If you’ve been exploring recently-launched consumer generative AI tools like Bard and thinking about how to build similar experiences for your business, Generative AI App Builder, or Gen App Builder for short, is here to get you started.

Gen App Builder is part of Google Cloud’s recently announced generative AI offerings and lets developers, even those with limited machine learning skills, quickly and easily tap into the power of Google’s foundation models, search expertise, and conversational AI technologies to create enterprise-grade generative AI applications. 

“Google Cloud’s leading AI technology enables STARZ customers to discover more relevant content, increasing engagement with, and the likelihood of completing the content served to them,” says Robin Chacko, EVP Direct-to-Consumer, STARZ. “We’re excited about how generative AI-powered search will help users find the most relevant content even easier and faster.”

Gen App Builder is exciting because unlike most existing generative AI offerings for developers, it offers an orchestration layer that abstracts the complexity of combining various enterprise systems with generative AI tools to create a smooth, helpful user experience. Gen App Builder provides step-by-step orchestration of search and conversational applications with pre-built workflows for common tasks like onboarding, data ingestion, and customization, making it easy for developers to set up and deploy their apps. With Gen App Builder developers can: 

• Build in minutes or hours. With access to Google’s no-code conversational and search tools powered by foundation models, organizations can get started with a few clicks and quickly build high-quality experiences that can be integrated into their applications and websites. 
• Combine the power of foundation models with information retrieval to find relevant, personalized information. Enterprises can build apps that understand user intent via natural language, and surface the right information with associated citations and attributions from a company’s public and private data. They can also fully control what data their applications access and the content or topics they want to address.
• Build multimodal apps that can respond with text, images, and other media. Gen App Builder supports not just text, but also other modalities such as images and videos. It allows developers to build apps using a combination of text and images as inputs to find information across documents, photos, and video content, enabling richer customer interactions. 
• Combine natural conversations with structured flows. Developers can granularly blend the output of foundation models with controls to ground answers in enterprise content, and step-by-step conversation orchestration to guide customers to the right answers.
• Provide the ability to transact and connect to third party apps and services. Gen App Builder makes it simple to create digital assistants and bots that not only serve content, but also connect to purchasing and provisioning systems to enable transactions from the conversational UI, and escalate customer conversations to a human agent when the context demands. 

A new generation of conversational AI experiences and assistants 

Consumers of enterprise applications expect to interact with technology in a seamless, conversational way to quickly find the information they need and act on it. Gen App Builder can help reinvent these customer and employee experiences by ingesting large, complex datasets that are specific to your company–from websites, documents, and transactional systems like billing and inventory, to emails, chat conversations, and more. These AI-powered apps can synthesize information across all of these sources to provide specific, actionable responses, using only the data you have provided. 

Some of the most popular uses are in customer service, where generative apps can contribute to increasing revenue, customer satisfaction, and customer loyalty. For example, if a retail customer reaches out to modify an order, a virtual agent can help them change it to another product. The customer doesn’t even need to provide the new product name—they can just upload an image and let the agent guide them through the rest. Watch this demo to see how a retail chatbot can use multimodal capabilities to help a consumer navigate various options on the website, including giving the customer ideas on how to use the product and even helping them complete the purchase with the ability to transact within the conversational UI. This scenario could apply to multiple industries and use cases, ranging from consumer goods and public services, to finance and internal corporate systems like intranets.

Combining the power of Google-quality search with foundation models

Finding the right information from data across the organization is a critical requirement within any enterprise. Yet it can be challenging to build high-quality enterprise search experiences with existing tools. Current systems struggle to understand user intent, are difficult to implement and customize, and don’t provide a high-quality user experience. 

One of the most exciting features of Gen App Builder is the ability to combine the power of Google-quality search with generative AI to help enterprises find the most relevant and personalized information when they need it. With Gen App Builder, enterprises can build conversational search experiences across their public and private data in minutes or hours with no coding experience. 

Enabling multimodal search across text, images and video within the enterprise is a key aspect of the search experiences in Gen App Builder. In addition to providing high-quality search results, Gen App Builder can conveniently summarize the results and provide corresponding citations in a natural, human-like fashion. Gen App Builder also automatically extracts key information from the data and enables personalized results for users. Watch this demo to see how these capabilities can come together to transform the search experience for employees at a financial services firm. The ability to integrate Google-quality search within the enterprise’s applications means they can enjoy a new level of data utilization, drive increased process efficiencies, and provide delightful experiences to their employees and customers.

“Customers have been shopping at Macy’s for generations. Being able to deliver 360° personalization and contextual recommendations will help ensure that Macy’s is still providing future generations of shoppers with a seamless, exceptional experience,” said Bennett Fox-Glassman, Senior Vice-President, Customer Journey, Macy’s. “We’ve already realized an increase in revenue per visit and conversion rates had great success using Google Cloud’s AI technology and are looking forward to exploring how these latest announcements bring together Natural Language Processing and Generative AI capabilities to deliver next-gen search and conversational experiences for our customers.”

The ability to intuitively interact with complex data across a variety of sources allows organizations to better serve their customers and deliver more relevant offerings. Combined with conversational and fulfillment abilities, the potential for improving customer engagement and employee productivity is immense. We’re excited to see how developers and enterprises use a mix of these capabilities to power new experiences and revenue opportunities.

If you’re interested in a closer look at the Gen App Builder, tune into this session at the Data Cloud & AI Summit. Take a step forward to getting hands-on and join the waitlist for our trusted tester program. And finally, bookmark our generative AI landing page to keep abreast of the latest news, updates and possibilities from this exciting new world of Gen Apps.

Posted by Jeff Dean, Senior Fellow and SVP of Google Research, on behalf of the entire Google Research community

Over the last several decades, I’ve witnessed a lot of change in the fields of machine learning (ML) and computer science. Early approaches, which often fell short, eventually gave rise to modern approaches that have been very successful. Following that long-arc pattern of progress, I think we’ll see a number of exciting advances over the next several years, advances that will ultimately benefit the lives of billions of people with greater impact than ever before. In this post, I’ll highlight five areas where ML is poised to have such impact. For each, I’ll discuss related research (mostly from 2021) and the directions and progress we’ll likely see in the next few years.

· Trend 1: More Capable, General-Purpose ML Models
· Trend 2: Continued Efficiency Improvements for ML
· Trend 3: ML Is Becoming More Personally and Communally Beneficial
· Trend 4: Growing Benefits of ML in Science, Health and Sustainability
· Trend 5: Deeper and Broader Understanding of ML

Trend 1: More Capable, General-Purpose ML Models

Researchers are training larger, more capable machine learning models than ever before. For example, just in the last couple of years models in the language domain have grown from billions of parameters trained on tens of billions of tokens of data (e.g., the 11B parameter T5 model), to hundreds of billions or trillions of parameters trained on trillions of tokens of data (e.g., dense models such as OpenAI’s 175B parameter GPT-3 model and DeepMind’s 280B parameter Gopher model, and sparse models such as Google’s 600B parameter GShard model and 1.2T parameter GLaM model). These increases in dataset and model size have led to significant increases in accuracy for a wide variety of language tasks, as shown by across-the-board improvements on standard natural language processing (NLP) benchmark tasks (as predicted by work on neural scaling laws for language models and machine translation models).

Many of these advanced models are focused on the single but important modality of written language and have shown state-of-the-art results in language understanding benchmarks and open-ended conversational abilities, even across multiple tasks in a domain. They have also shown exciting capabilities to generalize to new language tasks with relatively little training data, in some cases, with few to no training examples for a new task. A couple of examples include improved long-form question answering, zero-label learning in NLP, and our LaMDA model, which demonstrates a sophisticated ability to carry on open-ended conversations that maintain significant context across multiple turns of dialog.

Transformer models are also having a major impact in image, video, and speech models, all of which also benefit significantly from scale, as predicted by work on scaling laws for visual transformer models. Transformers for image recognition and for video classification are achieving state-of-the-art results on many benchmarks, and we’ve also demonstrated that co-training models on both image data and video data can improve performance on video tasks compared with video data alone. We’ve developed sparse, axial attention mechanisms for image and video transformers that use computation more efficiently, found better ways of tokenizing images for visual transformer models, and improved our understanding of visual transformer methods by examining how they operate compared with convolutional neural networks. Combining transformer models with convolutional operations has shown significant benefits in visual as well as speech recognition tasks.

The outputs of generative models are also substantially improving. This is most apparent in generative models for images, which have made significant strides over the last few years. For example, recent models have demonstrated the ability to create realistic images given just a category (e.g., “irish setter” or “streetcar”, if you desire), can “fill in” a low-resolution image to create a natural-looking high-resolution counterpart (“computer, enhance!”), and can even create natural-looking aerial nature scenes of arbitrary length. As another example, images can be converted to a sequence of discrete tokens that can then be synthesized at high fidelity with an autoregressive generative model.

Because these are powerful capabilities that come with great responsibility, we carefully vet potential applications of these sorts of models against our AI Principles.

Beyond advanced single-modality models, we are also starting to see large-scale multi-modal models. These are some of the most advanced models to date because they can accept multiple different input modalities (e.g., language, images, speech, video) and, in some cases, produce different output modalities, for example, generating images from descriptive sentences or paragraphs, or describing the visual content of images in human languages. This is an exciting direction because like the real world, some things are easier to learn in data that is multimodal (e.g., reading about something and seeing a demonstration is more useful than just reading about it). As such, pairing images and text can help with multi-lingual retrieval tasks, and better understanding of how to pair text and image inputs can yield improved results for image captioning tasks. Similarly, jointly training on visual and textual data can also help improve accuracy and robustness on visual classification tasks, while co-training on image, video, and audio tasks improves generalization performance for all modalities. There are also tantalizing hints that natural language can be used as an input for image manipulation, telling robots how to interact with the world and controlling other software systems, portending potential changes to how user interfaces are developed. Modalities handled by these models will include speech, sounds, images, video, and languages, and may even extend to structured data, knowledge graphs, and time series data.

Often these models are trained using self-supervised learning approaches, where the model learns from observations of “raw” data that has not been curated or labeled, e.g., language models used in GPT-3 and GLaM, the self-supervised speech model BigSSL, the visual contrastive learning model SimCLR, and the multimodal contrastive model VATT. Self-supervised learning allows a large speech recognition model to match the previous Voice Search automatic speech recognition (ASR) benchmark accuracy while using only 3% of the annotated training data. These trends are exciting because they can substantially reduce the effort required to enable ML for a particular task, and because they make it easier (though by no means trivial) to train models on more representative data that better reflects different subpopulations, regions, languages, or other important dimensions of representation.

All of these trends are pointing in the direction of training highly capable general-purpose models that can handle multiple modalities of data and solve thousands or millions of tasks. By building in sparsity, so that the only parts of a model that are activated for a given task are those that have been optimized for it, these multimodal models can be made highly efficient. Over the next few years, we are pursuing this vision in a next-generation architecture and umbrella effort called Pathways. We expect to see substantial progress in this area, as we combine together many ideas that to date have been pursued relatively independently.

Large Machine Learning (ML) models – such as large language models, generative AI, and vision models – are dramatically increasing the number of trainable parameters and are achieving state-of-the-art results. Increasing the number of parameters results in the model being too large to fit on a single VM instance thus demands distributed compute to spread the model across multiple nodes. Google Kubernetes Engine (GKE) has built-in support for NCCL Fast Socket, to help improve the time to train large ML models with distributed, multi-node clusters.

Enterprises are looking for faster and cheaper performance to train their ML models. With distributed training, communicating gradients across nodes is a performance bottleneck. Optimizing inter-node latency is critical to reduce training time and costs. Distributed training uses collective communication as a transport layer over the network between the multiple hosts. Collective communication primitives such as all-gather, all-reduce, broadcast, reduce, reduce-scatter, and point-to-point send and receive are used in distributed training in Machine Learning. 

The NVIDIA Collective Communication Library (NCCL) is commonly used by popular ML frameworks such as TensorFlow and PyTorch. It is a highly optimized implementation for high bandwidth and low latency between NVIDIA GPUs. Google developed a proprietary version of NCCL called NCCL Fast Socket to optimize performance for deep learning on Google Cloud.

NCCL Fast Socket uses a number of techniques to achieve better and more consistent NCCL performance.

• Use of multiple network flows to attain maximum throughput. NCCL Fast Socket introduces additional optimizations over NCCL’s built-in multi-stream support, including better overlapping of multiple communication requests.
• Dynamic load balancing of multiple network flows. NCCL can adapt to changing network and host conditions. With this optimization, straggler network flows will not significantly slow down the entire NCCL collective operation.
• Integration with Google Cloud’s Andromeda virtual network stack.This increases overall network throughput by avoiding contentions in virtual machines (VMs).

We tested (NVIDIA NCCL tests) the performance of NCCL Fast Socket vs NCCL on various machine shapes with 2 node GKE clusters.

The following chart shows the results. For each machine shape, the NCCL performance without Fast Socket is normalized to 1. In each case, using NCCL Fast Socket demonstrated increased performance in a range of 1.3 to 2.6 times faster internetwork communication speed.

As a built-in feature, GKE users can take advantage of NCCL Fast Socket without changing or recompiling their applications, ML frameworks (such as TensorFlow or PyTorch), or even the NCCL library itself. To start using NCCL Fast Socket, create a node pool that uses the plugin with the --enable-fast-socket and --enable-gvnic flags. You can also update an existing node pool using gcloud container node-pools update.

gcloud container node-pools create NODEPOOL_NAME \
    --accelerator type=ACCELERATOR_TYPE, count=ACCELERATOR_COUNT \
    --machine-type=MACHINE_TYPE \
    --cluster=CLUSTER_NAME \
    --enable-fast-socket \
    --enable-gvnic

To achieve better network throughput with NCCL, Google Virtual NICs (gVNICs) must be enabled when creating VM instances. For detailed instructions on how to use gVNICs, please refer to the gVNIC guide. 

To verify that NCCL Fast Socket has been enabled, view the kube-system pods:

kubectl get pods -n kube-system

And the output should b similar to:

NAME                         READY   STATUS    RESTARTS   AGE
fast-socket-installer-qvfdw  2/2     Running   0          10m
fast-socket-installer-rtjs4  2/2     Running   0          10m
fast-socket-installer-tm294  2/2     Running   0          10m

To learn more visit GKE NCCL Fast Socket documentation. We look forward to hearing how NCCL Fast Socket improves your ML Training experience on GKE.

Many of our customers want to know how to choose a technology stack for solving problems with machine learning (ML). There are many choices for these solutions available, some that you can build and some that you can buy. We’ll be focusing on the build side here, exploring the various options and the problems they solve, along with our recommendations. 

The best ML applications are trained with the largest amount of data

But first, keep in mind an important concept: the quality of your ML model improves with the size of your data. Dramatic ML performance and accuracy are driven by improvements in data size, as shown in the graph below. This is a text model, but the same principles hold for all kinds of ML models.

The X axis represents the size of the data set and the Y axis is the error rate. As the size of the data set increases, the error rate drops. But notice something critical about the size of the data set — the x-axis is2^20, 2^21, 2^ 22, etc. In other words, each new tic here is a doubling of the data set size. To get a linear decrease in your error rate you need to exponentially increase the size of your data set. 

The blue curve in the graph represents a slightly more sophisticated ML model than the orange curve. Suppose you are deciding between two choices: create a better model or double the data set size. Assuming that these two choices cost the same, it’s better to keep gathering more data. It’s only when improvements due to data size increases start to plateau that it becomes necessary to build a better model. 

Secondly, ML systems need to be retrained for new situations. For example, if you have a recommendation system in YouTube and you want to provide recommendations in Google Now, you can’t use the same recommendations model. You have to train it in the second instance on the recommendations you want to make in Google Now. So even though the model, the code, and the principles are the same, you have to retrain the model with new data for new situations. 

Now, let’s combine these two concepts: you get a better ML model when you have more data, and an ML model typically needs to be retrained for a new situation. You have a choice of either spending your time building an ML model or buying a vendor’s off-the-shelf model. 

To answer the question of whether to buy or whether to build, first determine if the buyable model is solving the same problem that you want to solve. Has it been trained on the same input and on similar labels? Let’s say you’re trying to do a product search, and the model has been trained on catalog images as inputs. But you want to do a product search based on users’ mobile phone photographs of the products. The model that was trained on catalog images won’t work on your mobile phone photographs, and you’d have to build a new model. 

But let’s say you’re considering a vendor’s translation model that’s been trained on speeches in the European Parliament. If you want to translate similar speeches, the model works well as it uses the same kind of data. 

The next question to ask: does the vendor have more data than you do? If the vendor has trained their model on speeches in the European Parliament but you have access to more speech data than they have, you should build. If they have more data, then we recommend buying their model. 

Bottom line: buy the vendor’s solution if it’s trained on the same problem and has access to more data than you do. 

Technology stack for common ML use cases

If you need to build, what is the technology stack you need? What are the skills your people need to develop? This depends on the type of problem you are solving.  There are four broad categories of ML applications: predictive analytics, unstructured data, automation, and personalization. The recommended technology stack for each is slightly different. 

Predictive analytics

Predictive analytics includes detecting fraud, predicting click-through rates, and forecasting demand. 

Step one: build an enterprise data warehouse
Here, your data set is primarily structured data, so our recommended first step is to store your data in an enterprise data warehouse (EDW). Your EDW is a source of training examples and product histories tracked over time, and can break down silos and gather data from throughout your organization.

Step two: get good at data analytics
Next, you’d build a data culture, get skilled at data analytics, start to build dashboards, and enable data-driven decisions. At this point, you have all of the data and you know which pieces are trustworthy. 

Step three: build ML
From your EDW, you can build your models using SQL pipelines. We recommend using BigQuery ML when doing ML with the data in your EDW. If you want to build a more sophisticated model, you can train TensorFlow/Keras models on BigQuery data. A third option is AutoML tables for state-of-the-art accuracy and for building online microservices.

Unstructured data

Examples of how our customers use ML to gain insights from unstructured data include annotating videos, identifying eye diseases, and triaging emails. Unstructured data can include videos, images, natural language, and text. Deep learning has revolutionized the way we do ML on unstructured data, whether you’re looking at language understanding, image classification, or speech-to-text. 

For unstructured data, the models you use will  employ deep learning. Here, the ROI heavily favors using AutoML. The amount of time that you’d spend trying to create a new ML model from scratch is almost never worth it. You can spend your money more effectively collecting more data than trying to get a slightly better model. Regardless of the type of unstructured data, our recommendation is to use AutoML for small and medium size data sizes.

But AutoML has a limit to scale. At some point, the size of your data set is going to be so large that architecture search is going to get really expensive. At that point, you may want to go to a best-of-breed model with custom retraining from TensorFlow Hub, for example.  If you have data sets that are in the millions of examples, you can build your own custom neural network (NN) architectures. But determine if your data set size has started to plateau, by plotting a graph similar to the one at the top of this post. Build a custom NN architecture only after you’ve plateaued, where increasing amounts of data won’t give you a better model. 

Automation

Some examples of how customers are using ML for automation include scheduling maintenance, counting retail footfall, and scanning medical forms. The key thing to keep in mind as you pick a technology stack for these problems is that you’re not building just one ML model. If you want to schedule maintenance orwant to reject transactions, for example, you’ll need to train multiple linked models. 

Instead of individual models, think in terms of ML pipelines, which you can orchestrate using all of the technologies already mentioned. Then you have three choices for operationalizing, with three levels of sophistication.

1. Vertex AI has turnkey serverless training and batch/online predictions. This is what is recommended for a team of data scientists. .
2. Deep Learning VM Image, Cloud Run, Cloud Functions or Dataflow feature customized training and batch/online predictions. This is what is recommended if the team consists of  data engineers and  scientists.
3. Vertex AI Pipelines are fully customizable and recommended for organizations with separate ML engineering and data science teams.

When doing automation, the individual models that you chain together into a pipeline will be a mix – some will be prebuilt, some will be customized, and others will be built from scratch. Vertex AI, by providing a unified interface for all these model types, simplifies the operationalization of these models.

Personalization

ML application examples of personalization include customer segmentation, customer targeting, and product recommendations. For personalization, we again recommend using an EDW, because customer segmentation uses structured marketing data. For product recommendations, you will similarly have prior purchases and web logs in your EDW., You can power clustering applications, or recommendation systems like matrix factorization, and create embeddings directly from your EDW for sophisticated recommendation systems.

For specific use cases, choose the technology stack based on your data size and scope. Start with BigQuery ML for its quick, easy matrix factorization approach. Once your application proves viable and you want a slightly better accuracy, then try AutoML recommendations. But once your data set grows beyond the capabilities of AutoML recommendations, consider training your own custom TensorFlow and Keras models. 

To summarize, successful ML starts with the question, “Do I build or do I buy?” If an off-the-shelf solution exists that was trained with similar data and with access to more data than you have, then buy it. Otherwise build it, using the technology stack recommended above for the four categories of ML applications.

Learn more about our artificial intelligence (AI) and ML solutions and check out sessions from our Applied ML Summit on-demand.