true);

    const previewImage = CardService.newImage()
      .setAltText('Image of book cover')
      .setImageUrl(bookImage);

    const buttonBook = CardService.newTextButton()
      .setText('View book')
      .setOpenLink(CardService.newOpenLink()
        .setUrl(event.docs.matchedUrl.url));

    const cardSectionBook = CardService.newCardSection()
      .addWidget(previewImage)
      .addWidget(previewPages)
      .addWidget(CardService.newDivider())
      .addWidget(previewDescription)
      .addWidget(buttonBook);

    return CardService.newCardBuilder()
    .setHeader(previewHeader)
    .addSection(cardSectionBook)
    .build();
  }
}
This is the Apps Script code to create a smart chip.
A smart chip hovered state.
A smart chip hovered state. The data displayed is fetched from the Google for Developers blog post URL that was pasted by the user.


For a detailed walkthrough of the code used in this post, please checkout the Preview links from Google Books with smart chips sample tutorial.



How to choose the technology for your add-on

When creating smart chips for link previewing, you can choose from two different technologies to create your add-on: Google Apps Script or alternate runtime.

Apps script is a rapid application development platform that is built into Google Workspace. This fact makes Apps Script a good choice for prototyping and validating your smart chip solution as it requires no pre-existing development environment. But Apps Script isn’t only for prototyping as some developers choose to create their Google Workspace Add-on with it and even publish it to the Google Workspace Marketplace for users to install.

If you want to create your smart chip with Apps Script you can check out the video below in which you learn how to build a smart chip for link previewing in Google Docs from A - Z. Want the code used in the video tutorial? Then have a look at the Preview links from Google Books with smart chips sample page.

If you prefer to create your Google Workspace Add-on using your own development environment, programming language, hosting, packages, etc., then alternate runtime is the right choice. You can choose from different programming languages like Node.js, Java, Python, and more. The hosting of the add-on runtime code can be on any cloud or on premise infrastructure as long as runtime code can be exposed as a public HTTP(S) endpoint. You can learn more about how to create smart chips using alternate runtimes from the developer documentation.



How to share your add-on with others

You can share your add-on with others through the Google Workspace Marketplace. Let’s say you want to make your smart chip solution available to your team. In that case you can publish the add-on to your Google Workspace organization, also known as a private app. On the other hand, if you want to share your add-on with anyone who has a Google Account, you can publish it as a public app.

To find out more about publishing to the Google Workspace Marketplace, you can watch this video that will walk you through the process.



Getting started

Learn more about creating smart chips for link previewing in the developer documentation. There you will find further information and code samples you can base your solution of. We can’t wait to see what smart chip solutions you will build.

Leverage Gemini in your Android apps

Posted by Dave Burke, VP of Engineering

Last week we unveiled our most capable foundation model, Gemini. Gemini is multimodal – it can accept both text and image inputs. We introduced a way for Android developers to leverage our smallest model Gemini Nano, on-device. This is available on select devices through AICore, a system service that handles model management, runtimes, safety features and more, simplifying the work for developers. And today, we're introducing new ways for Android developers to access the Gemini Pro model – which runs off-device, in Google's data centers.

App development with Gemini Pro

Gemini Pro is accessible via the Gemini API, and it’s our best model for scaling across a wide range of text and image reasoning tasks. To simplify integrating Gemini Pro, you can use the Google AI SDK, a client SDK for Android. This SDK enables direct integration from Android apps and removes the need for developers to build and manage their own backend infrastructure, reducing development costs and improving velocity.

Google AI Studio provides a streamlined way for developers to integrate the Gemini Pro model, craft prompts, create API keys, and effortlessly transform ideas into AI apps. Once you have developed your prompt in Google AI Studio, you can simply click on the “Get code” action to generate a Kotlin code snippet, and start integrating Gemini today using the Google AI SDK for Android.

ALT TEXT
Generate Kotlin code for the Gemini API in Google AI Studio

We are also making it easier for developers to use the Gemini API directly in the latest preview version of Android Studio. We’re introducing a new project template for developers to get started with the Google AI SDK for Android right away. You’ll benefit from Android Studio’s enhanced code completion and lint checkers, helping with API keys and security.

ALT TEXT
New Project template for AI in Android Studio

To leverage the new template in Android Studio, start a new project through File > New > New Project and pick the Gemini API starter template. This template provides a pre-configured project with the necessary code to use the Gemini API. After choosing a project name and location, you will be prompted to generate an API key in Google AI Studio, and asked to enter it in Android Studio. Android Studio will automatically set up the project for you with the Gemini API connection, simplifying your workflow.

Alternatively, you can import the generative AI code sample and set it up in Android Studio through File > New > Import Sample, and searching for "Generative AI Sample".

Get started building AI-powered features and Android apps using Gemini Pro.

It’s time for developers and enterprises to build with Gemini Pro

Posted by Jeanine Banks – VP/GM, Developer X and Developer Relations, and Burak Gokturk – VP/GM, Cloud AI and Industry Solutions

Learn more about how to integrate Gemini Pro into your app or business at ai.google.dev

This article is also published on the Keyword blog.

Last week, we announced Gemini, our largest and most capable AI model and the next step in our journey to make AI more helpful for everyone. It comes in three sizes: Ultra, Pro and Nano. We've already started rolling out Gemini in our products: Gemini Nano is in Android, starting with Pixel 8 Pro, and a specifically tuned version of Gemini Pro is in Bard.

Today, we’re making Gemini Pro available for developers and enterprises to build for your own use cases, and we’ll be further fine-tuning it in the weeks and months ahead as we listen and learn from your feedback.


Gemini Pro is available today

The first version of Gemini Pro is now accessible via the Gemini API and here’s more about it:

  • Gemini Pro outperforms other similarly-sized models on research benchmarks.
  • Today’s version comes with a 32K context window for text, and future versions will have a larger context window.
  • It’s free to use right now, within limits, and it will be competitively priced.
  • It comes with a range of features: function calling, embeddings, semantic retrieval and custom knowledge grounding, and chat functionality.
  • It supports 38 languages across 180+ countries and territories worldwide.
  • In today’s release, Gemini Pro accepts text as input and generates text as output. We’ve also made a dedicated Gemini Pro Vision multimodal endpoint available today that accepts text and imagery as input, with text output.
  • SDKs are available for Gemini Pro to help you build apps that run anywhere. Python, Android (Kotlin), Node.js, Swift and JavaScript are all supported.
A screenshot of a code snippet illustrating the SDKs supporting Gemini.
Gemini Pro has SDKs that help you build apps that run anywhere.

Google AI Studio: The fastest way to build with Gemini

Google AI Studio is a free, web-based developer tool that enables you to quickly develop prompts and then get an API key to use in your app development. You can sign into Google AI Studio with your Google account and take advantage of the free quota, which allows 60 requests per minute — 20x more than other free offerings. When you’re ready, you can simply click on “Get code” to transfer your work to your IDE of choice, or use one of the quickstart templates available in Android Studio, Colab or Project IDX. To help us improve product quality, when you use the free quota, your API and Google AI Studio input and output may be accessible to trained reviewers. This data is de-identified from your Google account and API key.

A screen recording of a developer using Google AI Studio.
Google AI Studio is a free, web-based developer tool that enables you to quickly develop prompts and then get an API key to use in your app development.

Build with Vertex AI on Google Cloud

When it's time for a fully-managed AI platform, you can easily transition from Google AI Studio to Vertex AI, which allows for customization of Gemini with full data control and benefits from additional Google Cloud features for enterprise security, safety, privacy and data governance and compliance.

With Vertex AI, you will have access to the same Gemini models, and will be able to:

  • Tune and distill Gemini with your own company’s data, and augment it with grounding to include up-to-minute information and extensions to take real-world actions.
  • Build Gemini-powered search and conversational agents in a low code / no code environment, including support for retrieval-augmented generation (RAG), blended search, embeddings, conversation playbooks and more.
  • Deploy with confidence. We never train our models on inputs or outputs from Google Cloud customers. Your data and IP are always your data and IP.

To read more about our new Vertex AI capabilities, visit the Google Cloud blog.


Gemini Pro pricing

Right now, developers have free access to Gemini Pro and Gemini Pro Vision through Google AI Studio, with up to 60 requests per minute, making it suitable for most app development needs. Vertex AI developers can try the same models, with the same rate limits, at no cost until general availability early next year, after which there will be a charge per 1,000 characters or per image across Google AI Studio and Vertex AI.

A screenshot of input and output prices for Gemini Pro.
Big impact, small price: Because of our investments in TPUs, Gemini Pro can be served more efficiently.

Looking ahead

We’re excited that Gemini is now available to developers and enterprises. As we continue to fine-tune it, your feedback will help us improve. You can learn more and start building with Gemini on ai.google.dev, or use Vertex AI’s robust capabilities on your own data with enterprise-grade controls.

Early next year, we’ll launch Gemini Ultra, our largest and most capable model for highly complex tasks, after further fine-tuning, safety testing and gathering valuable feedback from partners. We’ll also bring Gemini to more of our developer platforms like Chrome and Firebase.

We’re excited to see what you build with Gemini.