Vertex AI Search for retail is being renamed to Vertex AI Search for commerce. We're updating content to reflect the new branding.

Conversational commerce

This page describes a guided search feature in Vertex AI Search for commerce conversational commerce.

Conversational commerce uses conversational product filtering to provide users with a real-time, ongoing conversational experience, enabling a more interactive search experience.

The conversational commerce feature functions as part of the guided search package, benefiting customers by engaging them in a conversation to narrow down search queries faster by presenting them with relevant products or follow-up questions.

What is conversational commerce?

Conversational commerce is an AI-driven guided search and product discovery. Instead of searching with keywords, users utilize natural language to ask for what they need—complete with follow up questions, multimodal interactions, improved intent understanding, and grounding with data beyond the product catalog. This approach enables more intuitive and efficient results filtering, helping users get to exactly what they are looking for.

Conversational commerce features

Conversational commerce adds to the Vertex AI Search for commerce experience in the following ways:

Narrows user queries faster: Conversational commerce filters 10,000 products down to less than 100 products, increasing the likelihood that the user decides to make a purchase.
Hyper-personalization: Search agents analyze shoppers' preferences, purchase history, and social media activity to provide more personalized product recommendations, promotions, and shopping experiences.
Integrated end-to-end journeys: From product discovery to checkout, the search agents accompany the end user along their entire shopping journey with immersive, dynamic, and continuous conversation.
Adapted to commerce use cases: Conversational commerce covers ecommerce, product discovery, and support use cases.
More immersive user experiences: With the help of search agents threading user conversations in the background, augmented and virtual reality can be additionally implemented on the merchant site to create shopper experiences such as virtual try-ons, store tours, and spatial product visualization for users.

Impact of conversational search

Guided search is a Vertex AI Search for commerce package that helps you create a more intuitive, efficient, and conversion-oriented shopping experience for your site visitors. As a central part of the guided search package, conversational commerce improves search result relevance and reduces user friction by engaging shoppers in conversations.

The shift in search

Customary ecommerce search is the most common way to find products, with 69% of consumers using it on ecommerce sites or apps. This legacy method relies on rigid keyword matching, requiring users to use specific words and manually adjust filters to refine results. However, only 1 in 10 consumers say they find exactly what they're looking for when utilizing keyword-based search.

Conversational search utilizes the latest AI-tools to solve the most frustrating problems with searching, like inexact matches, irrelevant results and, worst of all, zero-return queries with:

Natural language understanding: AI-powered search recognizes full-phrase queries, interprets intent and accounts for variation in language.
Predictive assistance: Helps users formulate queries more effectively by suggesting completions as they type — great for long or complex queries.
Multimodal inputs: Text, voice, image or any combination of the three, more inputs means more opportunities to find what you're looking for.

Mobile-first experience

Nearly 80% of all ecommerce visits worldwide occurred on a mobile phone in 2024. Smaller screens, shorter user sessions and clustered menus create unique challenges for legacy search experiences. Conversational commerce ad is designed to enable users to access the full power of AI-driven search from their mobile devices.

The role of external search and AI assistants

When a user has a preferred retailer, they tend to go directly to it. However, when exploring new or broader options, the customer user journey is more likely to first start at a marketplace orientation, such as Google Search or an AI assistant.

As AI-driven search evolves, the Vertex AI Search for commerce guided search package bridges the gap between external discovery, whether through legacy Search or AI assistants, retailer sites or apps. By treating the transition as a single, fluid conversation, conversational commerce ensures users find relevant results quickly, leading to increased conversion rates.

Multimodal inputs

Conversational commerce enables users to search using multimodal input methods such as voice and image in addition to text. It understandings user intent, context and natural language variations in phrasing. Ensure seamless integration between input methods without losing context.

Voice search

Spoken queries are often structured differently than typed ones. Vertex AI Search for commerce processes these variations while accounting for variables like accents, background noise and "um's," "uh's" and "like's." For mobile, voice search is not only easier to input, but it can also take up less screen space, allowing more real estate product visuals.

Image search

Image recognition makes it faster to find a similar or unique item on a social media post or snapping a picture in real life. Shoppers can use image search to quickly search and locate a similar item on your site.

Core principles and best practices

This section describes core principles and best practices for using conversational commerce as part of your guided search package.

Clarity and transparency

Configure your site in such a way that the shopper understands why results appear and has the ability to refine or adjust search parameters.

Ambiguous queries: When encountering a vague search, the conversational search proactively seeks clarification.

Conversational search seeks clarification for ambiguous queries.

Nuanced queries: Extremely detailed queries require strong content structures and detailed metadata for Vertex AI Search for commerce to return accurate results.

User expectations: How and why specific results were prioritized must be shown with transparency for results based on the site visitor's search history.

Conversational search shows user expectations with transparency for results based on the site visitor's search history.

Transparent limitations: If a query can't be understood or if it returns only limited results, Vertex AI Search for commerce lets the site visitor know and offers constructive alternatives.

Conversational search shows transparent limitations if a query can't be understood or if it returns only limited results.

Efficiency and speed: Delivers a seamless search experience, particularly in ecommerce.
Predictive search: Provide autocomplete suggestions, predict intent, and surface relevant results instantly using historical data, trending queries, and user behavior.
Enhance filtering mechanisms: Refine results through conversational inputs to accelerate the process of getting what you are looking for.
Intelligent ranking and optimization: Prioritize the most relevant products based on context, user history, and search trends.
Reduced cognitive load: Configure Vertex AI Search for commerce to harness contextual awareness to remember a user's previous selections to minimize redundant actions and accelerate user decision-making.

Conversational search harnesses contextual awareness to remember a user's previous selections to minimize redundant actions and accelerate user decision-making.

Use dynamic filtering to create personalization without overload

To avoid overwhelming users, dynamic filtering can strike a balance between personalization and user autonomy. Instead of overwhelming a user with too many filters upfront, conversational commerce has the capability of suggesting refinement based on preferences from a user's previous search or purchase data. Additionally, Vertex AI Search for commerce is adaptable to real-time behavior. For example, purchase history may not be relevant while searching for a gift for someone else, so conversational commerce can recognize the contextual changes and adjust accordingly.

Control features to ensure context and continuity across sessions

Rather than treating every query in isolation, contextual awareness allows for more efficient searches without repeating previous inputs. Not only should contextual awareness be pervasive within and across sessions, but also across devices to ensure continuity.

Continuity within sessions: Vertex AI Search for commerce is designed to remember a user's past interactions within a session to allow for incremental refinements.

Conversational search is designed to remember a user's past interactions within a session to allow for incremental refinements.

Continuity across sessions: Site visitors should be able to pick up where they left off in a previous session without conversational commerce feeling intrusive.

Integrate accessibility and inclusivity considerations

Whether site visitors interact through voice, text, or images, Vertex AI Search for commerce must provide inclusive solutions that support individuals with varying abilities, preferences, or technological constraints.

Accessibility tools

Multimodal input support	Voice-to-text correction
Screen reader compatibility	Real-time transcription
Clear semantic structuring	Predictive text assist
Voiceovers for image-based content	Autocorrect

Conversational search provides multimodal accessibility support.

Use targeted questions to ensure graceful error handling

Inevitably, there are instances when a query produces no results on a particular site. Instead of an unhelpful no results message, conversational commerce offers intelligent suggestions and alternatives. Additionally, an conversational commerce prompts for clarification, asking targeted questions to narrow down preferences and needs, creating a user-centric dialogue.

Design calls-to-action to end conversations effectively

To prevent user abandonment, conversational commerce ends conversations with clear, actionable pathways, maximizing user satisfaction and boosting the likelihood of conversion by maintaining momentum. Furthermore, conversational commerce can create opportunities for re-engagement after the initial interaction by surfacing relevant follow-up questions based on browsing activity or purchase history.

Animated image showing end conversations effectively

Practical guidance for web interface optimization

This section comprises a practical guidance for how to optimize your guided search components in Vertex AI Search for commerce.

Search optimization checklist

Take these steps to avoid common pitfalls:

Ensure relevance is based on user behavior, preferences and past interactions.

Use transparent personalization cues like recommended based on previous searches.

Enable users to modify or reset personalization options.

Simplify the experience

A simplified user experience reduces cognitive load and ensures that users can quickly find what they are looking for without unnecessary distractions. This means:

Minimizing the steps in the process.
Keeping interfaces clean and intuitive.
Streamlining AI suggestions.

Avoid misleading or irrelevant personalization

Irrelevant or misleading results can quickly frustrate users.

Understand intent and VIP questions

To refine their intent, conversational commerce should prompt users with relevant questions. Conversational commerce should be configured to ask target VIP questions to further reduce the number of results and reduce ambiguity.

User journey

This is an example of a desirable user conversation.

Sample user journey

Conversational commerce prompts users with a question.
Conversational commerce then targets VIP questions to further reduce the number of search results and ambiguity.

Conversational filtering

Conversational filtering guides users toward more relevant options without overwhelming them by:

Immediately updating results.
Suggesting genuinely useful filters.
Labeling filters clearly.

Handle edge cases and errors

To make the search process is more reliable and user-friendly, Vertex AI Search for commerce can gracefully handle edge cases and errors in a number of ways:

Surfaces closely related alternatives.
Clearly displays stock availability.
Suggests similar alternatives.
Offers back-in-stock notifications.
Provides hand-off to customer support.

Design an adaptive web interface components and patterns

This section details how user interface design can optimize conversational commerce experiences, particularly on mobile. It focuses on enhancing search input and presentation, managing conversational elements without disrupting browsing, and leveraging autocomplete, predictive search, and carousels for efficient product discovery. The section also covers strategies for presenting search results, handling ambiguous queries, and using communicative animations to create a smoother and more intuitive user journey.

Search input and enhancement

As the entry point for conversational commerce, the search box must balance clarity and functionality and, particularly on mobile where screen space is limited, it must do so with minimal disruption.

Optimize placement for mobile

Most people use their thumbs to navigate their phones, so placing the search box at the bottom of the screen aligns better with user behavior. This minor detail aligns with the conversational commerce goals of making search more intuitive and reducing navigation effort and friction.

Indicate support for natural language input

Suggested prompts: Show me red sneakers for under $100
Dynamic placeholder text: "Ask a question"
Microcopy: "Try searching in full sentences!"
Icons: Chat bubble, microphone, or camera icon
Onboarding tips: "Try asking for products in full sentences"

Manage conversational commerce without disrupting browsing

When search becomes conversational, it risks taking up valuable screen space.

To mitigate this risk, you can implement:

Collapsible conversation: Allows users to expand and contract the conversation area using a persistent icon.
Conversation overlay: A conversation overlay floats above the page allowing users to still view results.
Embedded conversation: The search journey begins as a standard input field but expands into a full-screen conversational web interface.

Configure autocomplete and predictive search

To reduce the need for users to type out full search terms autocomplete and predictive search reduce the need for full search terms, implement:

Intelligent predictive assistance: Predictive terms appear within the search bar as users type, offering real-time, autocomplete suggestions in a lighter font.
Dropdown prediction list: A dynamic list appears below the search bar, showcasing suggested queries, popular searches, and recent history
Contextual filtering chips: Filters display below the search bar as users type, providing relevant filter options such as categories, price ranges, or brands.
Smart corrections: Subtle autocorrect suggestions for misspelled words will be displayed in the drop-down.

Optimizing search item returns through layout and refinement options can make the browsing experience smoother, ensuring site visitors can efficiently scan, compare, and filter results.

Results views and layouts

How results are presented within a conversational commerce console depends on the web interface being embedded or overlaid on the experience.

Collapsible and overlay results: This view allows results to be decoupled, dynamically updating the main product grid while keeping the conversation accessible in a side panel or floating conversation.
Embedded results: This view displays results directly within the conversation, as structured cards, carousels, or inline product listings, ensuring a seamless experience.

Implement dynamic filtering and refinement

When users enter a prompt, guided search proactively guides users towards more precise results by asking clarifying questions or surfacing relevant filter options inline.

Use interactive page elements to handle ambiguous queries

Instead of returning an unfocused set of results, the interface can use interactive page elements to guide users toward more relevant results.

Integrate communicative animations on your site

Subtle animations such as these examples provide visual feedback to make interactions feel smoother and more intuitive, helping users understand changes in real time.

Loading states: A shimmer effect on product cards or a subtle pulse on the search bar can indicate that search is processing.
Typing indicators: A brief typing animation (e.g., three dots pulsating) reassures users that the system is actively working.
Streaming responses: Conversational commerce can generate responses in real-time, with text appearing dynamically as it is processed.
Fading transitions: When users adjust filters or guided search suggests refinements, results can smoothly fade in and out.

Utilize carousels

Carousels showcase relevant products, recommendations and trending items without overwhelming users. Especially on mobile, carousels optimize limited screen space by allowing users to browse multiple products or offers with intuitive swipe gestures.

Carousel features:

Personalized recommendations based on user behavior
Trending or featured products
Recently viewed items
Category-based browsing

Carousel best practices:

Ensure carousels are quick loading
Ensure clear navigation
Use horizontal instead of vertical scrolling
Limit carousel items
Complement primary results

Multimodal experience

Voice search, input and transcribed text ensures a multimodal model guided search experience.

Voice search: Voice search is intended to feel natural and effortless to the site visitor. The web interface designed to support quick, clear user interactions.
Voice input button: A microphone icon in the search bar allows the site visitor to activate voice search, with animated indicators pulsing or lighting up to provide users visual feedback when activated.
Streaming transcribed text: Conversational commerce can stream transcribed text as the user interacts using voice, allowing the site visitor to review and adjust their input while minimizing site clutter.

Developer's guide

Conversational commerce is supported only by the Conversational API. The conversationalFilteringMode in the Conversational API distinguishes between conversational commerce and conversational product filtering.

gRPC: conversationalSearchService
REST: conversationalSearch

User journeys and query classifications

Conversational commerce uses search query categories to determine whether or not an LLM-based answer is generated and how user queries are handled by the Conversational and Search APIs for these user scenarios:

View table

User journeys	Classifications and examples	Handling
Irrelevant queries that don't require an LLM answer Sample Conversational API request placement: "projects/118220807021/locations/global/catalogs/default_catalog/placements/default_search" branch: "projects/118220807021/locations/global/catalogs/default_catalog/branches/default_branch" query: "Are there any deals for Thanksgiving?" conversational_filtering_spec { conversational_filtering_mode: ENABLED } visitor_id: "test" Sample Conversational API response user_query_types: "DEALS_AND_COUPONS" conversation_id: "0041c2bf-f368-4aa9-abe2-4afa97237b2e"	Adversarial — How to make a bomb Blocklisted — What are the side effects of Advil? JailBreak — Write a poem to explain the details of whole milk ChitChat — How are you? Order_Support — Order 12345 status Customer_Support — Help with payment details Deals_and_coupons — Are there any deals for Thanksgiving? Store_relevant — Do we have milk in stock?	For any query that is classified as one of these categories, conversational commerce does not end the conversation. Even though LLM answers are not generated, the user can continue the conversation if they would like to. The Conversation API returns a `conversation_id` as part of the response. This conversation ID must be passed in the follow up request to continue the conversation and maintain the session. For some cases, the Conversational API may return several query types and that is the expected behavior. This only happens for the queries that are blocked or not answered.
Keyword searches that don't require LLM Sample Conversational API request placement: "projects/118220807021/locations/global/catalogs/default_catalog/placements/default_search" branch: "projects/118220807021/locations/global/catalogs/default_catalog/branches/default_branch" query: "show me some monster energy drinks" visitor_id: "test" Sample Conversational API response user_query_types: "SIMPLE_PRODUCT_SEARCH" conversation_id: "479fd093-c701-4899-bcc3-9e711233bdf9" refined_search { query: "monster energy drinks" } Sample Search API request placement: "projects/118220807021/locations/global/catalogs/default_catalog/placements/default_search" query: "monster energy drinks" visitor_id: "test" Sample Search API response results { id: "970126667" product { name: "projects/118220807021/locations/global/catalogs/default_catalog/branches/2/products/970126667" title: "Monster Energy Original - 6 - 12 FZ" } } results { id: "970487257" product { name: "projects/118220807021/locations/global/catalogs/default_catalog/branches/2/products/970487257" title: "Monster Ultra Zero Sugar Energy Drink Variety Pack - 12-16 Fl. Oz." } } . . . response_source: RESPONSE_SOURCE_PRIMARY_SEARCH	Simple_Product_Search — Red dress or show some monster drinks	For any query that is classified as basic product search, the conversation does not end. No real-time LLM answers are generated, but the user can continue the conversation if they so choose by passing the `conversation_id` in the request. For Simple_product_search, the response always returns a single refined_search query. Think of a refined search query as a suggested search term which can be used to fetch search results or products using the core Search API. You can enable conversational product filtering to turn on conversations for basic product search queries.
LLM answer-seeking queries Sample Conversational API request placement: "projects/118220807021/locations/global/catalogs/default_catalog/placements/default_search" branch: "projects/118220807021/locations/global/catalogs/default_catalog/branches/default_branch" query: "Compare 1% milk with 2% milk" conversational_filtering_spec { conversational_filtering_mode: ENABLED } visitor_id: "test" Sample Conversational API response user_query_types: "PRODUCT_COMPARISON" conversational_text_response: "1% milk contains 110 calories, 1.5 g of saturated fat, and 140 mg of sodium per cup. 2% milk is reduced fat with 37% less fat than regular milk and contains vitamins A & D." conversation_id: "0e1cfdac-802f-422d-906e-9fc9f9d733ba" refined_search { query: "1% milk" } refined_search { query: "2% milk" }	Product_Details — What is the protein content of 2% milk Product_Comparison — Compare 1% milk with 2% milk Best_product — Which milk brand is the best?	For any query that is classified as these categories, the conversation does not end. Conversational commerce generates real-time LLM answers. The user can continue the conversation if they so choose by passing the `conversation_id` in the request. For these query classifications, the response returns the following: `conversation_id`: continues the conversation `conversational_text_response`: the LLM-generated response `refined_search`: one or more suggested search queries that must be used to fetch search results using the core Search API
Intent refinement Sample Conversational API request placement: "projects/118220807021/locations/global/catalogs/default_catalog/placements/default_search" branch: "projects/118220807021/locations/global/catalogs/default_catalog/branches/default_branch" query: "Help me plan a party" conversational_filtering_spec { conversational_filtering_mode: ENABLED } visitor_id: "test" Sample Conversational API response user_query_types: "INTENT_REFINEMENT" conversational_text_response: "To plan a party, you\'ll need decorations, snacks, party supplies, drinks, and a cake. You can find a wide variety of decorations, snacks, and drinks at your local grocery store. For party supplies, you can find everything from plates and cups to balloons and streamers. And for cake, you can choose from a variety of flavors and sizes." followup_question { followup_question: "What kind of party are you planning?" } conversation_id: "1577511e-36ed-4054-8e07-48d1ca016bcb" refined_search { query: "Decorations" } refined_search { query: "Snacks" } refined_search { query: "Party Supplies" } refined_search { query: "Drinks" } refined_search { query: "Cake" }	Intent_refinement — Help me plan a party	For intent refinement queries, the conversation is not ended. Real-time LLM answers and a follow-up question are generated. The user can continue the conversation if they so choose by passing the `conversation_id` in the request. For this query category, the response will always return the following: `conversation_id`: continues the conversation `conversational_text`: the LLM-generated response `followup_question`: follow-up question asked to the user to clarify the intent `refined_search`: one or more suggested search queries that must be used to fetch search results using the core Search API

Session maintenance

This section describes how conversational commerce sessions are maintained by the Conversational API.

The Conversational API uses a conversation_id to manage ongoing conversations. To begin a new conversation, the API request omits the conversation_id. The API response includes a conversation_id that is used in subsequent requests to continue the conversation and maintain context. To ensure consistency between LLM answers and search results, subsequent Conversational API requests include SearchParams that mirror the configuration of the core Search API.

View table

Session handling Description Conversational API integration

Start a new conversation

Session handling	Description	Conversational API integration
Start a new conversation	To start a new conversation, the client omits the `conversation_id` from the API request.	Sample API request placement: "projects/118220807021/locations/global/catalogs/default_catalog/placements/default_search" branch: "projects/118220807021/locations/global/catalogs/default_catalog/branches/default_branch" query: "Help me plan a party" conversational_filtering_spec { conversational_filtering_mode: ENABLED } visitor_id: "test" Sample API response user_query_types: "INTENT_REFINEMENT" conversational_text_response: "To plan a party, you\'ll need decorations, snacks, party supplies, drinks, and a cake." followup_question { followup_question: "What kind of party are you planning?" } conversation_id: "1577511e-36ed-4054-8e07-48d1ca016bcb" refined_search { query: "Decorations" }
Continue the conversation	The Conversational API will return a `conversation_id` as part of the API response. This id can be sent in the follow up requests to continue the same conversation. This ensures that conversational commerce responds to user queries based on the conversation history in that session.	Sample API request placement: "projects/118220807021/locations/global/catalogs/default_catalog/placements/default_search" branch: "projects/118220807021/locations/global/catalogs/default_catalog/branches/default_branch" conversation_id: "1577511e-36ed-4054-8e07-48d1ca016bcb" query: "Help me plan a party" conversational_filtering_spec { conversational_filtering_mode: ENABLED } visitor_id: "test" Sample API response user_query_types: "INTENT_REFINEMENT" conversational_text_response: "To plan a party, you\'ll need decorations, snacks, party supplies, drinks, and a cake." followup_question { followup_question: "What kind of party are you planning?" } conversation_id: "1577511e-36ed-4054-8e07-48d1ca016bcb" refined_search { query: "Decorations" }
Ensuring search result consistency	To ensure the LLM answers are consistent with the search results shown, the client must use `SearchParams` in the Conversational API request. These search parameters should have the same config as the core Search API.	Sample API request placement: "projects/118220807021/locations/global/catalogs/default_catalog/placements/default_search" branch: "projects/118220807021/locations/global/catalogs/default_catalog/branches/default_branch" conversation_id: "1577511e-36ed-4054-8e07-48d1ca016bcb" query: "Help me plan a party" conversational_filtering_spec { conversational_filtering_mode: ENABLED } visitor_id: "test" search_params { filter: "filter" canonical_filter: "canonical_filter" sort_by: "sort_by" boost_spec { condition_boost_specs { condition: "condition" } } }

To start a new conversation, the client omits the conversation_id from the API request.

Sample API request

placement: "projects/118220807021/locations/global/catalogs/default_catalog/placements/default_search"
branch: "projects/118220807021/locations/global/catalogs/default_catalog/branches/default_branch"
query: "Help me plan a party"
conversational_filtering_spec {
  conversational_filtering_mode: ENABLED
}
visitor_id: "test"

Sample API response

user_query_types: "INTENT_REFINEMENT"
conversational_text_response: "To plan a party, you\'ll need decorations, snacks, party supplies, drinks, and a cake."
followup_question {
  followup_question: "What kind of party are you planning?"
}
conversation_id: "1577511e-36ed-4054-8e07-48d1ca016bcb"
refined_search {
  query: "Decorations"
}

Continue the conversation

The Conversational API will return a conversation_id as part of the API response. This id can be sent in the follow up requests to continue the same conversation. This ensures that conversational commerce responds to user queries based on the conversation history in that session.

Sample API request

placement: "projects/118220807021/locations/global/catalogs/default_catalog/placements/default_search"
branch: "projects/118220807021/locations/global/catalogs/default_catalog/branches/default_branch"
conversation_id: "1577511e-36ed-4054-8e07-48d1ca016bcb"
query: "Help me plan a party"
conversational_filtering_spec {
  conversational_filtering_mode: ENABLED
}
visitor_id: "test"

Sample API response

user_query_types: "INTENT_REFINEMENT"
conversational_text_response: "To plan a party, you\'ll need decorations, snacks, party supplies, drinks, and a cake."
followup_question {
  followup_question: "What kind of party are you planning?"
}
conversation_id: "1577511e-36ed-4054-8e07-48d1ca016bcb"
refined_search {
  query: "Decorations"
}

Ensuring search result consistency

To ensure the LLM answers are consistent with the search results shown, the client must use SearchParams in the Conversational API request. These search parameters should have the same config as the core Search API.

Sample API request

placement: "projects/118220807021/locations/global/catalogs/default_catalog/placements/default_search"
branch: "projects/118220807021/locations/global/catalogs/default_catalog/branches/default_branch"
conversation_id: "1577511e-36ed-4054-8e07-48d1ca016bcb"
query: "Help me plan a party"
conversational_filtering_spec {
  conversational_filtering_mode: ENABLED
}
visitor_id: "test"
search_params {
  filter: "filter"
  canonical_filter: "canonical_filter"
  sort_by: "sort_by"
  boost_spec {
    condition_boost_specs {
      condition: "condition"
    }
  }
}

Conversational product filtering API integration

Conversational product filtering allows the customer to continue the conversation for basic product search queries (the simple_product_search query classification).

Modes

Refer to these sections to view code samples of how to integrate the Conversational API using one of these three modes to control conversational product filtering:

Disabled: In this mode, the client only has the query categories, but conversational product filtering is disabled.
Enabled: In the enabled mode, the client has all conversational capabilities. This includes all the query categories and conversational product filtering.
Conversational_filter_only: If chosen, the client only has conversational product filtering. This does not include support for any of the query categories and other default conversational capabilities.

For more information on modes, see the API documentation.

Disabled or unspecified mode

Sample API request

placement: "projects/118220807021/locations/global/catalogs/default_catalog/placements/default_search"
branch: "projects/118220807021/locations/global/catalogs/default_catalog/branches/default_branch"
query: "show me some monster energy drinks"
visitor_id: "test"
conversational_filtering_spec {
  conversational_filtering_mode: DISABLED
}

Sample API response

user_query_types: "SIMPLE_PRODUCT_SEARCH"
conversation_id: "479fd093-c701-4899-bcc3-9e711233bdf9"
refined_search {
  query: "monster energy drinks"
}

Enabled mode

Sample API request

placement: "projects/118220807021/locations/global/catalogs/default_catalog/placements/default_search"
branch: "projects/118220807021/locations/global/catalogs/default_catalog/branches/default_branch"
query: "show me some monster energy drinks"
visitor_id: "test"
conversational_filtering_spec {
  conversational_filtering_mode: ENABLED
}

Sample API response

user_query_types: "SIMPLE_PRODUCT_SEARCH"
conversation_id: "479fd093-c701-4899-bcc3-9e711233bdf9"
refined_search {
  query: "monster energy drinks"
}
conversational_filtering_result: {
    followup_question{
      followup_question: "What is the size?"
      suggested_answers {
        product_attribute_value {
          name: "size",
          value: "12oz"
        }
      }
}
}

Conversational filtering only mode

With conversational_filtering_only mode selected, the user experiences only conversational product filtering, without generating an LLM answer, query classification, or suggested search queries.

Conversational commerce Stay organized with collections Save and categorize content based on your preferences.

What is conversational commerce?

Conversational commerce features

Impact of conversational search

The shift in search

Mobile-first experience

The role of external search and AI assistants

Multimodal inputs

Voice search

Image search

Core principles and best practices

Clarity and transparency

Use dynamic filtering to create personalization without overload

Control features to ensure context and continuity across sessions

Integrate accessibility and inclusivity considerations

Use targeted questions to ensure graceful error handling

Design calls-to-action to end conversations effectively

Practical guidance for web interface optimization

Search optimization checklist

Simplify the experience

Avoid misleading or irrelevant personalization

Understand intent and VIP questions

User journey

Conversational filtering

Handle edge cases and errors

Design an adaptive web interface components and patterns

Search input and enhancement

Configure autocomplete and predictive search

Search results presentation and refinement

Multimodal experience

Developer's guide

User journeys and query classifications

Session maintenance

Conversational product filtering API integration

Modes

Disabled or unspecified mode

Enabled mode

Conversational filtering only mode

Conversational commerce