Index
EvaluationService
(interface)ExtensionExecutionService
(interface)ExtensionRegistryService
(interface)GenAiCacheConfigService
(interface)GenAiCacheService
(interface)GenAiTuningService
(interface)PredictionService
(interface)ReasoningEngineExecutionService
(interface)ReasoningEngineService
(interface)VertexRagDataService
(interface)VertexRagService
(interface)ApiAuth
(message)ApiAuth.ApiKeyConfig
(message)AugmentPromptRequest
(message)AugmentPromptRequest.Model
(message)AugmentPromptResponse
(message)AuthConfig
(message)AuthConfig.ApiKeyConfig
(message)AuthConfig.GoogleServiceAccountConfig
(message)AuthConfig.HttpBasicAuthConfig
(message)AuthConfig.OauthConfig
(message)AuthConfig.OidcConfig
(message)AuthType
(enum)BigQueryDestination
(message)BleuInput
(message)BleuInstance
(message)BleuMetricValue
(message)BleuResults
(message)BleuSpec
(message)Blob
(message)CacheConfig
(message)CachedContent
(message)CachedContent.UsageMetadata
(message)CancelTuningJobRequest
(message)Candidate
(message)Candidate.FinishReason
(enum)ChatCompletionsRequest
(message)Citation
(message)CitationMetadata
(message)Claim
(message)CodeExecutionResult
(message)CodeExecutionResult.Outcome
(enum)CoherenceInput
(message)CoherenceInstance
(message)CoherenceResult
(message)CoherenceSpec
(message)Content
(message)CorpusStatus
(message)CorpusStatus.State
(enum)CorroborateContentRequest
(message)CorroborateContentRequest.Parameters
(message)CorroborateContentResponse
(message)CountTokensRequest
(message)CountTokensResponse
(message)CreateCachedContentRequest
(message)CreateRagCorpusOperationMetadata
(message)CreateRagCorpusRequest
(message)CreateReasoningEngineOperationMetadata
(message)CreateReasoningEngineRequest
(message)CreateTuningJobRequest
(message)DatasetDistribution
(message)DatasetDistribution.DistributionBucket
(message)DatasetStats
(message)DeleteCachedContentRequest
(message)DeleteExtensionRequest
(message)DeleteOperationMetadata
(message)DeleteRagCorpusRequest
(message)DeleteRagFileRequest
(message)DeleteReasoningEngineRequest
(message)DirectUploadSource
(message)DistillationDataStats
(message)DistillationHyperParameters
(message)DistillationSpec
(message)DynamicRetrievalConfig
(message)DynamicRetrievalConfig.Mode
(enum)EncryptionSpec
(message)EvaluateInstancesRequest
(message)EvaluateInstancesResponse
(message)ExactMatchInput
(message)ExactMatchInstance
(message)ExactMatchMetricValue
(message)ExactMatchResults
(message)ExactMatchSpec
(message)ExecutableCode
(message)ExecutableCode.Language
(enum)ExecuteExtensionRequest
(message)ExecuteExtensionResponse
(message)Extension
(message)ExtensionManifest
(message)ExtensionManifest.ApiSpec
(message)ExtensionOperation
(message)ExtensionPrivateServiceConnectConfig
(message)Fact
(message)FileData
(message)FileStatus
(message)FileStatus.State
(enum)FluencyInput
(message)FluencyInstance
(message)FluencyResult
(message)FluencySpec
(message)FulfillmentInput
(message)FulfillmentInstance
(message)FulfillmentResult
(message)FulfillmentSpec
(message)FunctionCall
(message)FunctionCallingConfig
(message)FunctionCallingConfig.Mode
(enum)FunctionDeclaration
(message)FunctionResponse
(message)GcsDestination
(message)GcsSource
(message)GenerateContentRequest
(message)GenerateContentResponse
(message)GenerateContentResponse.PromptFeedback
(message)GenerateContentResponse.PromptFeedback.BlockedReason
(enum)GenerateContentResponse.UsageMetadata
(message)GenerationConfig
(message)GenerationConfig.RoutingConfig
(message)GenerationConfig.RoutingConfig.AutoRoutingMode
(message)GenerationConfig.RoutingConfig.AutoRoutingMode.ModelRoutingPreference
(enum)GenerationConfig.RoutingConfig.ManualRoutingMode
(message)GenericOperationMetadata
(message)GetCacheConfigRequest
(message)GetCachedContentRequest
(message)GetExtensionRequest
(message)GetRagCorpusRequest
(message)GetRagFileRequest
(message)GetReasoningEngineRequest
(message)GetTuningJobRequest
(message)GoogleDriveSource
(message)GoogleDriveSource.ResourceId
(message)GoogleDriveSource.ResourceId.ResourceType
(enum)GoogleSearchRetrieval
(message)GroundednessInput
(message)GroundednessInstance
(message)GroundednessResult
(message)GroundednessSpec
(message)GroundingChunk
(message)GroundingChunk.RetrievedContext
(message)GroundingChunk.Web
(message)GroundingMetadata
(message)GroundingSupport
(message)HarmCategory
(enum)HttpElementLocation
(enum)ImportExtensionOperationMetadata
(message)ImportExtensionRequest
(message)ImportRagFilesConfig
(message)ImportRagFilesOperationMetadata
(message)ImportRagFilesRequest
(message)ImportRagFilesResponse
(message)JiraSource
(message)JiraSource.JiraQueries
(message)JobState
(enum)ListCachedContentsRequest
(message)ListCachedContentsResponse
(message)ListExtensionsRequest
(message)ListExtensionsResponse
(message)ListRagCorporaRequest
(message)ListRagCorporaResponse
(message)ListRagFilesRequest
(message)ListRagFilesResponse
(message)ListReasoningEnginesRequest
(message)ListReasoningEnginesResponse
(message)ListTuningJobsRequest
(message)ListTuningJobsResponse
(message)LogprobsResult
(message)LogprobsResult.Candidate
(message)LogprobsResult.TopCandidates
(message)PairwiseChoice
(enum)PairwiseMetricInput
(message)PairwiseMetricInstance
(message)PairwiseMetricResult
(message)PairwiseMetricSpec
(message)PairwiseQuestionAnsweringQualityInput
(message)PairwiseQuestionAnsweringQualityInstance
(message)PairwiseQuestionAnsweringQualityResult
(message)PairwiseQuestionAnsweringQualitySpec
(message)PairwiseSummarizationQualityInput
(message)PairwiseSummarizationQualityInstance
(message)PairwiseSummarizationQualityResult
(message)PairwiseSummarizationQualitySpec
(message)Part
(message)PartnerModelTuningSpec
(message)PointwiseMetricInput
(message)PointwiseMetricInstance
(message)PointwiseMetricResult
(message)PointwiseMetricSpec
(message)PredictRequest
(message)PredictResponse
(message)QueryExtensionRequest
(message)QueryExtensionResponse
(message)QueryReasoningEngineRequest
(message)QueryReasoningEngineResponse
(message)QuestionAnsweringCorrectnessInput
(message)QuestionAnsweringCorrectnessInstance
(message)QuestionAnsweringCorrectnessResult
(message)QuestionAnsweringCorrectnessSpec
(message)QuestionAnsweringHelpfulnessInput
(message)QuestionAnsweringHelpfulnessInstance
(message)QuestionAnsweringHelpfulnessResult
(message)QuestionAnsweringHelpfulnessSpec
(message)QuestionAnsweringQualityInput
(message)QuestionAnsweringQualityInstance
(message)QuestionAnsweringQualityResult
(message)QuestionAnsweringQualitySpec
(message)QuestionAnsweringRelevanceInput
(message)QuestionAnsweringRelevanceInstance
(message)QuestionAnsweringRelevanceResult
(message)QuestionAnsweringRelevanceSpec
(message)RagContexts
(message)RagContexts.Context
(message)RagCorpus
(message)RagEmbeddingModelConfig
(message)RagEmbeddingModelConfig.HybridSearchConfig
(message)RagEmbeddingModelConfig.SparseEmbeddingConfig
(message)RagEmbeddingModelConfig.SparseEmbeddingConfig.Bm25
(message)RagEmbeddingModelConfig.VertexPredictionEndpoint
(message)RagFile
(message)RagFile.RagFileType
(enum)RagFileChunkingConfig
(message)RagFileParsingConfig
(message)RagQuery
(message)RagQuery.Ranking
(message)RagVectorDbConfig
(message)RagVectorDbConfig.Pinecone
(message)RagVectorDbConfig.RagManagedDb
(message)RagVectorDbConfig.VertexFeatureStore
(message)RagVectorDbConfig.VertexVectorSearch
(message)RagVectorDbConfig.Weaviate
(message)ReasoningEngine
(message)ReasoningEngineSpec
(message)ReasoningEngineSpec.PackageSpec
(message)RebaseTunedModelOperationMetadata
(message)RebaseTunedModelRequest
(message)Retrieval
(message)RetrievalMetadata
(message)RetrieveContextsRequest
(message)RetrieveContextsRequest.VertexRagStore
(message)RetrieveContextsRequest.VertexRagStore.RagResource
(message)RetrieveContextsResponse
(message)RougeInput
(message)RougeInstance
(message)RougeMetricValue
(message)RougeResults
(message)RougeSpec
(message)RuntimeConfig
(message)RuntimeConfig.CodeInterpreterRuntimeConfig
(message)RuntimeConfig.VertexAISearchRuntimeConfig
(message)SafetyInput
(message)SafetyInstance
(message)SafetyRating
(message)SafetyRating.HarmProbability
(enum)SafetyRating.HarmSeverity
(enum)SafetyResult
(message)SafetySetting
(message)SafetySetting.HarmBlockMethod
(enum)SafetySetting.HarmBlockThreshold
(enum)SafetySpec
(message)Schema
(message)SearchEntryPoint
(message)Segment
(message)SharePointSources
(message)SharePointSources.SharePointSource
(message)SlackSource
(message)SlackSource.SlackChannels
(message)SlackSource.SlackChannels.SlackChannel
(message)StreamDirectPredictRequest
(message)StreamDirectPredictResponse
(message)StreamDirectRawPredictRequest
(message)StreamDirectRawPredictResponse
(message)StreamingPredictRequest
(message)StreamingPredictResponse
(message)StreamingRawPredictRequest
(message)StreamingRawPredictResponse
(message)SummarizationHelpfulnessInput
(message)SummarizationHelpfulnessInstance
(message)SummarizationHelpfulnessResult
(message)SummarizationHelpfulnessSpec
(message)SummarizationQualityInput
(message)SummarizationQualityInstance
(message)SummarizationQualityResult
(message)SummarizationQualitySpec
(message)SummarizationVerbosityInput
(message)SummarizationVerbosityInstance
(message)SummarizationVerbosityResult
(message)SummarizationVerbositySpec
(message)SupervisedHyperParameters
(message)SupervisedHyperParameters.AdapterSize
(enum)SupervisedTuningDataStats
(message)SupervisedTuningDatasetDistribution
(message)SupervisedTuningDatasetDistribution.DatasetBucket
(message)SupervisedTuningSpec
(message)Tensor
(message)Tensor.DataType
(enum)Tool
(message)Tool.CodeExecution
(message)ToolCallValidInput
(message)ToolCallValidInstance
(message)ToolCallValidMetricValue
(message)ToolCallValidResults
(message)ToolCallValidSpec
(message)ToolConfig
(message)ToolNameMatchInput
(message)ToolNameMatchInstance
(message)ToolNameMatchMetricValue
(message)ToolNameMatchResults
(message)ToolNameMatchSpec
(message)ToolParameterKVMatchInput
(message)ToolParameterKVMatchInstance
(message)ToolParameterKVMatchMetricValue
(message)ToolParameterKVMatchResults
(message)ToolParameterKVMatchSpec
(message)ToolParameterKeyMatchInput
(message)ToolParameterKeyMatchInstance
(message)ToolParameterKeyMatchMetricValue
(message)ToolParameterKeyMatchResults
(message)ToolParameterKeyMatchSpec
(message)ToolUseExample
(message)ToolUseExample.ExtensionOperation
(message)TunedModel
(message)TunedModelRef
(message)TuningDataStats
(message)TuningJob
(message)Type
(enum)UpdateCacheConfigRequest
(message)UpdateCachedContentRequest
(message)UpdateExtensionRequest
(message)UpdateRagCorpusOperationMetadata
(message)UpdateRagCorpusRequest
(message)UpdateReasoningEngineOperationMetadata
(message)UpdateReasoningEngineRequest
(message)UploadRagFileConfig
(message)VertexAISearch
(message)VertexRagStore
(message)VertexRagStore.RagResource
(message)VideoMetadata
(message)
EvaluationService
Vertex AI Online Evaluation Service.
EvaluateInstances |
---|
Evaluates instances based on a given metric. |
ExtensionExecutionService
A service for Extension execution.
ExecuteExtension |
---|
Executes the request against a given extension.
|
QueryExtension |
---|
Queries an extension with a default controller.
|
ExtensionRegistryService
A service for managing Vertex AI's Extension registry.
DeleteExtension |
---|
Deletes an Extension.
|
GetExtension |
---|
Gets an Extension.
|
ImportExtension |
---|
Imports an Extension.
|
ListExtensions |
---|
Lists Extensions in a location.
|
UpdateExtension |
---|
Updates an Extension.
|
GenAiCacheConfigService
Service for GenAI Cache Config.
GetCacheConfig |
---|
Gets a GenAI cache config.
|
UpdateCacheConfig |
---|
Updates a cache config.
|
GenAiCacheService
Service for managing Vertex AI's CachedContent resource.
CreateCachedContent |
---|
Creates cached content, this call will initialize the cached content in the data storage, and users need to pay for the cache data storage.
|
DeleteCachedContent |
---|
Deletes cached content
|
GetCachedContent |
---|
Gets cached content configurations
|
ListCachedContents |
---|
Lists cached contents in a project
|
UpdateCachedContent |
---|
Updates cached content configurations
|
GenAiTuningService
A service for creating and managing GenAI Tuning Jobs.
CancelTuningJob |
---|
Cancels a TuningJob. Starts asynchronous cancellation on the TuningJob. The server makes a best effort to cancel the job, but success is not guaranteed. Clients can use
|
CreateTuningJob |
---|
Creates a TuningJob. A created TuningJob right away will be attempted to be run.
|
GetTuningJob |
---|
Gets a TuningJob.
|
ListTuningJobs |
---|
Lists TuningJobs in a Location.
|
RebaseTunedModel |
---|
Rebase a TunedModel.
|
PredictionService
A service for online predictions and explanations.
ChatCompletions |
---|
Exposes an OpenAI-compatible endpoint for chat completions.
|
CountTokens |
---|
Perform a token counting.
|
GenerateContent |
---|
Generate content with multimodal inputs.
|
Predict |
---|
Perform an online prediction.
|
ServerStreamingPredict |
---|
Perform a server-side streaming online prediction request for Vertex LLM streaming.
|
StreamDirectPredict |
---|
Perform a streaming online prediction request to a gRPC model server for Vertex first-party products and frameworks.
|
StreamDirectRawPredict |
---|
Perform a streaming online prediction request to a gRPC model server for custom containers.
|
StreamGenerateContent |
---|
Generate content with multimodal inputs with streaming support.
|
StreamingPredict |
---|
Perform a streaming online prediction request for Vertex first-party products and frameworks.
|
StreamingRawPredict |
---|
Perform a streaming online prediction request through gRPC.
|
ReasoningEngineExecutionService
A service for executing queries on Reasoning Engine.
QueryReasoningEngine |
---|
Queries using a reasoning engine.
|
ReasoningEngineService
A service for managing Vertex AI's Reasoning Engines.
CreateReasoningEngine |
---|
Creates a reasoning engine.
|
DeleteReasoningEngine |
---|
Deletes a reasoning engine.
|
GetReasoningEngine |
---|
Gets a reasoning engine.
|
ListReasoningEngines |
---|
Lists reasoning engines in a location.
|
UpdateReasoningEngine |
---|
Updates a reasoning engine.
|
VertexRagDataService
A service for managing user data for RAG.
CreateRagCorpus |
---|
Creates a RagCorpus. |
DeleteRagCorpus |
---|
Deletes a RagCorpus. |
DeleteRagFile |
---|
Deletes a RagFile. |
GetRagCorpus |
---|
Gets a RagCorpus. |
GetRagFile |
---|
Gets a RagFile. |
ImportRagFiles |
---|
Import files from Google Cloud Storage or Google Drive into a RagCorpus. |
ListRagCorpora |
---|
Lists RagCorpora in a Location. |
ListRagFiles |
---|
Lists RagFiles in a RagCorpus. |
UpdateRagCorpus |
---|
Updates a RagCorpus. |
VertexRagService
A service for retrieving relevant contexts.
AugmentPrompt |
---|
Given an input prompt, it returns augmented prompt from vertex rag store to guide LLM towards generating grounded responses.
|
CorroborateContent |
---|
Given an input text, it returns a score that evaluates the factuality of the text. It also extracts and returns claims from the text and provides supporting facts.
|
RetrieveContexts |
---|
Retrieves relevant contexts for a query.
|
ApiAuth
The generic reusable api auth config.
auth_config
. The auth config. auth_config
can be only one of the following:The API secret.
ApiKeyConfig
The API secret.
api_key_secret_version
string
Required. The SecretManager secret version resource name storing API key. e.g. projects/{project}/secrets/{secret}/versions/{version}
AugmentPromptRequest
Request message for AugmentPrompt.
parent
string
Required. The resource name of the Location from which to augment prompt. The users must have permission to make a call in the project. Format: projects/{project}/locations/{location}
.
Optional. Input content to augment, only text format is supported for now.
Optional. Metadata of the backend deployed model.
data_source
. The data source for retrieving contexts. data_source
can be only one of the following:Optional. Retrieves contexts from the Vertex RagStore.
Model
Metadata of the backend deployed model.
model
string
Optional. The model that the user will send the augmented prompt for content generation.
model_version
string
Optional. The model version of the backend deployed model.
AugmentPromptResponse
AuthConfig
Auth configuration to run the extension.
Type of auth scheme.
Union field auth_config
.
auth_config
can be only one of the following:
Config for API key auth.
Config for HTTP Basic auth.
Config for Google Service Account auth.
Config for user oauth.
Config for user OIDC auth.
ApiKeyConfig
Config for authentication with API key.
name
string
Required. The parameter name of the API key. E.g. If the API request is "https://example.com/act?api_key=
api_key_secret
string
Required. The name of the SecretManager secret version resource storing the API key. Format: projects/{project}/secrets/{secrete}/versions/{version}
- If specified, the
secretmanager.versions.access
permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource.
Required. The location of the API key.
GoogleServiceAccountConfig
Config for Google Service Account Authentication.
service_account
string
Optional. The service account that the extension execution service runs as.
If the service account is specified, the
iam.serviceAccounts.getAccessToken
permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified service account.If not specified, the Vertex AI Extension Service Agent will be used to execute the Extension.
HttpBasicAuthConfig
Config for HTTP Basic Authentication.
credential_secret
string
Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: projects/{project}/secrets/{secrete}/versions/{version}
- If specified, the
secretmanager.versions.access
permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource.
OauthConfig
Config for user oauth.
Union field oauth_config
.
oauth_config
can be only one of the following:
access_token
string
Access token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time.
service_account
string
The service account used to generate access tokens for executing the Extension.
- If the service account is specified, the
iam.serviceAccounts.getAccessToken
permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the provided service account.
OidcConfig
Config for user OIDC auth.
Union field oidc_config
.
oidc_config
can be only one of the following:
id_token
string
OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time.
service_account
string
The service account used to generate an OpenID Connect (OIDC)-compatible JWT token signed by the Google OIDC Provider (accounts.google.com) for extension endpoint (https://cloud.google.com/iam/docs/create-short-lived-credentials-direct#sa-credentials-oidc).
The audience for the token will be set to the URL in the server url defined in the OpenApi spec.
If the service account is provided, the service account should grant
iam.serviceAccounts.getOpenIdToken
permission to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents).
AuthType
Type of Auth.
Enums | |
---|---|
AUTH_TYPE_UNSPECIFIED |
|
NO_AUTH |
No Auth. |
API_KEY_AUTH |
API Key Auth. |
HTTP_BASIC_AUTH |
HTTP Basic Auth. |
GOOGLE_SERVICE_ACCOUNT_AUTH |
Google Service Account Auth. |
OAUTH |
OAuth auth. |
OIDC_AUTH |
OpenID Connect (OIDC) Auth. |
BigQueryDestination
The BigQuery location for the output content.
output_uri
string
Required. BigQuery URI to a project or table, up to 2000 characters long.
When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist.
Accepted forms:
- BigQuery path. For example:
bq://projectId
orbq://projectId.bqDatasetId
orbq://projectId.bqDatasetId.bqTableId
.
BleuInput
Input for bleu metric.
Required. Spec for bleu score metric.
Required. Repeated bleu instances.
BleuInstance
Spec for bleu instance.
prediction
string
Required. Output of the evaluated model.
reference
string
Required. Ground truth used to compare against the prediction.
BleuMetricValue
Bleu metric value for an instance.
score
float
Output only. Bleu score.
BleuResults
Results for bleu metric.
Output only. Bleu metric values.
BleuSpec
Spec for bleu score metric - calculates the precision of n-grams in the prediction as compared to reference - returns a score ranging between 0 to 1.
use_effective_order
bool
Optional. Whether to use_effective_order to compute bleu score.
Blob
Content blob.
It's preferred to send as text
directly rather than raw bytes.
mime_type
string
Required. The IANA standard MIME type of the source data.
data
bytes
Required. Raw bytes.
CacheConfig
Config of GenAI caching features. This is a singleton resource.
name
string
Identifier. Name of the cache config. Format: - projects/{project}/cacheConfig
.
disable_cache
bool
If set to true, disables GenAI caching. Otherwise caching is enabled.
CachedContent
A resource used in LLM queries for users to explicitly specify what to cache and how to cache.
name
string
Immutable. Identifier. The server-generated resource name of the cached content Format: projects/{project}/locations/{location}/cachedContents/{cached_content}
display_name
string
Optional. Immutable. The user-generated meaningful display name of the cached content.
model
string
Immutable. The name of the publisher model to use for cached content. Format: projects/{project}/locations/{location}/publishers/{publisher}/models/{model}
Optional. Input only. Immutable. Developer set system instruction. Currently, text only
Optional. Input only. Immutable. The content to cache
Optional. Input only. Immutable. A list of Tools
the model may use to generate the next response
Optional. Input only. Immutable. Tool config. This config is shared for all tools
Output only. Creatation time of the cache entry.
Output only. When the cache entry was last updated in UTC time.
Output only. Metadata on the usage of the cached content.
expiration
. Expiration time of the cached content. expiration
can be only one of the following:Timestamp of when this resource is considered expired. This is always provided on output, regardless of what was sent on input.
Input only. The TTL for this resource. The expiration time is computed: now + TTL.
UsageMetadata
Metadata on the usage of the cached content.
total_token_count
int32
Total number of tokens that the cached content consumes.
text_count
int32
Number of text characters.
image_count
int32
Number of images.
video_duration_seconds
int32
Duration of video in seconds.
audio_duration_seconds
int32
Duration of audio in seconds.
CancelTuningJobRequest
Request message for GenAiTuningService.CancelTuningJob
.
name
string
Required. The name of the TuningJob to cancel. Format: projects/{project}/locations/{location}/tuningJobs/{tuning_job}
Candidate
A response candidate generated from the model.
index
int32
Output only. Index of the candidate.
Output only. Content parts of the candidate.
avg_logprobs
double
Output only. Average log probability score of the candidate.
Output only. Log-likelihood scores for the response tokens and top tokens
Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.
Output only. List of ratings for the safety of a response candidate.
There is at most one rating per category.
Output only. Source attribution of the generated content.
Output only. Metadata specifies sources used to ground generated content.
finish_message
string
Output only. Describes the reason the mode stopped generating tokens in more detail. This is only filled when finish_reason
is set.
FinishReason
The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.
Enums | |
---|---|
FINISH_REASON_UNSPECIFIED |
The finish reason is unspecified. |
STOP |
Token generation reached a natural stopping point or a configured stop sequence. |
MAX_TOKENS |
Token generation reached the configured maximum output tokens. |
SAFETY |
Token generation stopped because the content potentially contains safety violations. NOTE: When streaming, content is empty if content filters blocks the output. |
RECITATION |
Token generation stopped because the content potentially contains copyright violations. |
OTHER |
All other reasons that stopped the token generation. |
BLOCKLIST |
Token generation stopped because the content contains forbidden terms. |
PROHIBITED_CONTENT |
Token generation stopped for potentially containing prohibited content. |
SPII |
Token generation stopped because the content potentially contains Sensitive Personally Identifiable Information (SPII). |
MALFORMED_FUNCTION_CALL |
The function call generated by the model is invalid. |
ChatCompletionsRequest
Request message for [PredictionService.ChatCompletions]
endpoint
string
Required. The name of the endpoint requested to serve the prediction. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
Optional. The prediction input. Supports HTTP headers and arbitrary data payload.
Citation
Source attributions for content.
start_index
int32
Output only. Start index into the content.
end_index
int32
Output only. End index into the content.
uri
string
Output only. Url reference of the attribution.
title
string
Output only. Title of the attribution.
license
string
Output only. License of the attribution.
Output only. Publication date of the attribution.
CitationMetadata
A collection of source attributions for a piece of content.
Output only. List of citations.
Claim
Claim that is extracted from the input text and facts that support it.
fact_indexes[]
int32
Indexes of the facts supporting this claim.
start_index
int32
Index in the input text where the claim starts (inclusive).
end_index
int32
Index in the input text where the claim ends (exclusive).
score
float
Confidence score of this corroboration.
CodeExecutionResult
Result of executing the [ExecutableCode].
Always follows a part
containing the [ExecutableCode].
Required. Outcome of the code execution.
output
string
Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
Outcome
Enumeration of possible outcomes of the code execution.
Enums | |
---|---|
OUTCOME_UNSPECIFIED |
Unspecified status. This value should not be used. |
OUTCOME_OK |
Code execution completed successfully. |
OUTCOME_FAILED |
Code execution finished but with a failure. stderr should contain the reason. |
OUTCOME_DEADLINE_EXCEEDED |
Code execution ran for too long, and was cancelled. There may or may not be a partial output present. |
CoherenceInput
Input for coherence metric.
Required. Spec for coherence score metric.
Required. Coherence instance.
CoherenceInstance
Spec for coherence instance.
prediction
string
Required. Output of the evaluated model.
CoherenceResult
Spec for coherence result.
explanation
string
Output only. Explanation for coherence score.
score
float
Output only. Coherence score.
confidence
float
Output only. Confidence for coherence score.
CoherenceSpec
Spec for coherence score metric.
version
int32
Optional. Which version to use for evaluation.
Content
The base structured datatype containing multi-part content of a message.
A Content
includes a role
field designating the producer of the Content
and a parts
field containing multi-part data that contains the content of the message turn.
role
string
Optional. The producer of the content. Must be either 'user' or 'model'.
Useful to set for multi-turn conversations, otherwise can be left blank or unset.
Required. Ordered Parts
that constitute a single message. Parts may have different IANA MIME types.
CorpusStatus
RagCorpus status.
Output only. RagCorpus life state.
error_status
string
Output only. Only when the state
field is ERROR.
State
RagCorpus life state.
Enums | |
---|---|
UNKNOWN |
This state is not supposed to happen. |
INITIALIZED |
RagCorpus resource entry is initialized, but hasn't done validation. |
ACTIVE |
RagCorpus is provisioned successfully and is ready to serve. |
ERROR |
RagCorpus is in a problematic situation. See error_message field for details. |
CorroborateContentRequest
Request message for CorroborateContent.
parent
string
Required. The resource name of the Location from which to corroborate text. The users must have permission to make a call in the project. Format: projects/{project}/locations/{location}
.
Optional. Facts used to generate the text can also be used to corroborate the text.
Optional. Parameters that can be set to override default settings per request.
Optional. Input content to corroborate, only text format is supported for now.
Parameters
Parameters that can be overrided per request.
citation_threshold
double
Optional. Only return claims with citation score larger than the threshold.
CorroborateContentResponse
Response message for CorroborateContent.
Claims that are extracted from the input content and facts that support the claims.
corroboration_score
float
Confidence score of corroborating content. Value is [0,1] with 1 is the most confidence.
CountTokensRequest
Request message for PredictionService.CountTokens
.
endpoint
string
Required. The name of the Endpoint requested to perform token counting. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
model
string
Optional. The name of the publisher model requested to serve the prediction. Format: projects/{project}/locations/{location}/publishers/*/models/*
Optional. The instances that are the input to token counting call. Schema is identical to the prediction schema of the underlying model.
Optional. Input content.
Optional. A list of Tools
the model may use to generate the next response.
A Tool
is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.
Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
Optional. Generation config that the model will use to generate the response.
CountTokensResponse
Response message for PredictionService.CountTokens
.
total_tokens
int32
The total number of tokens counted across all instances from the request.
total_billable_characters
int32
The total number of billable characters counted across all instances from the request.
CreateCachedContentRequest
Request message for GenAiCacheService.CreateCachedContent
.
parent
string
Required. The parent resource where the cached content will be created
Required. The cached content to create
CreateRagCorpusOperationMetadata
Runtime operation information for VertexRagDataService.CreateRagCorpus
.
The operation generic information.
CreateRagCorpusRequest
Request message for VertexRagDataService.CreateRagCorpus
.
parent
string
Required. The resource name of the Location to create the RagCorpus in. Format: projects/{project}/locations/{location}
Required. The RagCorpus to create.
CreateReasoningEngineOperationMetadata
Details of ReasoningEngineService.CreateReasoningEngine
operation.
The common part of the operation metadata.
CreateReasoningEngineRequest
Request message for ReasoningEngineService.CreateReasoningEngine
.
parent
string
Required. The resource name of the Location to create the ReasoningEngine in. Format: projects/{project}/locations/{location}
Required. The ReasoningEngine to create.
CreateTuningJobRequest
Request message for GenAiTuningService.CreateTuningJob
.
parent
string
Required. The resource name of the Location to create the TuningJob in. Format: projects/{project}/locations/{location}
Required. The TuningJob to create.
DatasetDistribution
Distribution computed over a tuning dataset.
sum
double
Output only. Sum of a given population of values.
min
double
Output only. The minimum of the population values.
max
double
Output only. The maximum of the population values.
mean
double
Output only. The arithmetic mean of the values in the population.
median
double
Output only. The median of the values in the population.
p5
double
Output only. The 5th percentile of the values in the population.
p95
double
Output only. The 95th percentile of the values in the population.
Output only. Defines the histogram bucket.
DistributionBucket
Dataset bucket used to create a histogram for the distribution given a population of values.
count
int64
Output only. Number of values in the bucket.
left
double
Output only. Left bound of the bucket.
right
double
Output only. Right bound of the bucket.
DatasetStats
Statistics computed over a tuning dataset.
tuning_dataset_example_count
int64
Output only. Number of examples in the tuning dataset.
total_tuning_character_count
int64
Output only. Number of tuning characters in the tuning dataset.
total_billable_character_count
int64
Output only. Number of billable characters in the tuning dataset.
tuning_step_count
int64
Output only. Number of tuning steps for this Tuning Job.
Output only. Dataset distributions for the user input tokens.
Output only. Dataset distributions for the messages per example.
Output only. Sample user messages in the training dataset uri.
Output only. Dataset distributions for the user output tokens.
DeleteCachedContentRequest
Request message for GenAiCacheService.DeleteCachedContent
.
name
string
Required. The resource name referring to the cached content
DeleteExtensionRequest
Request message for ExtensionRegistryService.DeleteExtension
.
name
string
Required. The name of the Extension resource to be deleted. Format: projects/{project}/locations/{location}/extensions/{extension}
DeleteOperationMetadata
Details of operations that perform deletes of any entities.
The common part of the operation metadata.
DeleteRagCorpusRequest
Request message for VertexRagDataService.DeleteRagCorpus
.
name
string
Required. The name of the RagCorpus resource to be deleted. Format: projects/{project}/locations/{location}/ragCorpora/{rag_corpus}
force
bool
Optional. If set to true, any RagFiles in this RagCorpus will also be deleted. Otherwise, the request will only work if the RagCorpus has no RagFiles.
DeleteRagFileRequest
Request message for VertexRagDataService.DeleteRagFile
.
name
string
Required. The name of the RagFile resource to be deleted. Format: projects/{project}/locations/{location}/ragCorpora/{rag_corpus}/ragFiles/{rag_file}
DeleteReasoningEngineRequest
Request message for ReasoningEngineService.DeleteReasoningEngine
.
name
string
Required. The name of the ReasoningEngine resource to be deleted. Format: projects/{project}/locations/{location}/reasoningEngines/{reasoning_engine}
DirectUploadSource
This type has no fields.
The input content is encapsulated and uploaded in the request.
DistillationDataStats
Statistics computed for datasets used for distillation.
Output only. Statistics computed for the training dataset.
DistillationHyperParameters
Hyperparameters for Distillation.
Optional. Adapter size for distillation.
epoch_count
int64
Optional. Number of complete passes the model makes over the entire training dataset during training.
learning_rate_multiplier
double
Optional. Multiplier for adjusting the default learning rate.
DistillationSpec
Tuning Spec for Distillation.
training_dataset_uri
string
Required. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file.
Optional. Hyperparameters for Distillation.
student_model
string
The student model that is being tuned, e.g., "google/gemma-2b-1.1-it".
pipeline_root_directory
string
Required. A path in a Cloud Storage bucket, which will be treated as the root output directory of the distillation pipeline. It is used by the system to generate the paths of output artifacts.
teacher_model
. The teacher model that is being distilled from, e.g., "gemini-1.0-pro-002". teacher_model
can be only one of the following:base_teacher_model
string
The base teacher model that is being distilled, e.g., "gemini-1.0-pro-002".
tuned_teacher_model_source
string
The resource name of the Tuned teacher model. Format: projects/{project}/locations/{location}/models/{model}
.
validation_dataset_uri
string
Optional. Cloud Storage path to file containing validation dataset for tuning. The dataset must be formatted as a JSONL file.
DynamicRetrievalConfig
Describes the options to customize dynamic retrieval.
The mode of the predictor to be used in dynamic retrieval.
dynamic_threshold
float
Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used.
Mode
The mode of the predictor to be used in dynamic retrieval.
Enums | |
---|---|
MODE_UNSPECIFIED |
Always trigger retrieval. |
MODE_DYNAMIC |
Run retrieval only when system decides it is necessary. |
EncryptionSpec
Represents a customer-managed encryption key spec that can be applied to a top-level resource.
kms_key_name
string
Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
EvaluateInstancesRequest
Request message for EvaluationService.EvaluateInstances.
location
string
Required. The resource name of the Location to evaluate the instances. Format: projects/{project}/locations/{location}
metric_inputs
. Instances and specs for evaluation metric_inputs
can be only one of the following:Auto metric instances. Instances and metric spec for exact match metric.
Instances and metric spec for bleu metric.
Instances and metric spec for rouge metric.
LLM-based metric instance. General text generation metrics, applicable to other categories. Input for fluency metric.
Input for coherence metric.
Input for safety metric.
Input for groundedness metric.
Input for fulfillment metric.
Input for summarization quality metric.
Input for pairwise summarization quality metric.
Input for summarization helpfulness metric.
Input for summarization verbosity metric.
Input for question answering quality metric.
Input for pairwise question answering quality metric.
Input for question answering relevance metric.
Input for question answering helpfulness metric.
Input for question answering correctness metric.
Input for pointwise metric.
Input for pairwise metric.
Tool call metric instances. Input for tool call valid metric.
Input for tool name match metric.
Input for tool parameter key match metric.
Input for tool parameter key value match metric.
EvaluateInstancesResponse
Response message for EvaluationService.EvaluateInstances.
evaluation_results
. Evaluation results will be served in the same order as presented in EvaluationRequest.instances. evaluation_results
can be only one of the following:Auto metric evaluation results. Results for exact match metric.
Results for bleu metric.
Results for rouge metric.
LLM-based metric evaluation result. General text generation metrics, applicable to other categories. Result for fluency metric.
Result for coherence metric.
Result for safety metric.
Result for groundedness metric.
Result for fulfillment metric.
Summarization only metrics. Result for summarization quality metric.
Result for pairwise summarization quality metric.
Result for summarization helpfulness metric.
Result for summarization verbosity metric.
Question answering only metrics. Result for question answering quality metric.
Result for pairwise question answering quality metric.
Result for question answering relevance metric.
Result for question answering helpfulness metric.
Result for question answering correctness metric.
Generic metrics. Result for pointwise metric.
Result for pairwise metric.
Tool call metrics. Results for tool call valid metric.
Results for tool name match metric.
Results for tool parameter key match metric.
Results for tool parameter key value match metric.
ExactMatchInput
Input for exact match metric.
Required. Spec for exact match metric.
Required. Repeated exact match instances.
ExactMatchInstance
Spec for exact match instance.
prediction
string
Required. Output of the evaluated model.
reference
string
Required. Ground truth used to compare against the prediction.
ExactMatchMetricValue
Exact match metric value for an instance.
score
float
Output only. Exact match score.
ExactMatchResults
Results for exact match metric.
Output only. Exact match metric values.
ExactMatchSpec
This type has no fields.
Spec for exact match metric - returns 1 if prediction and reference exactly matches, otherwise 0.
ExecutableCode
Code generated by the model that is meant to be executed, and the result returned to the model.
Generated when using the [FunctionDeclaration] tool and [FunctionCallingConfig] mode is set to [Mode.CODE].
Required. Programming language of the code
.
code
string
Required. The code to be executed.
Language
Supported programming languages for the generated code.
Enums | |
---|---|
LANGUAGE_UNSPECIFIED |
Unspecified language. This value should not be used. |
PYTHON |
Python >= 3.10, with numpy and simpy available. |
ExecuteExtensionRequest
Request message for ExtensionExecutionService.ExecuteExtension
.
name
string
Required. Name (identifier) of the extension; Format: projects/{project}/locations/{location}/extensions/{extension}
operation_id
string
Required. The desired ID of the operation to be executed in this extension as defined in ExtensionOperation.operation_id
.
Optional. Request parameters that will be used for executing this operation.
The struct should be in a form of map with param name as the key and actual param value as the value. E.g. If this operation requires a param "name" to be set to "abc". you can set this to something like {"name": "abc"}.
Optional. Auth config provided at runtime to override the default value in [Extension.manifest.auth_config][]. The AuthConfig.auth_type should match the value in [Extension.manifest.auth_config][].
ExecuteExtensionResponse
Response message for ExtensionExecutionService.ExecuteExtension
.
content
string
Response content from the extension. The content should be conformant to the response.content schema in the extension's manifest/OpenAPI spec.
Extension
Extensions are tools for large language models to access external data, run computations, etc.
name
string
Identifier. The resource name of the Extension.
display_name
string
Required. The display name of the Extension. The name can be up to 128 characters long and can consist of any UTF-8 characters.
description
string
Optional. The description of the Extension.
Output only. Timestamp when this Extension was created.
Output only. Timestamp when this Extension was most recently updated.
etag
string
Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
Required. Manifest of the Extension.
Output only. Supported operations.
Optional. Runtime config controlling the runtime behavior of this Extension.
Optional. Examples to illustrate the usage of the extension as a tool.
Optional. The PrivateServiceConnect config for the extension. If specified, the service endpoints associated with the Extension should be registered with private network access in the provided Service Directory (https://cloud.google.com/service-directory/docs/configuring-private-network-access).
If the service contains more than one endpoint with a network, the service will arbitrarilty choose one of the endpoints to use for extension execution.
ExtensionManifest
Manifest spec of an Extension needed for runtime execution.
name
string
Required. Extension name shown to the LLM. The name can be up to 128 characters long.
description
string
Required. The natural language description shown to the LLM. It should describe the usage of the extension, and is essential for the LLM to perform reasoning. e.g., if the extension is a data store, you can let the LLM know what data it contains.
Required. Immutable. The API specification shown to the LLM.
Required. Immutable. Type of auth supported by this extension.
ApiSpec
The API specification shown to the LLM.
Union field api_spec
.
api_spec
can be only one of the following:
open_api_yaml
string
The API spec in Open API standard and YAML format.
open_api_gcs_uri
string
Cloud Storage URI pointing to the OpenAPI spec.
ExtensionOperation
Operation of an extension.
operation_id
string
Operation ID that uniquely identifies the operations among the extension. See: "Operation Object" in https://swagger.io/specification/.
This field is parsed from the OpenAPI spec. For HTTP extensions, if it does not exist in the spec, we will generate one from the HTTP method and path.
Output only. Structured representation of a function declaration as defined by the OpenAPI Spec.
ExtensionPrivateServiceConnectConfig
PrivateExtensionConfig configuration for the extension.
service_directory
string
Required. The Service Directory resource name in which the service endpoints associated to the extension are registered. Format: projects/{project_id}/locations/{location_id}/namespaces/{namespace_id}/services/{service_id}
- The Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) should be granted
servicedirectory.viewer
andservicedirectory.pscAuthorizedService
roles on the resource.
Fact
The fact used in grounding.
query
string
Query that is used to retrieve this fact.
title
string
If present, it refers to the title of this fact.
uri
string
If present, this uri links to the source of the fact.
summary
string
If present, the summary/snippet of the fact.
vector_distance
double
If present, the distance between the query vector and this fact vector.
FileData
URI based data.
mime_type
string
Required. The IANA standard MIME type of the source data.
file_uri
string
Required. URI.
FileStatus
RagFile status.
Output only. RagFile state.
error_status
string
Output only. Only when the state
field is ERROR.
State
RagFile state.
Enums | |
---|---|
STATE_UNSPECIFIED |
RagFile state is unspecified. |
ACTIVE |
RagFile resource has been created and indexed successfully. |
ERROR |
RagFile resource is in a problematic state. See error_message field for details. |
FluencyInput
Input for fluency metric.
Required. Spec for fluency score metric.
Required. Fluency instance.
FluencyInstance
Spec for fluency instance.
prediction
string
Required. Output of the evaluated model.
FluencyResult
Spec for fluency result.
explanation
string
Output only. Explanation for fluency score.
score
float
Output only. Fluency score.
confidence
float
Output only. Confidence for fluency score.
FluencySpec
Spec for fluency score metric.
version
int32
Optional. Which version to use for evaluation.
FulfillmentInput
Input for fulfillment metric.
Required. Spec for fulfillment score metric.
Required. Fulfillment instance.
FulfillmentInstance
Spec for fulfillment instance.
prediction
string
Required. Output of the evaluated model.
instruction
string
Required. Inference instruction prompt to compare prediction with.
FulfillmentResult
Spec for fulfillment result.
explanation
string
Output only. Explanation for fulfillment score.
score
float
Output only. Fulfillment score.
confidence
float
Output only. Confidence for fulfillment score.
FulfillmentSpec
Spec for fulfillment metric.
version
int32
Optional. Which version to use for evaluation.
FunctionCall
A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values.
name
string
Required. The name of the function to call. Matches [FunctionDeclaration.name].
Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
FunctionCallingConfig
Function calling config.
Optional. Function calling mode.
allowed_function_names[]
string
Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided.
Mode
Function calling mode.
Enums | |
---|---|
MODE_UNSPECIFIED |
Unspecified function calling mode. This value should not be used. |
AUTO |
Default model behavior, model decides to predict either function calls or natural language response. |
ANY |
Model is constrained to always predicting function calls only. If "allowed_function_names" are set, the predicted function calls will be limited to any one of "allowed_function_names", else the predicted function calls will be any one of the provided "function_declarations". |
NONE |
Model will not predict any function calls. Model behavior is same as when not passing any function declarations. |
FunctionDeclaration
Structured representation of a function declaration as defined by the OpenAPI 3.0 specification. Included in this declaration are the function name and parameters. This FunctionDeclaration is a representation of a block of code that can be used as a Tool
by the model and executed by the client.
name
string
Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64.
description
string
Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function.
Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1
Optional. Describes the output from this function in JSON Schema format. Reflects the Open API 3.03 Response Object. The Schema defines the type used for the response value of the function.
FunctionResponse
The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction.
name
string
Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
Required. The function response in JSON object format. Use "output" key to specify function output and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as function output.
GcsDestination
The Google Cloud Storage location where the output is to be written to.
output_uri_prefix
string
Required. Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
GcsSource
The Google Cloud Storage location for the input content.
uris[]
string
Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
GenerateContentRequest
Request message for [PredictionService.GenerateContent].
model
string
Required. The fully qualified name of the publisher model or tuned model endpoint to use.
Publisher model format: projects/{project}/locations/{location}/publishers/*/models/*
Tuned model endpoint format: projects/{project}/locations/{location}/endpoints/{endpoint}
Required. The content of the current conversation with the model.
For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request.
cached_content
string
Optional. The name of the cached content used as context to serve the prediction. Note: only used in explicit caching, where users can have control over caching (e.g. what content to cache) and enjoy guaranteed cost savings. Format: projects/{project}/locations/{location}/cachedContents/{cachedContent}
Optional. A list of Tools
the model may use to generate the next response.
A Tool
is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.
Optional. Tool config. This config is shared for all tools provided in the request.
labels
map<string, string>
Optional. The labels with user-defined metadata for the request. It is used for billing and reporting only.
Label keys and values can be no longer than 63 characters (Unicode codepoints) and can only contain lowercase letters, numeric characters, underscores, and dashes. International characters are allowed. Label values are optional. Label keys must start with a letter.
Optional. Per request settings for blocking unsafe content. Enforced on GenerateContentResponse.candidates.
Optional. Generation config.
Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
GenerateContentResponse
Response message for [PredictionService.GenerateContent].
Output only. Generated candidates.
model_version
string
Output only. The model version used to generate the response.
Output only. Content filter results for a prompt sent in the request. Note: Sent only in the first stream chunk. Only happens when no candidates were generated due to content violations.
Usage metadata about the response(s).
PromptFeedback
Content filter results for a prompt sent in the request.
Output only. Blocked reason.
Output only. Safety ratings.
block_reason_message
string
Output only. A readable block reason message.
BlockedReason
Blocked reason enumeration.
Enums | |
---|---|
BLOCKED_REASON_UNSPECIFIED |
Unspecified blocked reason. |
SAFETY |
Candidates blocked due to safety. |
OTHER |
Candidates blocked due to other reason. |
BLOCKLIST |
Candidates blocked due to the terms which are included from the terminology blocklist. |
PROHIBITED_CONTENT |
Candidates blocked due to prohibited content. |
UsageMetadata
Usage metadata about response(s).
prompt_token_count
int32
Number of tokens in the request. When cached_content
is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.
candidates_token_count
int32
Number of tokens in the response(s).
total_token_count
int32
Total token count for prompt and response candidates.
cached_content_token_count
int32
Output only. Number of tokens in the cached part in the input (the cached content).
GenerationConfig
Generation config.
stop_sequences[]
string
Optional. Stop sequences.
response_mime_type
string
Optional. Output response mimetype of the generated candidate text. Supported mimetype: - text/plain
: (default) Text output. - application/json
: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature.
temperature
float
Optional. Controls the randomness of predictions.
top_p
float
Optional. If specified, nucleus sampling will be used.
top_k
float
Optional. If specified, top-k sampling will be used.
candidate_count
int32
Optional. Number of candidates to generate.
max_output_tokens
int32
Optional. The maximum number of output tokens to generate per message.
response_logprobs
bool
Optional. If true, export the logprobs results in response.
logprobs
int32
Optional. Logit probabilities.
presence_penalty
float
Optional. Positive penalties.
frequency_penalty
float
Optional. Frequency penalties.
seed
int32
Optional. Seed.
Optional. The Schema
object allows the definition of input and output data types. These types can be objects, but also primitives and arrays. Represents a select subset of an OpenAPI 3.0 schema object. If set, a compatible response_mime_type must also be set. Compatible mimetypes: application/json
: Schema for JSON response.
Optional. Routing configuration.
audio_timestamp
bool
Optional. If enabled, audio timestamp will be included in the request to the model.
RoutingConfig
The configuration for routing the request to a specific model.
routing_config
. Routing mode. routing_config
can be only one of the following:Automated routing.
Manual routing.
AutoRoutingMode
When automated routing is specified, the routing will be determined by the pretrained routing model and customer provided model routing preference.
The model routing preference.
ModelRoutingPreference
The model routing preference.
Enums | |
---|---|
UNKNOWN |
Unspecified model routing preference. |
PRIORITIZE_QUALITY |
Prefer higher quality over low cost. |
BALANCED |
Balanced model routing preference. |
PRIORITIZE_COST |
Prefer lower cost over higher quality. |
ManualRoutingMode
When manual routing is set, the specified model will be used directly.
model_name
string
The model name to use. Only the public LLM models are accepted. e.g. 'gemini-1.5-pro-001'.
GenericOperationMetadata
Generic Metadata shared by all operations.
Output only. Partial failures encountered. E.g. single files that couldn't be read. This field should never exceed 20 entries. Status details field will contain standard Google Cloud error details.
Output only. Time when the operation was created.
Output only. Time when the operation was updated for the last time. If the operation has finished (successfully or not), this is the finish time.
GetCacheConfigRequest
Request message for getting a cache config.
name
string
Required. Name of the cache config. Format: - projects/{project}/cacheConfig
.
GetCachedContentRequest
Request message for GenAiCacheService.GetCachedContent
.
name
string
Required. The resource name referring to the cached content
GetExtensionRequest
Request message for ExtensionRegistryService.GetExtension
.
name
string
Required. The name of the Extension resource. Format: projects/{project}/locations/{location}/extensions/{extension}
GetRagCorpusRequest
Request message for VertexRagDataService.GetRagCorpus
name
string
Required. The name of the RagCorpus resource. Format: projects/{project}/locations/{location}/ragCorpora/{rag_corpus}
GetRagFileRequest
Request message for VertexRagDataService.GetRagFile
name
string
Required. The name of the RagFile resource. Format: projects/{project}/locations/{location}/ragCorpora/{rag_corpus}/ragFiles/{rag_file}
GetReasoningEngineRequest
Request message for ReasoningEngineService.GetReasoningEngine
.
name
string
Required. The name of the ReasoningEngine resource. Format: projects/{project}/locations/{location}/reasoningEngines/{reasoning_engine}
GetTuningJobRequest
Request message for GenAiTuningService.GetTuningJob
.
name
string
Required. The name of the TuningJob resource. Format: projects/{project}/locations/{location}/tuningJobs/{tuning_job}
GoogleDriveSource
The Google Drive location for the input content.
Required. Google Drive resource IDs.
ResourceId
The type and ID of the Google Drive resource.
Required. The type of the Google Drive resource.
resource_id
string
Required. The ID of the Google Drive resource.
ResourceType
The type of the Google Drive resource.
Enums | |
---|---|
RESOURCE_TYPE_UNSPECIFIED |
Unspecified resource type. |
RESOURCE_TYPE_FILE |
File resource type. |
RESOURCE_TYPE_FOLDER |
Folder resource type. |
GoogleSearchRetrieval
Tool to retrieve public web data for grounding, powered by Google.
Specifies the dynamic retrieval configuration for the given source.
GroundednessInput
Input for groundedness metric.
Required. Spec for groundedness metric.
Required. Groundedness instance.
GroundednessInstance
Spec for groundedness instance.
prediction
string
Required. Output of the evaluated model.
context
string
Required. Background information provided in context used to compare against the prediction.
GroundednessResult
Spec for groundedness result.
explanation
string
Output only. Explanation for groundedness score.
score
float
Output only. Groundedness score.
confidence
float
Output only. Confidence for groundedness score.
GroundednessSpec
Spec for groundedness metric.
version
int32
Optional. Which version to use for evaluation.
GroundingChunk
Grounding chunk.
chunk_type
. Chunk type. chunk_type
can be only one of the following:Grounding chunk from the web.
Grounding chunk from context retrieved by the retrieval tools.
RetrievedContext
Chunk from context retrieved by the retrieval tools.
uri
string
URI reference of the attribution.
title
string
Title of the attribution.
text
string
Text of the attribution.
Web
Chunk from the web.
uri
string
URI reference of the chunk.
title
string
Title of the chunk.
GroundingMetadata
Metadata returned to client when grounding is enabled.
web_search_queries[]
string
Optional. Web search queries for the following-up web search.
retrieval_queries[]
string
Optional. Queries executed by the retrieval tools.
List of supporting references retrieved from specified grounding source.
Optional. List of grounding support.
Optional. Google search entry for the following-up web searches.
Optional. Output only. Retrieval metadata.
GroundingSupport
Grounding support.
grounding_chunk_indices[]
int32
A list of indices (into 'grounding_chunk') specifying the citations associated with the claim. For instance [1,3,4] means that grounding_chunk[1], grounding_chunk[3], grounding_chunk[4] are the retrieved content attributed to the claim.
confidence_scores[]
float
Confidence score of the support references. Ranges from 0 to 1. 1 is the most confident. This list must have the same size as the grounding_chunk_indices.
Segment of the content this support belongs to.
HarmCategory
Harm categories that will block the content.
Enums | |
---|---|
HARM_CATEGORY_UNSPECIFIED |
The harm category is unspecified. |
HARM_CATEGORY_HATE_SPEECH |
The harm category is hate speech. |
HARM_CATEGORY_DANGEROUS_CONTENT |
The harm category is dangerous content. |
HARM_CATEGORY_HARASSMENT |
The harm category is harassment. |
HARM_CATEGORY_SEXUALLY_EXPLICIT |
The harm category is sexually explicit content. |
HARM_CATEGORY_CIVIC_INTEGRITY |
The harm category is civic integrity. |
HttpElementLocation
Enum of location an HTTP element can be.
Enums | |
---|---|
HTTP_IN_UNSPECIFIED |
|
HTTP_IN_QUERY |
Element is in the HTTP request query. |
HTTP_IN_HEADER |
Element is in the HTTP request header. |
HTTP_IN_PATH |
Element is in the HTTP request path. |
HTTP_IN_BODY |
Element is in the HTTP request body. |
HTTP_IN_COOKIE |
Element is in the HTTP request cookie. |
ImportExtensionOperationMetadata
Details of ExtensionRegistryService.ImportExtension
operation.
The common part of the operation metadata.
ImportExtensionRequest
Request message for ExtensionRegistryService.ImportExtension
.
parent
string
Required. The resource name of the Location to import the Extension in. Format: projects/{project}/locations/{location}
Required. The Extension to import.
ImportRagFilesConfig
Config for importing RagFiles.
Specifies the size and overlap of chunks after importing RagFiles.
Specifies the parsing config for RagFiles.
max_embedding_requests_per_min
int32
Optional. The max number of queries per minute that this job is allowed to make to the embedding model specified on the corpus. This value is specific to this job and not shared across other import jobs. Consult the Quotas page on the project to set an appropriate value here. If unspecified, a default value of 1,000 QPM would be used.
import_source
. The source of the import. import_source
can be only one of the following:Google Cloud Storage location. Supports importing individual files as well as entire Google Cloud Storage directories. Sample formats: - gs://bucket_name/my_directory/object_name/my_file.txt
- gs://bucket_name/my_directory
Google Drive location. Supports importing individual files as well as Google Drive folders.
Slack channels with their corresponding access tokens.
Jira queries with their corresponding authentication.
partial_failure_sink
. Optional. If provided, all partial failures are written to the sink. Deprecated. Prefer to use the import_result_sink
. partial_failure_sink
can be only one of the following:The Cloud Storage path to write partial failures to. Deprecated. Prefer to use import_result_gcs_sink
.
The BigQuery destination to write partial failures to. It should be a bigquery table resource name (e.g. "bq://projectId.bqDatasetId.bqTableId"). The dataset must exist. If the table does not exist, it will be created with the expected schema. If the table exists, the schema will be validated and data will be added to this existing table. Deprecated. Prefer to use import_result_bq_sink
.
ImportRagFilesOperationMetadata
Runtime operation information for VertexRagDataService.ImportRagFiles
.
The operation generic information.
rag_corpus_id
int64
The resource ID of RagCorpus that this operation is executed on.
Output only. The config that was passed in the ImportRagFilesRequest.
progress_percentage
int32
The progress percentage of the operation. Value is in the range [0, 100]. This percentage is calculated as follows: progress_percentage = 100 * (successes + failures + skips) / total
ImportRagFilesRequest
Request message for VertexRagDataService.ImportRagFiles
.
parent
string
Required. The name of the RagCorpus resource into which to import files. Format: projects/{project}/locations/{location}/ragCorpora/{rag_corpus}
Required. The config for the RagFiles to be synced and imported into the RagCorpus. VertexRagDataService.ImportRagFiles
.
ImportRagFilesResponse
Response message for VertexRagDataService.ImportRagFiles
.
imported_rag_files_count
int64
The number of RagFiles that had been imported into the RagCorpus.
failed_rag_files_count
int64
The number of RagFiles that had failed while importing into the RagCorpus.
skipped_rag_files_count
int64
The number of RagFiles that was skipped while importing into the RagCorpus.
partial_failure_sink
. The location into which the partial failures were written. partial_failure_sink
can be only one of the following:partial_failures_gcs_path
string
The Google Cloud Storage path into which the partial failures were written.
partial_failures_bigquery_table
string
The BigQuery table into which the partial failures were written.
JiraSource
The Jira source for the ImportRagFilesRequest.
Required. The Jira queries.
JiraQueries
JiraQueries contains the Jira queries and corresponding authentication.
projects[]
string
A list of Jira projects to import in their entirety.
custom_queries[]
string
A list of custom Jira queries to import. For information about JQL (Jira Query Language), see https://support.atlassian.com/jira-service-management-cloud/docs/use-advanced-search-with-jira-query-language-jql/
email
string
Required. The Jira email address.
server_uri
string
Required. The Jira server URI.
Required. The SecretManager secret version resource name (e.g. projects/{project}/secrets/{secret}/versions/{version}) storing the Jira API key (https://support.atlassian.com/atlassian-account/docs/manage-api-tokens-for-your-atlassian-account).
JobState
Describes the state of a job.
Enums | |
---|---|
JOB_STATE_UNSPECIFIED |
The job state is unspecified. |
JOB_STATE_QUEUED |
The job has been just created or resumed and processing has not yet begun. |
JOB_STATE_PENDING |
The service is preparing to run the job. |
JOB_STATE_RUNNING |
The job is in progress. |
JOB_STATE_SUCCEEDED |
The job completed successfully. |
JOB_STATE_FAILED |
The job failed. |
JOB_STATE_CANCELLING |
The job is being cancelled. From this state the job may only go to either JOB_STATE_SUCCEEDED , JOB_STATE_FAILED or JOB_STATE_CANCELLED . |
JOB_STATE_CANCELLED |
The job has been cancelled. |
JOB_STATE_PAUSED |
The job has been stopped, and can be resumed. |
JOB_STATE_EXPIRED |
The job has expired. |
JOB_STATE_UPDATING |
The job is being updated. Only jobs in the RUNNING state can be updated. After updating, the job goes back to the RUNNING state. |
JOB_STATE_PARTIALLY_SUCCEEDED |
The job is partially succeeded, some results may be missing due to errors. |
ListCachedContentsRequest
Request to list CachedContents.
parent
string
Required. The parent, which owns this collection of cached contents.
page_size
int32
Optional. The maximum number of cached contents to return. The service may return fewer than this value. If unspecified, some default (under maximum) number of items will be returned. The maximum value is 1000; values above 1000 will be coerced to 1000.
page_token
string
Optional. A page token, received from a previous ListCachedContents
call. Provide this to retrieve the subsequent page.
When paginating, all other parameters provided to ListCachedContents
must match the call that provided the page token.
ListCachedContentsResponse
Response with a list of CachedContents.
List of cached contents.
next_page_token
string
A token, which can be sent as page_token
to retrieve the next page. If this field is omitted, there are no subsequent pages.
ListExtensionsRequest
Request message for ExtensionRegistryService.ListExtensions
.
parent
string
Required. The resource name of the Location to list the Extensions from. Format: projects/{project}/locations/{location}
filter
string
Optional. The standard list filter. Supported fields: * display_name
* create_time
* update_time
More detail in AIP-160.
page_size
int32
Optional. The standard list page size.
page_token
string
Optional. The standard list page token.
order_by
string
Optional. A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields: * display_name
* create_time
* update_time
Example: display_name, create_time desc
.
ListExtensionsResponse
Response message for ExtensionRegistryService.ListExtensions
List of Extension in the requested page.
next_page_token
string
A token to retrieve the next page of results. Pass to ListExtensionsRequest.page_token
to obtain that page.
ListRagCorporaRequest
Request message for VertexRagDataService.ListRagCorpora
.
parent
string
Required. The resource name of the Location from which to list the RagCorpora. Format: projects/{project}/locations/{location}
page_size
int32
Optional. The standard list page size.
page_token
string
Optional. The standard list page token. Typically obtained via ListRagCorporaResponse.next_page_token
of the previous VertexRagDataService.ListRagCorpora
call.
ListRagCorporaResponse
Response message for VertexRagDataService.ListRagCorpora
.
List of RagCorpora in the requested page.
next_page_token
string
A token to retrieve the next page of results. Pass to ListRagCorporaRequest.page_token
to obtain that page.
ListRagFilesRequest
Request message for VertexRagDataService.ListRagFiles
.
parent
string
Required. The resource name of the RagCorpus from which to list the RagFiles. Format: projects/{project}/locations/{location}/ragCorpora/{rag_corpus}
page_size
int32
Optional. The standard list page size.
page_token
string
Optional. The standard list page token. Typically obtained via ListRagFilesResponse.next_page_token
of the previous VertexRagDataService.ListRagFiles
call.
ListRagFilesResponse
Response message for VertexRagDataService.ListRagFiles
.
List of RagFiles in the requested page.
next_page_token
string
A token to retrieve the next page of results. Pass to ListRagFilesRequest.page_token
to obtain that page.
ListReasoningEnginesRequest
Request message for ReasoningEngineService.ListReasoningEngines
.
parent
string
Required. The resource name of the Location to list the ReasoningEngines from. Format: projects/{project}/locations/{location}
filter
string
Optional. The standard list filter. More detail in AIP-160.
page_size
int32
Optional. The standard list page size.
page_token
string
Optional. The standard list page token.
ListReasoningEnginesResponse
Response message for ReasoningEngineService.ListReasoningEngines
List of ReasoningEngines in the requested page.
next_page_token
string
A token to retrieve the next page of results. Pass to ListReasoningEnginesRequest.page_token
to obtain that page.
ListTuningJobsRequest
Request message for GenAiTuningService.ListTuningJobs
.
parent
string
Required. The resource name of the Location to list the TuningJobs from. Format: projects/{project}/locations/{location}
filter
string
Optional. The standard list filter.
page_size
int32
Optional. The standard list page size.
page_token
string
Optional. The standard list page token. Typically obtained via [ListTuningJob.next_page_token][] of the previous GenAiTuningService.ListTuningJob][] call.
ListTuningJobsResponse
Response message for GenAiTuningService.ListTuningJobs
List of TuningJobs in the requested page.
next_page_token
string
A token to retrieve the next page of results. Pass to ListTuningJobsRequest.page_token
to obtain that page.
LogprobsResult
Logprobs Result
Length = total number of decoding steps.
Length = total number of decoding steps. The chosen candidates may or may not be in top_candidates.
Candidate
Candidate for the logprobs token and score.
token
string
The candidate's token string value.
token_id
int32
The candidate's token id value.
log_probability
float
The candidate's log probability.
TopCandidates
Candidates with top log probabilities at each decoding step.
Sorted by log probability in descending order.
PairwiseChoice
Pairwise prediction autorater preference.
Enums | |
---|---|
PAIRWISE_CHOICE_UNSPECIFIED |
Unspecified prediction choice. |
BASELINE |
Baseline prediction wins |
CANDIDATE |
Candidate prediction wins |
TIE |
Winner cannot be determined |
PairwiseMetricInput
Input for pairwise metric.
Required. Spec for pairwise metric.
Required. Pairwise metric instance.
PairwiseMetricInstance
Pairwise metric instance. Usually one instance corresponds to one row in an evaluation dataset.
instance
. Instance for pairwise metric. instance
can be only one of the following:json_instance
string
Instance specified as a json string. String key-value pairs are expected in the json_instance to render PairwiseMetricSpec.instance_prompt_template.
PairwiseMetricResult
Spec for pairwise metric result.
Output only. Pairwise metric choice.
explanation
string
Output only. Explanation for pairwise metric score.
PairwiseMetricSpec
Spec for pairwise metric.
metric_prompt_template
string
Required. Metric prompt template for pairwise metric.
PairwiseQuestionAnsweringQualityInput
Input for pairwise question answering quality metric.
Required. Spec for pairwise question answering quality score metric.
Required. Pairwise question answering quality instance.
PairwiseQuestionAnsweringQualityInstance
Spec for pairwise question answering quality instance.
prediction
string
Required. Output of the candidate model.
baseline_prediction
string
Required. Output of the baseline model.
reference
string
Optional. Ground truth used to compare against the prediction.
context
string
Required. Text to answer the question.
instruction
string
Required. Question Answering prompt for LLM.
PairwiseQuestionAnsweringQualityResult
Spec for pairwise question answering quality result.
Output only. Pairwise question answering prediction choice.
explanation
string
Output only. Explanation for question answering quality score.
confidence
float
Output only. Confidence for question answering quality score.
PairwiseQuestionAnsweringQualitySpec
Spec for pairwise question answering quality score metric.
use_reference
bool
Optional. Whether to use instance.reference to compute question answering quality.
version
int32
Optional. Which version to use for evaluation.
PairwiseSummarizationQualityInput
Input for pairwise summarization quality metric.
Required. Spec for pairwise summarization quality score metric.
Required. Pairwise summarization quality instance.
PairwiseSummarizationQualityInstance
Spec for pairwise summarization quality instance.
prediction
string
Required. Output of the candidate model.
baseline_prediction
string
Required. Output of the baseline model.
reference
string
Optional. Ground truth used to compare against the prediction.
context
string
Required. Text to be summarized.
instruction
string
Required. Summarization prompt for LLM.
PairwiseSummarizationQualityResult
Spec for pairwise summarization quality result.
Output only. Pairwise summarization prediction choice.
explanation
string
Output only. Explanation for summarization quality score.
confidence
float
Output only. Confidence for summarization quality score.
PairwiseSummarizationQualitySpec
Spec for pairwise summarization quality score metric.
use_reference
bool
Optional. Whether to use instance.reference to compute pairwise summarization quality.
version
int32
Optional. Which version to use for evaluation.
Part
A datatype containing media that is part of a multi-part Content
message.
A Part
consists of data which has an associated datatype. A Part
can only contain one of the accepted types in Part.data
.
A Part
must have a fixed IANA MIME type identifying the type and subtype of the media if inline_data
or file_data
field is filled with raw bytes.
Union field data
.
data
can be only one of the following:
text
string
Optional. Text part (can be code).
Optional. Inlined bytes data.
Optional. URI based data.
Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
Optional. Code generated by the model that is meant to be executed.
Optional. Result of executing the [ExecutableCode].
Union field metadata
.
metadata
can be only one of the following:
Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
PartnerModelTuningSpec
Tuning spec for Partner models.
training_dataset_uri
string
Required. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file.
validation_dataset_uri
string
Optional. Cloud Storage path to file containing validation dataset for tuning. The dataset must be formatted as a JSONL file.
Hyperparameters for tuning. The accepted hyper_parameters and their valid range of values will differ depending on the base model.
PointwiseMetricInput
Input for pointwise metric.
Required. Spec for pointwise metric.
Required. Pointwise metric instance.
PointwiseMetricInstance
Pointwise metric instance. Usually one instance corresponds to one row in an evaluation dataset.
instance
. Instance for pointwise metric. instance
can be only one of the following:json_instance
string
Instance specified as a json string. String key-value pairs are expected in the json_instance to render PointwiseMetricSpec.instance_prompt_template.
PointwiseMetricResult
Spec for pointwise metric result.
explanation
string
Output only. Explanation for pointwise metric score.
score
float
Output only. Pointwise metric score.
PointwiseMetricSpec
Spec for pointwise metric.
metric_prompt_template
string
Required. Metric prompt template for pointwise metric.
PredictRequest
Request message for PredictionService.Predict
.
endpoint
string
Required. The name of the Endpoint requested to serve the prediction. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
Required. The instances that are the input to the prediction call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the prediction call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's
PredictSchemata's
instance_schema_uri
.
The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's
PredictSchemata's
parameters_schema_uri
.
PredictResponse
Response message for PredictionService.Predict
.
The predictions that are the output of the predictions call. The schema of any single prediction may be specified via Endpoint's DeployedModels' Model's
PredictSchemata's
prediction_schema_uri
.
deployed_model_id
string
ID of the Endpoint's DeployedModel that served this prediction.
model
string
Output only. The resource name of the Model which is deployed as the DeployedModel that this prediction hits.
model_version_id
string
Output only. The version ID of the Model which is deployed as the DeployedModel that this prediction hits.
model_display_name
string
Output only. The display name
of the Model which is deployed as the DeployedModel that this prediction hits.
Output only. Request-level metadata returned by the model. The metadata type will be dependent upon the model implementation.
QueryExtensionRequest
Request message for ExtensionExecutionService.QueryExtension
.
name
string
Required. Name (identifier) of the extension; Format: projects/{project}/locations/{location}/extensions/{extension}
Required. The content of the current conversation with the model.
For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request.
QueryExtensionResponse
Response message for ExtensionExecutionService.QueryExtension
.
Steps of extension or LLM interaction, can contain function call, function response, or text response. The last step contains the final response to the query.
failure_message
string
Failure message if any.
QueryReasoningEngineRequest
Request message for [ReasoningEngineExecutionService.Query][].
name
string
Required. The name of the ReasoningEngine resource to use. Format: projects/{project}/locations/{location}/reasoningEngines/{reasoning_engine}
Optional. Input content provided by users in JSON object format. Examples include text query, function calling parameters, media bytes, etc.
QueryReasoningEngineResponse
Response message for [ReasoningEngineExecutionService.Query][]
Response provided by users in JSON object format.
QuestionAnsweringCorrectnessInput
Input for question answering correctness metric.
Required. Spec for question answering correctness score metric.
Required. Question answering correctness instance.
QuestionAnsweringCorrectnessInstance
Spec for question answering correctness instance.
prediction
string
Required. Output of the evaluated model.
reference
string
Optional. Ground truth used to compare against the prediction.
context
string
Optional. Text provided as context to answer the question.
instruction
string
Required. The question asked and other instruction in the inference prompt.
QuestionAnsweringCorrectnessResult
Spec for question answering correctness result.
explanation
string
Output only. Explanation for question answering correctness score.
score
float
Output only. Question Answering Correctness score.
confidence
float
Output only. Confidence for question answering correctness score.
QuestionAnsweringCorrectnessSpec
Spec for question answering correctness metric.
use_reference
bool
Optional. Whether to use instance.reference to compute question answering correctness.
version
int32
Optional. Which version to use for evaluation.
QuestionAnsweringHelpfulnessInput
Input for question answering helpfulness metric.
Required. Spec for question answering helpfulness score metric.
Required. Question answering helpfulness instance.
QuestionAnsweringHelpfulnessInstance
Spec for question answering helpfulness instance.
prediction
string
Required. Output of the evaluated model.
reference
string
Optional. Ground truth used to compare against the prediction.
context
string
Optional. Text provided as context to answer the question.
instruction
string
Required. The question asked and other instruction in the inference prompt.
QuestionAnsweringHelpfulnessResult
Spec for question answering helpfulness result.
explanation
string
Output only. Explanation for question answering helpfulness score.
score
float
Output only. Question Answering Helpfulness score.
confidence
float
Output only. Confidence for question answering helpfulness score.
QuestionAnsweringHelpfulnessSpec
Spec for question answering helpfulness metric.
use_reference
bool
Optional. Whether to use instance.reference to compute question answering helpfulness.
version
int32
Optional. Which version to use for evaluation.
QuestionAnsweringQualityInput
Input for question answering quality metric.
Required. Spec for question answering quality score metric.
Required. Question answering quality instance.
QuestionAnsweringQualityInstance
Spec for question answering quality instance.
prediction
string
Required. Output of the evaluated model.
reference
string
Optional. Ground truth used to compare against the prediction.
context
string
Required. Text to answer the question.
instruction
string
Required. Question Answering prompt for LLM.
QuestionAnsweringQualityResult
Spec for question answering quality result.
explanation
string
Output only. Explanation for question answering quality score.
score
float
Output only. Question Answering Quality score.
confidence
float
Output only. Confidence for question answering quality score.
QuestionAnsweringQualitySpec
Spec for question answering quality score metric.
use_reference
bool
Optional. Whether to use instance.reference to compute question answering quality.
version
int32
Optional. Which version to use for evaluation.
QuestionAnsweringRelevanceInput
Input for question answering relevance metric.
Required. Spec for question answering relevance score metric.
Required. Question answering relevance instance.
QuestionAnsweringRelevanceInstance
Spec for question answering relevance instance.
prediction
string
Required. Output of the evaluated model.
reference
string
Optional. Ground truth used to compare against the prediction.
context
string
Optional. Text provided as context to answer the question.
instruction
string
Required. The question asked and other instruction in the inference prompt.
QuestionAnsweringRelevanceResult
Spec for question answering relevance result.
explanation
string
Output only. Explanation for question answering relevance score.
score
float
Output only. Question Answering Relevance score.
confidence
float
Output only. Confidence for question answering relevance score.
QuestionAnsweringRelevanceSpec
Spec for question answering relevance metric.
use_reference
bool
Optional. Whether to use instance.reference to compute question answering relevance.
version
int32
Optional. Which version to use for evaluation.
RagContexts
Relevant contexts for one query.
All its contexts.
Context
A context of the query.
source_uri
string
If the file is imported from Cloud Storage or Google Drive, source_uri will be original file URI in Cloud Storage or Google Drive; if file is uploaded, source_uri will be file display name.
text
string
The text chunk.
distance
double
The distance between the query dense embedding vector and the context text vector.
sparse_distance
double
The distance between the query sparse embedding vector and the context text vector.
RagCorpus
A RagCorpus is a RagFile container and a project can have multiple RagCorpora.
name
string
Output only. The resource name of the RagCorpus.
display_name
string
Required. The display name of the RagCorpus. The name can be up to 128 characters long and can consist of any UTF-8 characters.
description
string
Optional. The description of the RagCorpus.
Optional. Immutable. The embedding model config of the RagCorpus.
Optional. Immutable. The Vector DB config of the RagCorpus.
Output only. Timestamp when this RagCorpus was created.
Output only. Timestamp when this RagCorpus was last updated.
Output only. RagCorpus state.
RagEmbeddingModelConfig
Config for the embedding model to use for RAG.
model_config
. The model config to use. model_config
can be only one of the following:The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
Configuration for hybrid search.
HybridSearchConfig
Config for hybrid search.
Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus.
Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations.
SparseEmbeddingConfig
Configuration for sparse emebdding generation.
model
. The model to use for sparse embedding generation. model
can be only one of the following:Use BM25 scoring algorithm.
Bm25
Message for BM25 parameters.
multilingual
bool
Optional. Use multilingual tokenizer if set to true.
k1
float
Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2.
b
float
Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75.
VertexPredictionEndpoint
Config representing a model hosted on Vertex Prediction Endpoint.
endpoint
string
Required. The endpoint resource name. Format: projects/{project}/locations/{location}/publishers/{publisher}/models/{model}
or projects/{project}/locations/{location}/endpoints/{endpoint}
model
string
Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: projects/{project}/locations/{location}/models/{model}
model_version_id
string
Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
RagFile
A RagFile contains user data for chunking, embedding and indexing.
name
string
Output only. The resource name of the RagFile.
display_name
string
Required. The display name of the RagFile. The name can be up to 128 characters long and can consist of any UTF-8 characters.
description
string
Optional. The description of the RagFile.
size_bytes
int64
Output only. The size of the RagFile in bytes.
Output only. The type of the RagFile.
Output only. Timestamp when this RagFile was created.
Output only. Timestamp when this RagFile was last updated.
Output only. State of the RagFile.
rag_file_source
. The origin location of the RagFile if it is imported from Google Cloud Storage or Google Drive. rag_file_source
can be only one of the following:Output only. Google Cloud Storage location of the RagFile. It does not support wildcards in the Cloud Storage uri for now.
Output only. Google Drive location. Supports importing individual files as well as Google Drive folders.
Output only. The RagFile is encapsulated and uploaded in the UploadRagFile request.
The RagFile is imported from a Slack channel.
The RagFile is imported from a Jira query.
RagFileType
The type of the RagFile.
Enums | |
---|---|
RAG_FILE_TYPE_UNSPECIFIED |
RagFile type is unspecified. |
RAG_FILE_TYPE_TXT |
RagFile type is TXT. |
RAG_FILE_TYPE_PDF |
RagFile type is PDF. |
RagFileChunkingConfig
Specifies the size and overlap of chunks for RagFiles.
chunk_size
int32
The size of the chunks.
chunk_overlap
int32
The overlap between chunks.
RagFileParsingConfig
Specifies the parsing config for RagFiles.
use_advanced_pdf_parsing
bool
Whether to use advanced PDF parsing.
RagQuery
A query to retrieve relevant contexts.
similarity_top_k
int32
Optional. The number of contexts to retrieve.
Optional. Configurations for hybrid search results ranking.
query
. The query to retrieve contexts. Currently only text query is supported. query
can be only one of the following:text
string
Optional. The query in text format to get relevant contexts.
Ranking
Configurations for hybrid search results ranking.
alpha
float
Optional. Alpha value controls the weight between dense and sparse vector search results. The range is [0, 1], while 0 means sparse vector search only and 1 means dense vector search only. The default value is 0.5 which balances sparse and dense vector search equally.
RagVectorDbConfig
Config for the Vector DB to use for RAG.
Authentication config for the chosen Vector DB.
vector_db
. The config for the Vector DB. vector_db
can be only one of the following:The config for the RAG-managed Vector DB.
The config for the Weaviate.
The config for the Pinecone.
The config for the Vertex Feature Store.
The config for the Vertex Vector Search.
Pinecone
The config for the Pinecone.
index_name
string
Pinecone index name. This value cannot be changed after it's set.
RagManagedDb
This type has no fields.
The config for the default RAG-managed Vector DB.
VertexFeatureStore
The config for the Vertex Feature Store.
feature_view_resource_name
string
The resource name of the FeatureView. Format: projects/{project}/locations/{location}/featureOnlineStores/{feature_online_store}/featureViews/{feature_view}
VertexVectorSearch
The config for the Vertex Vector Search.
index_endpoint
string
The resource name of the Index Endpoint. Format: projects/{project}/locations/{location}/indexEndpoints/{index_endpoint}
index
string
The resource name of the Index. Format: projects/{project}/locations/{location}/indexes/{index}
Weaviate
The config for the Weaviate.
http_endpoint
string
Weaviate DB instance HTTP endpoint. e.g. 34.56.78.90:8080 Vertex RAG only supports HTTP connection to Weaviate. This value cannot be changed after it's set.
collection_name
string
The corresponding collection this corpus maps to. This value cannot be changed after it's set.
ReasoningEngine
ReasoningEngine provides a customizable runtime for models to determine which actions to take and in which order.
name
string
Identifier. The resource name of the ReasoningEngine.
display_name
string
Required. The display name of the ReasoningEngine.
description
string
Optional. The description of the ReasoningEngine.
Required. Configurations of the ReasoningEngine
Output only. Timestamp when this ReasoningEngine was created.
Output only. Timestamp when this ReasoningEngine was most recently updated.
etag
string
Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
ReasoningEngineSpec
ReasoningEngine configurations
Required. User provided package spec of the ReasoningEngine.
Optional. Declarations for object class methods.
PackageSpec
User provided package spec like pickled object and package requirements.
pickle_object_gcs_uri
string
Optional. The Cloud Storage URI of the pickled python object.
dependency_files_gcs_uri
string
Optional. The Cloud Storage URI of the dependency files in tar.gz format.
requirements_gcs_uri
string
Optional. The Cloud Storage URI of the requirements.txt
file
python_version
string
Optional. The Python version. Currently support 3.8, 3.9, 3.10, 3.11. If not specified, default value is 3.10.
RebaseTunedModelOperationMetadata
Runtime operation information for GenAiTuningService.RebaseTunedModel
.
The common part of the operation generic information.
RebaseTunedModelRequest
Request message for GenAiTuningService.RebaseTunedModel
.
parent
string
Required. The resource name of the Location into which to rebase the Model. Format: projects/{project}/locations/{location}
Required. TunedModel reference to retrieve the legacy model information.
Optional. The TuningJob to be updated. Users can use this TuningJob field to overwrite tuning configs.
Optional. The Google Cloud Storage location to write the artifacts.
deploy_to_same_endpoint
bool
Optional. By default, bison to gemini migration will always create new model/endpoint, but for gemini-1.0 to gemini-1.5 migration, we default deploy to the same endpoint. See details in this Section.
Retrieval
Defines a retrieval tool that model can call to access external knowledge.
disable_attribution
(deprecated)
bool
Optional. Deprecated. This option is no longer supported.
source
. The source of the retrieval. source
can be only one of the following:Set to use data source powered by Vertex AI Search.
Set to use data source powered by Vertex RAG store. User data is uploaded via the VertexRagDataService.
RetrievalMetadata
Metadata related to retrieval in the grounding flow.
google_search_dynamic_retrieval_score
float
Optional. Score indicating how likely information from Google Search could help answer the prompt. The score is in the range [0, 1]
, where 0 is the least likely and 1 is the most likely. This score is only populated when Google Search grounding and dynamic retrieval is enabled. It will be compared to the threshold to determine whether to trigger Google Search.
RetrieveContextsRequest
Request message for VertexRagService.RetrieveContexts
.
parent
string
Required. The resource name of the Location from which to retrieve RagContexts. The users must have permission to make a call in the project. Format: projects/{project}/locations/{location}
.
Required. Single RAG retrieve query.
data_source
. Data Source to retrieve contexts. data_source
can be only one of the following:The data source for Vertex RagStore.
VertexRagStore
The data source for Vertex RagStore.
rag_corpora[]
(deprecated)
string
Optional. Deprecated. Please use rag_resources to specify the data source.
Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support.
vector_distance_threshold
double
Optional. Only return contexts with vector distance smaller than the threshold.
RagResource
The definition of the Rag resource.
rag_corpus
string
Optional. RagCorpora resource name. Format: projects/{project}/locations/{location}/ragCorpora/{rag_corpus}
rag_file_ids[]
string
Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field.
RetrieveContextsResponse
Response message for VertexRagService.RetrieveContexts
.
The contexts of the query.
RougeInput
Input for rouge metric.
Required. Spec for rouge score metric.
Required. Repeated rouge instances.
RougeInstance
Spec for rouge instance.
prediction
string
Required. Output of the evaluated model.
reference
string
Required. Ground truth used to compare against the prediction.
RougeMetricValue
Rouge metric value for an instance.
score
float
Output only. Rouge score.
RougeResults
Results for rouge metric.
Output only. Rouge metric values.
RougeSpec
Spec for rouge score metric - calculates the recall of n-grams in prediction as compared to reference - returns a score ranging between 0 and 1.
rouge_type
string
Optional. Supported rouge types are rougen[1-9], rougeL, and rougeLsum.
use_stemmer
bool
Optional. Whether to use stemmer to compute rouge score.
split_summaries
bool
Optional. Whether to split summaries while using rougeLsum.
RuntimeConfig
Runtime configuration to run the extension.
Optional. Default parameters that will be set for all the execution of this extension. If specified, the parameter values can be overridden by values in [[ExecuteExtensionRequest.operation_params]] at request time.
The struct should be in a form of map with param name as the key and actual param value as the value. E.g. If this operation requires a param "name" to be set to "abc". you can set this to something like {"name": "abc"}.
GoogleFirstPartyExtensionConfig
. Runtime configurations for Google first party extensions. GoogleFirstPartyExtensionConfig
can be only one of the following:Code execution runtime configurations for code interpreter extension.
Runtime configuration for Vertex AI Search extension.
CodeInterpreterRuntimeConfig
file_input_gcs_bucket
string
Optional. The Cloud Storage bucket for file input of this Extension. If specified, support input from the Cloud Storage bucket. Vertex Extension Custom Code Service Agent should be granted file reader to this bucket. If not specified, the extension will only accept file contents from request body and reject Cloud Storage file inputs.
file_output_gcs_bucket
string
Optional. The Cloud Storage bucket for file output of this Extension. If specified, write all output files to the Cloud Storage bucket. Vertex Extension Custom Code Service Agent should be granted file writer to this bucket. If not specified, the file content will be output in response body.
VertexAISearchRuntimeConfig
serving_config_name
string
Optional. Vertex AI Search serving config name. Format: projects/{project}/locations/{location}/collections/{collection}/engines/{engine}/servingConfigs/{serving_config}
engine_id
string
Optional. Vertex AI Search engine ID. This is used to construct the search request. By setting this engine_id, API will construct the serving config using the default value to call search API for the user. The engine_id and serving_config_name cannot both be empty at the same time.
SafetyInput
Input for safety metric.
Required. Spec for safety metric.
Required. Safety instance.
SafetyInstance
Spec for safety instance.
prediction
string
Required. Output of the evaluated model.
SafetyRating
Safety rating corresponding to the generated content.
Output only. Harm category.
Output only. Harm probability levels in the content.
probability_score
float
Output only. Harm probability score.
Output only. Harm severity levels in the content.
severity_score
float
Output only. Harm severity score.
blocked
bool
Output only. Indicates whether the content was filtered out because of this rating.
HarmProbability
Harm probability levels in the content.
Enums | |
---|---|
HARM_PROBABILITY_UNSPECIFIED |
Harm probability unspecified. |
NEGLIGIBLE |
Negligible level of harm. |
LOW |
Low level of harm. |
MEDIUM |
Medium level of harm. |
HIGH |
High level of harm. |
HarmSeverity
Harm severity levels.
Enums | |
---|---|
HARM_SEVERITY_UNSPECIFIED |
Harm severity unspecified. |
HARM_SEVERITY_NEGLIGIBLE |
Negligible level of harm severity. |
HARM_SEVERITY_LOW |
Low level of harm severity. |
HARM_SEVERITY_MEDIUM |
Medium level of harm severity. |
HARM_SEVERITY_HIGH |
High level of harm severity. |
SafetyResult
Spec for safety result.
explanation
string
Output only. Explanation for safety score.
score
float
Output only. Safety score.
confidence
float
Output only. Confidence for safety score.
SafetySetting
Safety settings.
Required. Harm category.
Required. The harm block threshold.
Optional. Specify if the threshold is used for probability or severity score. If not specified, the threshold is used for probability score.
HarmBlockMethod
Probability vs severity.
Enums | |
---|---|
HARM_BLOCK_METHOD_UNSPECIFIED |
The harm block method is unspecified. |
SEVERITY |
The harm block method uses both probability and severity scores. |
PROBABILITY |
The harm block method uses the probability score. |
HarmBlockThreshold
Probability based thresholds levels for blocking.
Enums | |
---|---|
HARM_BLOCK_THRESHOLD_UNSPECIFIED |
Unspecified harm block threshold. |
BLOCK_LOW_AND_ABOVE |
Block low threshold and above (i.e. block more). |
BLOCK_MEDIUM_AND_ABOVE |
Block medium threshold and above. |
BLOCK_ONLY_HIGH |
Block only high threshold (i.e. block less). |
BLOCK_NONE |
Block none. |
OFF |
Turn off the safety filter. |
SafetySpec
Spec for safety metric.
version
int32
Optional. Which version to use for evaluation.
Schema
Schema is used to define the format of input/output data. Represents a select subset of an OpenAPI 3.0 schema object. More fields may be added in the future as needed.
Optional. The type of the data.
format
string
Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc
title
string
Optional. The title of the Schema.
description
string
Optional. The description of the data.
nullable
bool
Optional. Indicates if the value may be null.
Optional. Default value of the data.
Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
min_items
int64
Optional. Minimum number of the elements for Type.ARRAY.
max_items
int64
Optional. Maximum number of the elements for Type.ARRAY.
enum[]
string
Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:["101", "201", "301"]}
Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
property_ordering[]
string
Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
required[]
string
Optional. Required properties of Type.OBJECT.
min_properties
int64
Optional. Minimum number of the properties for Type.OBJECT.
max_properties
int64
Optional. Maximum number of the properties for Type.OBJECT.
minimum
double
Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
maximum
double
Optional. Maximum value of the Type.INTEGER and Type.NUMBER
min_length
int64
Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
max_length
int64
Optional. Maximum length of the Type.STRING
pattern
string
Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
Optional. Example of the object. Will only populated when the object is the root.
Optional. The value should be validated against any (one or more) of the subschemas in the list.
SearchEntryPoint
Google search entry point.
rendered_content
string
Optional. Web content snippet that can be embedded in a web page or an app webview.
sdk_blob
bytes
Optional. Base64 encoded JSON representing array of <search term, search url> tuple.
Segment
Segment of the content.
part_index
int32
Output only. The index of a Part object within its parent Content object.
start_index
int32
Output only. Start index in the given Part, measured in bytes. Offset from the start of the Part, inclusive, starting at zero.
end_index
int32
Output only. End index in the given Part, measured in bytes. Offset from the start of the Part, exclusive, starting at zero.
text
string
Output only. The text corresponding to the segment from the response.
SlackSource
The Slack source for the ImportRagFilesRequest.
Required. The Slack channels.
SlackChannels
SlackChannels contains the Slack channels and corresponding access token.
Required. The Slack channel IDs.
Required. The SecretManager secret version resource name (e.g. projects/{project}/secrets/{secret}/versions/{version}) storing the Slack channel access token that has access to the slack channel IDs. See: https://api.slack.com/tutorials/tracks/getting-a-token.
SlackChannel
StreamDirectPredictRequest
Request message for PredictionService.StreamDirectPredict
.
The first message must contain endpoint
field and optionally [input][]. The subsequent messages must contain [input][].
endpoint
string
Required. The name of the Endpoint requested to serve the prediction. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
Optional. The prediction input.
Optional. The parameters that govern the prediction.
StreamDirectPredictResponse
Response message for PredictionService.StreamDirectPredict
.
The prediction output.
The parameters that govern the prediction.
StreamDirectRawPredictRequest
Request message for PredictionService.StreamDirectRawPredict
.
The first message must contain endpoint
and method_name
fields and optionally input
. The subsequent messages must contain input
. method_name
in the subsequent messages have no effect.
endpoint
string
Required. The name of the Endpoint requested to serve the prediction. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
method_name
string
Optional. Fully qualified name of the API method being invoked to perform predictions.
Format: /namespace.Service/Method/
Example: /tensorflow.serving.PredictionService/Predict
input
bytes
Optional. The prediction input.
StreamDirectRawPredictResponse
Response message for PredictionService.StreamDirectRawPredict
.
output
bytes
The prediction output.
StreamingPredictRequest
Request message for PredictionService.StreamingPredict
.
The first message must contain endpoint
field and optionally [input][]. The subsequent messages must contain [input][].
endpoint
string
Required. The name of the Endpoint requested to serve the prediction. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
The prediction input.
The parameters that govern the prediction.
StreamingPredictResponse
Response message for PredictionService.StreamingPredict
.
The prediction output.
The parameters that govern the prediction.
StreamingRawPredictRequest
Request message for PredictionService.StreamingRawPredict
.
The first message must contain endpoint
and method_name
fields and optionally input
. The subsequent messages must contain input
. method_name
in the subsequent messages have no effect.
endpoint
string
Required. The name of the Endpoint requested to serve the prediction. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
method_name
string
Fully qualified name of the API method being invoked to perform predictions.
Format: /namespace.Service/Method/
Example: /tensorflow.serving.PredictionService/Predict
input
bytes
The prediction input.
StreamingRawPredictResponse
Response message for PredictionService.StreamingRawPredict
.
output
bytes
The prediction output.
SummarizationHelpfulnessInput
Input for summarization helpfulness metric.
Required. Spec for summarization helpfulness score metric.
Required. Summarization helpfulness instance.
SummarizationHelpfulnessInstance
Spec for summarization helpfulness instance.
prediction
string
Required. Output of the evaluated model.
reference
string
Optional. Ground truth used to compare against the prediction.
context
string
Required. Text to be summarized.
instruction
string
Optional. Summarization prompt for LLM.
SummarizationHelpfulnessResult
Spec for summarization helpfulness result.
explanation
string
Output only. Explanation for summarization helpfulness score.
score
float
Output only. Summarization Helpfulness score.
confidence
float
Output only. Confidence for summarization helpfulness score.
SummarizationHelpfulnessSpec
Spec for summarization helpfulness score metric.
use_reference
bool
Optional. Whether to use instance.reference to compute summarization helpfulness.
version
int32
Optional. Which version to use for evaluation.
SummarizationQualityInput
Input for summarization quality metric.
Required. Spec for summarization quality score metric.
Required. Summarization quality instance.
SummarizationQualityInstance
Spec for summarization quality instance.
prediction
string
Required. Output of the evaluated model.
reference
string
Optional. Ground truth used to compare against the prediction.
context
string
Required. Text to be summarized.
instruction
string
Required. Summarization prompt for LLM.
SummarizationQualityResult
Spec for summarization quality result.
explanation
string
Output only. Explanation for summarization quality score.
score
float
Output only. Summarization Quality score.
confidence
float
Output only. Confidence for summarization quality score.
SummarizationQualitySpec
Spec for summarization quality score metric.
use_reference
bool
Optional. Whether to use instance.reference to compute summarization quality.
version
int32
Optional. Which version to use for evaluation.
SummarizationVerbosityInput
Input for summarization verbosity metric.
Required. Spec for summarization verbosity score metric.
Required. Summarization verbosity instance.
SummarizationVerbosityInstance
Spec for summarization verbosity instance.
prediction
string
Required. Output of the evaluated model.
reference
string
Optional. Ground truth used to compare against the prediction.
context
string
Required. Text to be summarized.
instruction
string
Optional. Summarization prompt for LLM.
SummarizationVerbosityResult
Spec for summarization verbosity result.
explanation
string
Output only. Explanation for summarization verbosity score.
score
float
Output only. Summarization Verbosity score.
confidence
float
Output only. Confidence for summarization verbosity score.
SummarizationVerbositySpec
Spec for summarization verbosity score metric.
use_reference
bool
Optional. Whether to use instance.reference to compute summarization verbosity.
version
int32
Optional. Which version to use for evaluation.
SupervisedHyperParameters
Hyperparameters for SFT.
epoch_count
int64
Optional. Number of complete passes the model makes over the entire training dataset during training.
learning_rate_multiplier
double
Optional. Multiplier for adjusting the default learning rate.
Optional. Adapter size for tuning.
AdapterSize
Supported adapter sizes for tuning.
Enums | |
---|---|
ADAPTER_SIZE_UNSPECIFIED |
Adapter size is unspecified. |
ADAPTER_SIZE_ONE |
Adapter size 1. |
ADAPTER_SIZE_FOUR |
Adapter size 4. |
ADAPTER_SIZE_EIGHT |
Adapter size 8. |
ADAPTER_SIZE_SIXTEEN |
Adapter size 16. |
ADAPTER_SIZE_THIRTY_TWO |
Adapter size 32. |
SupervisedTuningDataStats
Tuning data statistics for Supervised Tuning.
tuning_dataset_example_count
int64
Output only. Number of examples in the tuning dataset.
total_tuning_character_count
int64
Output only. Number of tuning characters in the tuning dataset.
total_billable_character_count
(deprecated)
int64
Output only. Number of billable characters in the tuning dataset.
total_billable_token_count
int64
Output only. Number of billable tokens in the tuning dataset.
tuning_step_count
int64
Output only. Number of tuning steps for this Tuning Job.
Output only. Dataset distributions for the user input tokens.
Output only. Dataset distributions for the user output tokens.
Output only. Dataset distributions for the messages per example.
Output only. Sample user messages in the training dataset uri.
total_truncated_example_count
int64
The number of examples in the dataset that have been truncated by any amount.
truncated_example_indices[]
int64
A partial sample of the indices (starting from 1) of the truncated examples.
SupervisedTuningDatasetDistribution
Dataset distribution for Supervised Tuning.
sum
int64
Output only. Sum of a given population of values.
billable_sum
int64
Output only. Sum of a given population of values that are billable.
min
double
Output only. The minimum of the population values.
max
double
Output only. The maximum of the population values.
mean
double
Output only. The arithmetic mean of the values in the population.
median
double
Output only. The median of the values in the population.
p5
double
Output only. The 5th percentile of the values in the population.
p95
double
Output only. The 95th percentile of the values in the population.
Output only. Defines the histogram bucket.
DatasetBucket
Dataset bucket used to create a histogram for the distribution given a population of values.
count
double
Output only. Number of values in the bucket.
left
double
Output only. Left bound of the bucket.
right
double
Output only. Right bound of the bucket.
SupervisedTuningSpec
Tuning Spec for Supervised Tuning for first party models.
training_dataset_uri
string
Required. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file.
validation_dataset_uri
string
Optional. Cloud Storage path to file containing validation dataset for tuning. The dataset must be formatted as a JSONL file.
Optional. Hyperparameters for SFT.
Tensor
A tensor value type.
The data type of tensor.
shape[]
int64
Shape of the tensor.
bool_val[]
bool
Type specific representations that make it easy to create tensor protos in all languages. Only the representation corresponding to "dtype" can be set. The values hold the flattened representation of the tensor in row major order.
[BOOL][google.aiplatform.master.Tensor.DataType.BOOL]
string_val[]
string
[STRING][google.aiplatform.master.Tensor.DataType.STRING]
bytes_val[]
bytes
[STRING][google.aiplatform.master.Tensor.DataType.STRING]
float_val[]
float
[FLOAT][google.aiplatform.master.Tensor.DataType.FLOAT]
double_val[]
double
[DOUBLE][google.aiplatform.master.Tensor.DataType.DOUBLE]
int_val[]
int32
[INT_8][google.aiplatform.master.Tensor.DataType.INT8] [INT_16][google.aiplatform.master.Tensor.DataType.INT16] [INT_32][google.aiplatform.master.Tensor.DataType.INT32]
int64_val[]
int64
[INT64][google.aiplatform.master.Tensor.DataType.INT64]
uint_val[]
uint32
[UINT8][google.aiplatform.master.Tensor.DataType.UINT8] [UINT16][google.aiplatform.master.Tensor.DataType.UINT16] [UINT32][google.aiplatform.master.Tensor.DataType.UINT32]
uint64_val[]
uint64
[UINT64][google.aiplatform.master.Tensor.DataType.UINT64]
A list of tensor values.
A map of string to tensor.
tensor_val
bytes
Serialized raw tensor content.
DataType
Data type of the tensor.
Enums | |
---|---|
DATA_TYPE_UNSPECIFIED |
Not a legal value for DataType. Used to indicate a DataType field has not been set. |
BOOL |
Data types that all computation devices are expected to be capable to support. |
STRING |
|
FLOAT |
|
DOUBLE |
|
INT8 |
|
INT16 |
|
INT32 |
|
INT64 |
|
UINT8 |
|
UINT16 |
|
UINT32 |
|
UINT64 |
Tool
Tool details that the model may use to generate response.
A Tool
is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).
Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating [FunctionCall][content.part.function_call] in the response. User should provide a [FunctionResponse][content.part.function_response] for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 128 function declarations can be provided.
Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation.
Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search.
Optional. CodeExecution tool type. Enables the model to execute code as part of generation. This field is only used by the Gemini Developer API services.
CodeExecution
This type has no fields.
Tool that executes code generated by the model, and automatically returns the result to the model.
See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool.
ToolCallValidInput
Input for tool call valid metric.
Required. Spec for tool call valid metric.
Required. Repeated tool call valid instances.
ToolCallValidInstance
Spec for tool call valid instance.
prediction
string
Required. Output of the evaluated model.
reference
string
Required. Ground truth used to compare against the prediction.
ToolCallValidMetricValue
Tool call valid metric value for an instance.
score
float
Output only. Tool call valid score.
ToolCallValidResults
Results for tool call valid metric.
Output only. Tool call valid metric values.
ToolCallValidSpec
This type has no fields.
Spec for tool call valid metric.
ToolConfig
Tool config. This config is shared for all tools provided in the request.
Optional. Function calling config.
ToolNameMatchInput
Input for tool name match metric.
Required. Spec for tool name match metric.
Required. Repeated tool name match instances.
ToolNameMatchInstance
Spec for tool name match instance.
prediction
string
Required. Output of the evaluated model.
reference
string
Required. Ground truth used to compare against the prediction.
ToolNameMatchMetricValue
Tool name match metric value for an instance.
score
float
Output only. Tool name match score.
ToolNameMatchResults
Results for tool name match metric.
Output only. Tool name match metric values.
ToolNameMatchSpec
This type has no fields.
Spec for tool name match metric.
ToolParameterKVMatchInput
Input for tool parameter key value match metric.
Required. Spec for tool parameter key value match metric.
Required. Repeated tool parameter key value match instances.
ToolParameterKVMatchInstance
Spec for tool parameter key value match instance.
prediction
string
Required. Output of the evaluated model.
reference
string
Required. Ground truth used to compare against the prediction.
ToolParameterKVMatchMetricValue
Tool parameter key value match metric value for an instance.
score
float
Output only. Tool parameter key value match score.
ToolParameterKVMatchResults
Results for tool parameter key value match metric.
Output only. Tool parameter key value match metric values.
ToolParameterKVMatchSpec
Spec for tool parameter key value match metric.
use_strict_string_match
bool
Optional. Whether to use STRICT string match on parameter values.
ToolParameterKeyMatchInput
Input for tool parameter key match metric.
Required. Spec for tool parameter key match metric.
Required. Repeated tool parameter key match instances.
ToolParameterKeyMatchInstance
Spec for tool parameter key match instance.
prediction
string
Required. Output of the evaluated model.
reference
string
Required. Ground truth used to compare against the prediction.
ToolParameterKeyMatchMetricValue
Tool parameter key match metric value for an instance.
score
float
Output only. Tool parameter key match score.
ToolParameterKeyMatchResults
Results for tool parameter key match metric.
Output only. Tool parameter key match metric values.
ToolParameterKeyMatchSpec
This type has no fields.
Spec for tool parameter key match metric.
ToolUseExample
A single example of the tool usage.
display_name
string
Required. The display name for example.
query
string
Required. Query that should be routed to this tool.
Request parameters used for executing this tool.
Response parameters generated by this tool.
response_summary
string
Summary of the tool response to the user query.
Target
. Target tool to use. Target
can be only one of the following:Extension operation to call.
function_name
string
Function name to call.
ExtensionOperation
Identifies one operation of the extension.
extension
string
Resource name of the extension.
operation_id
string
Required. Operation ID of the extension.
TunedModel
The Model Registry Model and Online Prediction Endpoint assiociated with this TuningJob
.
model
string
Output only. The resource name of the TunedModel. Format: projects/{project}/locations/{location}/models/{model}
.
endpoint
string
Output only. A resource name of an Endpoint. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
.
TunedModelRef
TunedModel Reference for legacy model migration.
tuned_model_ref
. The Tuned Model Reference for the model. tuned_model_ref
can be only one of the following:tuned_model
string
Support migration from model registry.
tuning_job
string
Support migration from tuning job list page, from gemini-1.0-pro-002 to 1.5 and above.
pipeline_job
string
Support migration from tuning job list page, from bison model to gemini model.
TuningDataStats
The tuning data statistic values for TuningJob
.
Union field tuning_data_stats
.
tuning_data_stats
can be only one of the following:
The SFT Tuning data stats.
Output only. Statistics for distillation.
TuningJob
Represents a TuningJob that runs with Google owned models.
name
string
Output only. Identifier. Resource name of a TuningJob. Format: projects/{project}/locations/{location}/tuningJobs/{tuning_job}
tuned_model_display_name
string
Optional. The display name of the TunedModel
. The name can be up to 128 characters long and can consist of any UTF-8 characters.
description
string
Optional. The description of the TuningJob
.
Output only. The detailed state of the job.
Output only. Only populated when job's state is JOB_STATE_FAILED
or JOB_STATE_CANCELLED
.
labels
map<string, string>
Optional. The labels with user-defined metadata to organize TuningJob
and generated resources such as Model
and Endpoint
.
Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed.
See https://goo.gl/xmQnxf for more information and examples of labels.
experiment
string
Output only. The Experiment associated with this TuningJob
.
Output only. The tuned model resources assiociated with this TuningJob
.
Output only. The tuning data statistics associated with this TuningJob
.
pipeline_job
string
Output only. The resource name of the PipelineJob associated with the TuningJob
. Format: projects/{project}/locations/{location}/pipelineJobs/{pipeline_job}
.
Customer-managed encryption key options for a TuningJob. If this is set, then all resources created by the TuningJob will be encrypted with the provided encryption key.
Union field source_model
.
source_model
can be only one of the following:
base_model
string
The base model that is being tuned, e.g., "gemini-1.0-pro-002".
Union field tuning_spec
.
tuning_spec
can be only one of the following:
Tuning Spec for Supervised Fine Tuning.
Tuning Spec for Distillation.
Tuning Spec for open sourced and third party Partner models.
Type
Type contains the list of OpenAPI data types as defined by https://swagger.io/docs/specification/data-models/data-types/
Enums | |
---|---|
TYPE_UNSPECIFIED |
Not specified, should not be used. |
STRING |
OpenAPI string type |
NUMBER |
OpenAPI number type |
INTEGER |
OpenAPI integer type |
BOOLEAN |
OpenAPI boolean type |
ARRAY |
OpenAPI array type |
OBJECT |
OpenAPI object type |
UpdateCacheConfigRequest
Request message for updating a cache config.
Required. The cache config to be updated. cache_config.name
is used to identify the cache config. Format: - projects/{project}/cacheConfig
.
UpdateCachedContentRequest
Request message for GenAiCacheService.UpdateCachedContent
. Only expire_time or ttl can be updated.
Required. The cached content to update
Required. The list of fields to update.
UpdateExtensionRequest
Request message for ExtensionRegistryService.UpdateExtension
.
Required. The Extension which replaces the resource on the server.
Required. Mask specifying which fields to update. Supported fields:
display_name
description
runtime_config
tool_use_examples
manifest.description
UpdateRagCorpusOperationMetadata
Runtime operation information for VertexRagDataService.UpdateRagCorpus
.
The operation generic information.
UpdateRagCorpusRequest
Request message for VertexRagDataService.UpdateRagCorpus
.
Required. The RagCorpus which replaces the resource on the server.
UpdateReasoningEngineOperationMetadata
Details of ReasoningEngineService.UpdateReasoningEngine
operation.
The common part of the operation metadata.
UpdateReasoningEngineRequest
Request message for ReasoningEngineService.UpdateReasoningEngine
.
Required. The ReasoningEngine which replaces the resource on the server.
Optional. Mask specifying which fields to update.
UploadRagFileConfig
Config for uploading RagFile.
Specifies the size and overlap of chunks after uploading RagFile.
VertexAISearch
Retrieve from Vertex AI Search datastore for grounding. See https://cloud.google.com/products/agent-builder
datastore
string
Required. Fully-qualified Vertex AI Search data store resource ID. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}
VertexRagStore
Retrieve from Vertex RAG Store for grounding.
rag_corpora[]
(deprecated)
string
Optional. Deprecated. Please use rag_resources instead.
Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support.
similarity_top_k
int32
Optional. Number of top k results to return from the selected corpora.
vector_distance_threshold
double
Optional. Only return results with vector distance smaller than the threshold.
RagResource
The definition of the Rag resource.
rag_corpus
string
Optional. RagCorpora resource name. Format: projects/{project}/locations/{location}/ragCorpora/{rag_corpus}
rag_file_ids[]
string
Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field.