Package google.shopping.merchant.productstudio.v1alpha

Index

• TextSuggestionsService (interface)
• GenerateProductTextSuggestionsRequest (message)
• GenerateProductTextSuggestionsResponse (message)
• Image (message)
• OutputSpec (message)
• ProductInfo (message)
• ProductTextGenerationMetadata (message)
• ProductTextGenerationSuggestion (message)
• TitleExample (message)

TextSuggestionsService

Service that exposes Generative AI (GenAI) endpoints for creating and enhancing product text content, such as titles, descriptions, etc.

GenerateProductTextSuggestions

rpc GenerateProductTextSuggestions(GenerateProductTextSuggestionsRequest) returns (GenerateProductTextSuggestionsResponse) GenerateProductTextSuggestions generates a set of candidate text completions (e.g., product titles, descriptions) based on provided product information. This endpoint leverages GenAI models to create suggestions for improving existing product text or generating new content. Authorization scopes Requires the following OAuth scope: https://www.googleapis.com/auth/content For more information, see the OAuth 2.0 Overview.

GenerateProductTextSuggestionsRequest

Request message for the GenerateProductTextSuggestions method.

Fields
name	string Required. The name of the account to generate text suggestions for. This acts as a container for the request and does not affect the generation itself, as this is a stateless API. Format: accounts/{account}
product_info	ProductInfo Required. Available information about the product. Used to inform the genAI models.
title_examples[]	TitleExample Optional. Provide some hand-crafted examples of title improvements that are unique to your use case. This is a general tool that handles multiple product categories, but your brand identity may require custom functionality. Feel free to specify that here.
output_spec	OutputSpec Optional. Configuration parameters that directly influence what content is generated, and how that content is rendered in the final response.

GenerateProductTextSuggestionsResponse

Response message for the GenerateProductTextSuggestions method.

Fields
attributes	map<string, string> Any other generated attributes.
title	ProductTextGenerationSuggestion Generated title suggestion.
description	ProductTextGenerationSuggestion Generated description suggestion.
metadata	ProductTextGenerationMetadata Additional info that clients may want to audit surrounding the generation.

Image

Product image represented as bytes directly or a URI.

Fields
Union field image. Required. The image to use for text generation. image can be only one of the following:
uri	string Generally web-requestable URI.
data	bytes Raw bytes for the image.

OutputSpec

Configuration parameters that directly influence what content is generated, and how that content is rendered in the final response.

Fields
attribute_order[]	string Optional. The order that generated attributes should be placed in the generated title. Eg., if the attribute order is ["brand", "product", "size"], the generated title will have brand first, followed by the product name, and then size information after that.
workflow_id	string Optional. The workflow to execute for the provided product data. Workflows may populate the response's title, description, or both. Currently supported workflow_ids are: "title", "description", and "tide"
tone	string Optional. The tone of the output generated text. Supported tones are: "playful", "formal", "persuasive", and "conversational"
editorial_changes	string Optional. Any editorial changes for the generated product data. For example, replace Small with "S", do not modify color if already present.
target_language	string Optional. The language for output titles/descriptions. For example. 'German', 'es', 'FR'. Default is 'en'.
attribute_separator	string Optional. Character used to separate attributes in the generated title. For example, '|', '-', ','.

ProductInfo

Available information about the product. Used to inform the genAI models.

Fields
product_attributes	map<string, string> Required. A mapping of all available product attributes. This may include title, description, brand, gender, color, size, etc.
product_image	Image Optional. Image associated with the product.

ProductTextGenerationMetadata

Wrapper data type for any metadata associated with text generation.

Fields
metadata	Struct Metadata is a pretty loose concept. The data is modeled as a map here to indicate that there is no guaranteed structure to the output past a simple K:V association. The first use-case is to track words added/removed/changed in generations.

ProductTextGenerationSuggestion

Text generated for a product, optionally including its quality score.

Fields
text	string The text generated
score	float The quality score associated with the generation. Heuristic implemented according to the feedgen team's implementation styles.
change_summary	string A brief summarization of all the changes that have been made.

TitleExample

A hand-crafted example of a product title improvement. These examples are provided to the AI to improve its quality and guide it towards required outputs.

Fields
product_info	map<string, string> Required. A map containing all existing product information. For example: {"title": "dress", "description": "A red dress", "brand": "Dresses4All"} Any information that you might use to populate your product feed.
final_product_info	map<string, string> Required. A map in the same format as product_info but with all improvements included. For example, {"brand": "Dresses4All", "product": "dress", "color": "red", ...}. The order of attributes in this map may be used to guide the order in which they appear in the final generated title. For instance, the above will become: Dresses4All dress | red
category	string Required. The product's category. This helps the AI understand when certain examples are more relevant than others.
title_format	string Required. The attributes or approximate attributes that make up the title. For example, title "Google GShoe M" title_format can be "brand | product | size".