Recommendations from Vertex AI Search

Take advantage of Google's expertise in recommendations, powered by state-of-the-art machine learning models. Provide effective and real-time personalization with the recommendations capability (formerly Recommendations AI) of Vertex AI Search.

Give customers more of what they love

Earn your customers’ trust and loyalty by proving how well you understand them. Google delivers content to billions across consumer facing platforms including Google Ads, Google Search, and YouTube.

Recommendations from Vertex AI Search lets businesses harness that experience and expertise to deliver personalized recommendations that suit each customer’s tastes and preferences.

Choose your strategy logo

Choose your outcome

Customize recommendations to deliver your desired outcome: engagement, revenue, or conversions. Apply business rules to fine-tune what customers see, diversify product displays, and filter by product availability, custom tags, etc.

Your data, your models logo

Your data, your models

Your data and models are yours and yours alone. They’ll never be used for any other Google product nor shown to any other Google customer. You’re never locked in, and can delete your data and models anytime. Learn more.

Fully managed service logo

Fully managed service

No need to preprocess data, train or hypertune machine learning models, load balance, or manually provision your infrastructure to handle unpredictable traffic spikes. We do it all for you automatically.

Deliver high-performing recommendations across channels

With the recommendations capability of Vertex AI Search you can deliver high-performing recommendations to any customer touchpoint including your website, mobile experience, email, contact center, and more. Seamlessly deliver curated recommendations with low latency to customers anywhere in the world. 

Get started in 4 simple steps

Upload and sync catalog, import and sync user events, select a modela and goal, and deliver

Vertex AI Search for industries

Take advantage of industry specific features to fully optimize outcomes for your business.

Recommendations for media

Engage and retain audiences. 

Recommend media content (articles, video) based on watch history. Optimize for goals like converting trial subscriptions or growing ad inventory.

Read documentation

Recommendations for retail

Convert shoppers. 

Recommend products based on models like user history and frequently bought together. Use cart events to optimize and increase your conversion rates.  

Read documentation
Galaxus Logo

"Recommendations AI was easy to integrate with our existing recommendations framework, and enabled us to deliver next-gen recommendations without a ton of work. We are steadily investing in data science and it is very helpful for us to be able to integrate and test different algorithms. Recommendations AI performs really well on our product detail pages and increased conversions and revenue significantly."

Oliver Herren, CIO, Galaxus


Pricing for recommendations is based on operations such as training and tuning (per node per hour) and requesting predictions (per 1,000 predictions). Prediction cost is tiered by number of monthly prediction requests.

You can try recommendations with a free credit. This credit is typically sufficient to train a model and test its performance in production through a two-week A/B test.

View our pricing page for more details:

Take the next step

Start building on Google Cloud with $300 in free credits and 20+ always free products.

Need help getting started?
Work with a trusted partner
Continue browsing

Take the next step

Start your next project, explore interactive tutorials, and manage your account.

Need help getting started?
Work with a trusted partner
Get tips & best practices