Features and capabilities of Vertex AI Search for commerce
Stay organized with collections
Save and categorize content based on your preferences.
Within the Vertex AI Search for commerce product, you get both the recommendations capability
and the search and browse capability.
You can upload and manage product catalog
information and user event logs for your ecommerce applications. You can get and
customize results based on this information, and this data continues to be used
to train and update models, thus improving your recommendations and search
results.
Vertex AI Search for commerce lets you build high quality, personalized
product recommendation systems without requiring a high level of expertise in
machine learning, systems design, or operations. Leveraging your site's retail
products and user behavior, you can use recommendations to build recommendation models specific to your use case,
such as "Frequently Bought Together" and "Recommended for You".
Vertex AI Search for commerce uses user events and your product catalog to train
your recommendation machine learning models, which provide recommendations
based on this data.
When you deploy recommendation models to your application, you can then request
recommendations for other products in your catalog and display to your users.
Recommendations capabilities include:
Custom models. Each model is trained specifically for your data, based
on sequence-based machine learning models using transformers.
Personalized results. Use personalization algorithms without any
machine learning expertise. Recommendations are based on user behavior and
activities like views, clicks, and in-store purchases as well as online
activity, so that every prediction result is personalized.
Real-time predictions. Each recommendation served considers previous
user activity like click, view, and purchase events, so recommendations are
in real time.
Automatic model training and tuning. Daily model retraining ensures all
the models can accurately capture user behavior every day.
Optimization objectives. Goals like conversion rate, click-through rate,
and revenue optimization help you precisely optimize for your business goal.
Omnichannel recommendations. With the API model, go beyond website
recommendations to personalize your entire shopper journey to
recommendations on mobile apps, personalized email recommendations, store
kiosks, or call center applications.
Search
Vertex AI Search for commerce lets you provide high quality product search results
that are customizable for your retail business needs. Use Google's query
and contextual understanding to improve product discovery across your website
and mobile applications.
Search capabilities include:
Product hierarchies: You can include collections and variants in your
searchable product catalog.
Query expansion: Increase the relevant results returned for query terms
that would normally produce fewer results, such as queries that use very
specific keywords.
Relevance thresholding: Adjust how Vertex AI Search for commerce balances
returning precision (the relevance of the search results returned) and
recall (returning more results for that query).
Pagination: Control pagination of your search results to decrease lookup
time and response size.
Filtering: Use expression syntax to provide filtering that refines your
site's search results.
Ordering: Set the order of search results by multiple fields in order of
priority.
Faceting: Generate faceting to provide more relevant options to your
users based on attributes you provide. Buckets need to be provided for
numerical attributes in the search request to return them in the search
response.
Dynamic faceting: Automatically generate facet keys based on search
queries and automatically combine (and rerank) with facet keys provided in
the search request. This feature is based on an allowlist. Contact
support for help enabling this feature.
Boosting and burying: Control search result ranking by prioritizing or
deprioritizing some types of results.
Browsing: Get results that are sorted to maximize revenue when your
users browse products using site navigation. Browse search can be combined
with filtering, ordering, faceting, dynamic faceting, boosting, and burying.
Personalized results. Deliver personalized text search and browse search
results that are personalized for each end-user, based on each user's
behavior on your site, including each user's history of product views,
clicks, add to cart, and purchases.
Use Vertex AI Search for commerce
In order to build machine learning models for recommendations or search,
you need to supply two sets of information:
Product catalog: Information about the products being recommended to
customers. This includes the product title, description, in-stock
availability, and pricing.
User events: End user behavior on your website. This includes events
such as when a user views or purchases a specific item, or when your
website shows the user a list of products.
With many integration options, you can ingest your data using tools you might
already use, such as BigQuery, Cloud Storage, Tag Manager, and
Google Analytics.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-29 UTC."],[],[],null,["# Features and capabilities of Vertex AI Search for commerce\n\nWithin the Vertex AI Search for commerce product, you get both the recommendations capability\nand the search and browse capability.\nYou can upload and manage product catalog\ninformation and user event logs for your ecommerce applications. You can get and\ncustomize results based on this information, and this data continues to be used\nto train and update models, thus improving your recommendations and search\nresults.\n\nFor more information about the process of implementing Vertex AI Search for commerce\nfor your application, see [Implementing Vertex AI Search for commerce](/retail/docs/overview).\n\nRecommendations\n---------------\n\nVertex AI Search for commerce lets you build high quality, personalized\nproduct recommendation systems without requiring a high level of expertise in\nmachine learning, systems design, or operations. Leveraging your site's retail\nproducts and user behavior, you can use recommendations to build recommendation models specific to your use case,\nsuch as \"Frequently Bought Together\" and \"Recommended for You\".\n\nVertex AI Search for commerce uses user events and your product catalog to train\nyour recommendation machine learning models, which provide recommendations\nbased on this data.\n\nWhen you deploy recommendation models to your application, you can then request\nrecommendations for other products in your catalog and display to your users.\n\nRecommendations capabilities include:\n\n- **Custom models**. Each model is trained specifically for your data, based\n on sequence-based machine learning models using transformers.\n\n- **Personalized results**. Use personalization algorithms without any\n machine learning expertise. Recommendations are based on user behavior and\n activities like views, clicks, and in-store purchases as well as online\n activity, so that every prediction result is personalized.\n\n- **Real-time predictions**. Each recommendation served considers previous\n user activity like click, view, and purchase events, so recommendations are\n in real time.\n\n- **Automatic model training and tuning**. Daily model retraining ensures all\n the models can accurately capture user behavior every day.\n\n- **Optimization objectives**. Goals like conversion rate, click-through rate,\n and revenue optimization help you precisely optimize for your business goal.\n\n- **Omnichannel recommendations**. With the API model, go beyond website\n recommendations to personalize your entire shopper journey to\n recommendations on mobile apps, personalized email recommendations, store\n kiosks, or call center applications.\n\nSearch\n------\n\nVertex AI Search for commerce lets you provide high quality product search results\nthat are customizable for your retail business needs. Use Google's query\nand contextual understanding to improve product discovery across your website\nand mobile applications.\n\nSearch capabilities include:\n\n- **Product hierarchies**: You can include collections and variants in your\n searchable product catalog.\n\n- **Query expansion**: Increase the relevant results returned for query terms\n that would normally produce fewer results, such as queries that use very\n specific keywords.\n\n- **Relevance thresholding**: Adjust how Vertex AI Search for commerce balances\n returning precision (the relevance of the search results returned) and\n recall (returning more results for that query).\n\n- **Pagination**: Control pagination of your search results to decrease lookup\n time and response size.\n\n- **Filtering**: Use expression syntax to provide filtering that refines your\n site's search results.\n\n- **Ordering**: Set the order of search results by multiple fields in order of\n priority.\n\n- **Faceting**: Generate faceting to provide more relevant options to your\n users based on attributes you provide. Buckets need to be provided for\n numerical attributes in the search request to return them in the search\n response.\n\n- **Dynamic faceting**: Automatically generate facet keys based on search\n queries and automatically combine (and rerank) with facet keys provided in\n the search request. This feature is based on an allowlist. Contact\n support for help enabling this feature.\n\n- **Boosting and burying**: Control search result ranking by prioritizing or\n deprioritizing some types of results.\n\n- **Browsing**: Get results that are sorted to maximize revenue when your\n users browse products using site navigation. Browse search can be combined\n with filtering, ordering, faceting, dynamic faceting, boosting, and burying.\n\n- **Personalized results**. Deliver personalized text search and browse search\n results that are personalized for each end-user, based on each user's\n behavior on your site, including each user's history of product views,\n clicks, add to cart, and purchases.\n\nUse Vertex AI Search for commerce\n---------------------------------\n\nIn order to build machine learning models for recommendations or search,\nyou need to supply two sets of information:\n\n- **Product catalog:** Information about the products being recommended to\n customers. This includes the product title, description, in-stock\n availability, and pricing.\n\n- **User events:** End user behavior on your website. This includes events\n such as when a user views or purchases a specific item, or when your\n website shows the user a list of products.\n\nWith many integration options, you can ingest your data using tools you might\nalready use, such as BigQuery, Cloud Storage, Tag Manager, and\nGoogle Analytics.\n| **Important:** Vertex AI Search for commerce processes data on your behalf. It is your responsibility to ensure that the data you send to Vertex AI Search for commerce is collected in accordance with applicable laws."]]