Class: Google::Apis::DiscoveryengineV1::GoogleCloudDiscoveryengineV1alphaSearchRequestContentSearchSpecSummarySpec
- Inherits:
-
Object
- Object
- Google::Apis::DiscoveryengineV1::GoogleCloudDiscoveryengineV1alphaSearchRequestContentSearchSpecSummarySpec
- Includes:
- Core::Hashable, Core::JsonObjectSupport
- Defined in:
- lib/google/apis/discoveryengine_v1/classes.rb,
lib/google/apis/discoveryengine_v1/representations.rb,
lib/google/apis/discoveryengine_v1/representations.rb
Overview
A specification for configuring a summary returned in a search response.
Instance Attribute Summary collapse
-
#ignore_adversarial_query ⇒ Boolean
(also: #ignore_adversarial_query?)
Specifies whether to filter out adversarial queries.
-
#ignore_jail_breaking_query ⇒ Boolean
(also: #ignore_jail_breaking_query?)
Optional.
-
#ignore_low_relevant_content ⇒ Boolean
(also: #ignore_low_relevant_content?)
Specifies whether to filter out queries that have low relevance.
-
#ignore_non_summary_seeking_query ⇒ Boolean
(also: #ignore_non_summary_seeking_query?)
Specifies whether to filter out queries that are not summary-seeking.
-
#include_citations ⇒ Boolean
(also: #include_citations?)
Specifies whether to include citations in the summary.
-
#language_code ⇒ String
Language code for Summary.
-
#model_prompt_spec ⇒ Google::Apis::DiscoveryengineV1::GoogleCloudDiscoveryengineV1alphaSearchRequestContentSearchSpecSummarySpecModelPromptSpec
Specification of the prompt to use with the model.
-
#model_spec ⇒ Google::Apis::DiscoveryengineV1::GoogleCloudDiscoveryengineV1alphaSearchRequestContentSearchSpecSummarySpecModelSpec
Specification of the model.
-
#summary_result_count ⇒ Fixnum
The number of top results to generate the summary from.
-
#use_semantic_chunks ⇒ Boolean
(also: #use_semantic_chunks?)
If true, answer will be generated from most relevant chunks from top search results.
Instance Method Summary collapse
-
#initialize(**args) ⇒ GoogleCloudDiscoveryengineV1alphaSearchRequestContentSearchSpecSummarySpec
constructor
A new instance of GoogleCloudDiscoveryengineV1alphaSearchRequestContentSearchSpecSummarySpec.
-
#update!(**args) ⇒ Object
Update properties of this object.
Constructor Details
#initialize(**args) ⇒ GoogleCloudDiscoveryengineV1alphaSearchRequestContentSearchSpecSummarySpec
Returns a new instance of GoogleCloudDiscoveryengineV1alphaSearchRequestContentSearchSpecSummarySpec.
13448 13449 13450 |
# File 'lib/google/apis/discoveryengine_v1/classes.rb', line 13448 def initialize(**args) update!(**args) end |
Instance Attribute Details
#ignore_adversarial_query ⇒ Boolean Also known as: ignore_adversarial_query?
Specifies whether to filter out adversarial queries. The default value is
false
. Google employs search-query classification to detect adversarial
queries. No summary 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
summaries for adversarial queries and return fallback messages instead.
Corresponds to the JSON property ignoreAdversarialQuery
13360 13361 13362 |
# File 'lib/google/apis/discoveryengine_v1/classes.rb', line 13360 def ignore_adversarial_query @ignore_adversarial_query end |
#ignore_jail_breaking_query ⇒ Boolean Also known as: ignore_jail_breaking_query?
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.
Corresponds to the JSON property ignoreJailBreakingQuery
13373 13374 13375 |
# File 'lib/google/apis/discoveryengine_v1/classes.rb', line 13373 def ignore_jail_breaking_query @ignore_jail_breaking_query end |
#ignore_low_relevant_content ⇒ Boolean Also known as: ignore_low_relevant_content?
Specifies whether to filter out queries that have low relevance. The default
value is false
. If this field is set to false
, all search results are used
regardless of relevance to generate answers. If set to true
, only queries
with high relevance search results will generate answers.
Corresponds to the JSON property ignoreLowRelevantContent
13382 13383 13384 |
# File 'lib/google/apis/discoveryengine_v1/classes.rb', line 13382 def ignore_low_relevant_content @ignore_low_relevant_content end |
#ignore_non_summary_seeking_query ⇒ Boolean Also known as: ignore_non_summary_seeking_query?
Specifies whether to filter out queries that are not summary-seeking. The
default value is false
. Google employs search-query classification to detect
summary-seeking queries. No summary is returned if the search query is
classified as a non-summary seeking query. For example, why is the sky blue
and Who is the best soccer player in the world?
are summary-seeking queries,
but SFO airport
and world cup 2026
are not. They are most likely
navigational queries. If this field is set to true
, we skip generating
summaries for non-summary seeking queries and return fallback messages instead.
Corresponds to the JSON property ignoreNonSummarySeekingQuery
13395 13396 13397 |
# File 'lib/google/apis/discoveryengine_v1/classes.rb', line 13395 def ignore_non_summary_seeking_query @ignore_non_summary_seeking_query end |
#include_citations ⇒ Boolean Also known as: include_citations?
Specifies whether to include citations in the summary. The default value is
false
. When this field is set to true
, summaries include in-line citation
numbers. Example summary including citations: BigQuery is Google Cloud's fully
managed and completely serverless enterprise data warehouse [1]. BigQuery
supports all data types, works across clouds, and has built-in machine
learning and business intelligence, all within a unified platform [2, 3]. The
citation numbers refer to the returned search results and are 1-indexed. For
example, [1] means that the sentence is attributed to the first search result.
[2, 3] means that the sentence is attributed to both the second and third
search results.
Corresponds to the JSON property includeCitations
13410 13411 13412 |
# File 'lib/google/apis/discoveryengine_v1/classes.rb', line 13410 def include_citations @include_citations end |
#language_code ⇒ String
Language code for Summary. Use language tags defined by BCP47. Note: This is an experimental feature.
Corresponds to the JSON property languageCode
13417 13418 13419 |
# File 'lib/google/apis/discoveryengine_v1/classes.rb', line 13417 def language_code @language_code end |
#model_prompt_spec ⇒ Google::Apis::DiscoveryengineV1::GoogleCloudDiscoveryengineV1alphaSearchRequestContentSearchSpecSummarySpecModelPromptSpec
Specification of the prompt to use with the model.
Corresponds to the JSON property modelPromptSpec
13422 13423 13424 |
# File 'lib/google/apis/discoveryengine_v1/classes.rb', line 13422 def model_prompt_spec @model_prompt_spec end |
#model_spec ⇒ Google::Apis::DiscoveryengineV1::GoogleCloudDiscoveryengineV1alphaSearchRequestContentSearchSpecSummarySpecModelSpec
Specification of the model.
Corresponds to the JSON property modelSpec
13427 13428 13429 |
# File 'lib/google/apis/discoveryengine_v1/classes.rb', line 13427 def model_spec @model_spec end |
#summary_result_count ⇒ Fixnum
The number of top results to generate the summary from. If the number of
results returned is less than summaryResultCount
, the summary is generated
from all of the results. At most 10 results for documents mode, or 50 for
chunks mode, can be used to generate a summary. The chunks mode is used when
SearchRequest.ContentSearchSpec.search_result_mode is set to CHUNKS.
Corresponds to the JSON property summaryResultCount
13436 13437 13438 |
# File 'lib/google/apis/discoveryengine_v1/classes.rb', line 13436 def summary_result_count @summary_result_count end |
#use_semantic_chunks ⇒ Boolean Also known as: use_semantic_chunks?
If true, answer will be generated from most relevant chunks from top search
results. This feature will improve summary quality. Note that with this
feature enabled, not all top search results will be referenced and included in
the reference list, so the citation source index only points to the search
results listed in the reference list.
Corresponds to the JSON property useSemanticChunks
13445 13446 13447 |
# File 'lib/google/apis/discoveryengine_v1/classes.rb', line 13445 def use_semantic_chunks @use_semantic_chunks end |
Instance Method Details
#update!(**args) ⇒ Object
Update properties of this object
13453 13454 13455 13456 13457 13458 13459 13460 13461 13462 13463 13464 |
# File 'lib/google/apis/discoveryengine_v1/classes.rb', line 13453 def update!(**args) @ignore_adversarial_query = args[:ignore_adversarial_query] if args.key?(:ignore_adversarial_query) @ignore_jail_breaking_query = args[:ignore_jail_breaking_query] if args.key?(:ignore_jail_breaking_query) @ignore_low_relevant_content = args[:ignore_low_relevant_content] if args.key?(:ignore_low_relevant_content) @ignore_non_summary_seeking_query = args[:ignore_non_summary_seeking_query] if args.key?(:ignore_non_summary_seeking_query) @include_citations = args[:include_citations] if args.key?(:include_citations) @language_code = args[:language_code] if args.key?(:language_code) @model_prompt_spec = args[:model_prompt_spec] if args.key?(:model_prompt_spec) @model_spec = args[:model_spec] if args.key?(:model_spec) @summary_result_count = args[:summary_result_count] if args.key?(:summary_result_count) @use_semantic_chunks = args[:use_semantic_chunks] if args.key?(:use_semantic_chunks) end |