Reference documentation and code samples for the Google Cloud Discovery Engine V1 Client class SummarySpec.
A specification for configuring a summary returned in a search response.
Generated from protobuf message google.cloud.discoveryengine.v1.SearchRequest.ContentSearchSpec.SummarySpec
Namespace
Google \ Cloud \ DiscoveryEngine \ V1 \ SearchRequest \ ContentSearchSpecMethods
__construct
Constructor.
| Parameters | |
|---|---|
| Name | Description |
data |
array
Optional. Data for populating the Message object. |
↳ summary_result_count |
int
The number of top results to generate the summary from. If the number of results returned is less than |
↳ include_citations |
bool
Specifies whether to include citations in the summary. The default value is |
↳ ignore_adversarial_query |
bool
Specifies whether to filter out adversarial queries. The default value is |
↳ ignore_non_summary_seeking_query |
bool
Specifies whether to filter out queries that are not summary-seeking. The default value is |
↳ model_prompt_spec |
Google\Cloud\DiscoveryEngine\V1\SearchRequest\ContentSearchSpec\SummarySpec\ModelPromptSpec
If specified, the spec will be used to modify the prompt provided to the LLM. |
↳ language_code |
string
Language code for Summary. Use language tags defined by BCP47. Note: This is an experimental feature. |
↳ model_spec |
Google\Cloud\DiscoveryEngine\V1\SearchRequest\ContentSearchSpec\SummarySpec\ModelSpec
If specified, the spec will be used to modify the model specification provided to the LLM. |
↳ use_semantic_chunks |
bool
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. |
getSummaryResultCount
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.
| Returns | |
|---|---|
| Type | Description |
int |
|
setSummaryResultCount
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.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getIncludeCitations
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.
| Returns | |
|---|---|
| Type | Description |
bool |
|
setIncludeCitations
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.
| Parameter | |
|---|---|
| Name | Description |
var |
bool
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getIgnoreAdversarialQuery
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.
| Returns | |
|---|---|
| Type | Description |
bool |
|
setIgnoreAdversarialQuery
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.
| Parameter | |
|---|---|
| Name | Description |
var |
bool
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getIgnoreNonSummarySeekingQuery
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.
| Returns | |
|---|---|
| Type | Description |
bool |
|
setIgnoreNonSummarySeekingQuery
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.
| Parameter | |
|---|---|
| Name | Description |
var |
bool
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getModelPromptSpec
If specified, the spec will be used to modify the prompt provided to the LLM.
| Returns | |
|---|---|
| Type | Description |
Google\Cloud\DiscoveryEngine\V1\SearchRequest\ContentSearchSpec\SummarySpec\ModelPromptSpec|null |
|
hasModelPromptSpec
clearModelPromptSpec
setModelPromptSpec
If specified, the spec will be used to modify the prompt provided to the LLM.
| Parameter | |
|---|---|
| Name | Description |
var |
Google\Cloud\DiscoveryEngine\V1\SearchRequest\ContentSearchSpec\SummarySpec\ModelPromptSpec
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getLanguageCode
Language code for Summary. Use language tags defined by BCP47.
Note: This is an experimental feature.
| Returns | |
|---|---|
| Type | Description |
string |
|
setLanguageCode
Language code for Summary. Use language tags defined by BCP47.
Note: This is an experimental feature.
| Parameter | |
|---|---|
| Name | Description |
var |
string
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getModelSpec
If specified, the spec will be used to modify the model specification provided to the LLM.
| Returns | |
|---|---|
| Type | Description |
Google\Cloud\DiscoveryEngine\V1\SearchRequest\ContentSearchSpec\SummarySpec\ModelSpec|null |
|
hasModelSpec
clearModelSpec
setModelSpec
If specified, the spec will be used to modify the model specification provided to the LLM.
| Parameter | |
|---|---|
| Name | Description |
var |
Google\Cloud\DiscoveryEngine\V1\SearchRequest\ContentSearchSpec\SummarySpec\ModelSpec
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getUseSemanticChunks
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.
| Returns | |
|---|---|
| Type | Description |
bool |
|
setUseSemanticChunks
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.
| Parameter | |
|---|---|
| Name | Description |
var |
bool
|
| Returns | |
|---|---|
| Type | Description |
$this |
|