AnswerGenerationSpec

Answer generation specification.

JSON representation 
{
  "modelSpec": {
    object (ModelSpec)
  },
  "promptSpec": {
    object (PromptSpec)
  },
  "includeCitations": boolean,
  "answerLanguageCode": string,
  "ignoreAdversarialQuery": boolean,
  "ignoreNonAnswerSeekingQuery": boolean,
  "ignoreJailBreakingQuery": boolean,
  "multimodalSpec": {
    object (MultimodalSpec)
  },
  "ignoreLowRelevantContent": boolean
}
Fields
modelSpec

object (ModelSpec)

Answer generation model specification.
promptSpec

object (PromptSpec)

Answer generation prompt specification.
includeCitations

boolean

Specifies whether to include citation metadata in the answer. The default value is false.
answerLanguageCode

string

Language code for Answer. Use language tags defined by BCP47. Note: This is an experimental feature.
ignoreAdversarialQuery

boolean

Specifies whether to filter out adversarial queries. The default value is false.

Google employs search-query classification to detect adversarial queries. No answer is returned if the search query is classified as an adversarial query. For example, a user might ask a question regarding negative comments about the company or submit a query designed to generate unsafe, policy-violating output. If this field is set to true, we skip generating answers for adversarial queries and return fallback messages instead.
ignoreNonAnswerSeekingQuery

boolean

Specifies whether to filter out queries that are not answer-seeking. The default value is false.

Google employs search-query classification to detect answer-seeking queries. No answer is returned if the search query is classified as a non-answer seeking query. If this field is set to true, we skip generating answers for non-answer seeking queries and return fallback messages instead.
ignoreJailBreakingQuery

boolean

Optional. Specifies whether to filter out jail-breaking queries. The default value is false.

Google employs search-query classification to detect jail-breaking queries. No summary is returned if the search query is classified as a jail-breaking query. A user might add instructions to the query to change the tone, style, language, content of the answer, or ask the model to act as a different entity, e.g. "Reply in the tone of a competing company's CEO". If this field is set to true, we skip generating summaries for jail-breaking queries and return fallback messages instead.
multimodalSpec

object (MultimodalSpec)

Optional. Multimodal specification.
ignoreLowRelevantContent

boolean

Specifies whether to filter out queries that have low relevance.

If this field is set to false, all search results are used regardless of relevance to generate answers. If set to true or unset, the behavior will be determined automatically by the service.

ModelSpec

Answer Generation Model specification.

JSON representation 
{
  "modelVersion": string
}
Fields
modelVersion

string

Model version. If not set, it will use the default stable model. Allowed values are: stable, preview.

PromptSpec

Answer generation prompt specification.

JSON representation 
{
  "preamble": string
}
Fields
preamble

string

Customized preamble.

MultimodalSpec

Multimodal specification: Will return an image from specified source. If multiple sources are specified, the pick is a quality based decision.

JSON representation 
{
  "imageSource": enum (ImageSource)
}
Fields
imageSource

enum (ImageSource)

Optional. Source of image returned in the answer.

ImageSource

Specifies the image source.

Enums
IMAGE_SOURCE_UNSPECIFIED Unspecified image source (multimodal feature is disabled by default).
ALL_AVAILABLE_SOURCES Behavior when service determines the pick from all available sources.
CORPUS_IMAGE_ONLY Includes image from corpus in the answer.
FIGURE_GENERATION_ONLY Triggers figure generation in the answer.