Index
EvaluationService(interface)GenAiTuningService(interface)PredictionService(interface)BleuInput(message)BleuInstance(message)BleuMetricValue(message)BleuResults(message)BleuSpec(message)Blob(message)CancelTuningJobRequest(message)Candidate(message)Candidate.FinishReason(enum)ChatCompletionsRequest(message)Citation(message)CitationMetadata(message)CoherenceInput(message)CoherenceInstance(message)CoherenceResult(message)CoherenceSpec(message)Content(message)CreateTuningJobRequest(message)DynamicRetrievalConfig(message)DynamicRetrievalConfig.Mode(enum)EncryptionSpec(message)EvaluateInstancesRequest(message)EvaluateInstancesResponse(message)ExactMatchInput(message)ExactMatchInstance(message)ExactMatchMetricValue(message)ExactMatchResults(message)ExactMatchSpec(message)FileData(message)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)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)GetTuningJobRequest(message)GoogleSearchRetrieval(message)GroundednessInput(message)GroundednessInstance(message)GroundednessResult(message)GroundednessSpec(message)GroundingChunk(message)GroundingChunk.RetrievedContext(message)GroundingChunk.Web(message)GroundingMetadata(message)GroundingSupport(message)HarmCategory(enum)JobState(enum)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)PointwiseMetricInput(message)PointwiseMetricInstance(message)PointwiseMetricResult(message)PointwiseMetricSpec(message)PredictRequest(message)PredictResponse(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)RebaseTunedModelOperationMetadata(message)RebaseTunedModelRequest(message)Retrieval(message)RetrievalMetadata(message)RougeInput(message)RougeInstance(message)RougeMetricValue(message)RougeResults(message)RougeSpec(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)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)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)TunedModel(message)TunedModelRef(message)TuningDataStats(message)TuningJob(message)Type(enum)VertexAISearch(message)VertexRagStore(message)VertexRagStore.RagResource(message)VideoMetadata(message)
EvaluationService
Vertex AI Online Evaluation Service.
| EvaluateInstances |
|---|
|
Evaluates instances based on a given metric. |
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.
|
| 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.
|
BleuInput
Input for bleu metric.
Required. Spec for bleu score metric.
Required. Repeated bleu instances.
BleuInstance
Spec for bleu instance.
predictionstring
Required. Output of the evaluated model.
referencestring
Required. Ground truth used to compare against the prediction.
BleuMetricValue
Bleu metric value for an instance.
scorefloat
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_orderbool
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_typestring
Required. The IANA standard MIME type of the source data.
databytes
Required. Raw bytes.
CancelTuningJobRequest
Request message for GenAiTuningService.CancelTuningJob.
namestring
Required. The name of the TuningJob to cancel. Format: projects/{project}/locations/{location}/tuningJobs/{tuning_job}
Candidate
A response candidate generated from the model.
indexint32
Output only. Index of the candidate.
Output only. Content parts of the candidate.
avg_logprobsdouble
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_messagestring
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]
endpointstring
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_indexint32
Output only. Start index into the content.
end_indexint32
Output only. End index into the content.
uristring
Output only. Url reference of the attribution.
titlestring
Output only. Title of the attribution.
licensestring
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.
CoherenceInput
Input for coherence metric.
Required. Spec for coherence score metric.
Required. Coherence instance.
CoherenceInstance
Spec for coherence instance.
predictionstring
Required. Output of the evaluated model.
CoherenceResult
Spec for coherence result.
explanationstring
Output only. Explanation for coherence score.
scorefloat
Output only. Coherence score.
confidencefloat
Output only. Confidence for coherence score.
CoherenceSpec
Spec for coherence score metric.
versionint32
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.
rolestring
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.
CreateTuningJobRequest
Request message for GenAiTuningService.CreateTuningJob.
parentstring
Required. The resource name of the Location to create the TuningJob in. Format: projects/{project}/locations/{location}
Required. The TuningJob to create.
DynamicRetrievalConfig
Describes the options to customize dynamic retrieval.
The mode of the predictor to be used in dynamic retrieval.
dynamic_thresholdfloat
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_namestring
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.
locationstring
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.
predictionstring
Required. Output of the evaluated model.
referencestring
Required. Ground truth used to compare against the prediction.
ExactMatchMetricValue
Exact match metric value for an instance.
scorefloat
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.
FileData
URI based data.
mime_typestring
Required. The IANA standard MIME type of the source data.
file_uristring
Required. URI.
FluencyInput
Input for fluency metric.
Required. Spec for fluency score metric.
Required. Fluency instance.
FluencyInstance
Spec for fluency instance.
predictionstring
Required. Output of the evaluated model.
FluencyResult
Spec for fluency result.
explanationstring
Output only. Explanation for fluency score.
scorefloat
Output only. Fluency score.
confidencefloat
Output only. Confidence for fluency score.
FluencySpec
Spec for fluency score metric.
versionint32
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.
predictionstring
Required. Output of the evaluated model.
instructionstring
Required. Inference instruction prompt to compare prediction with.
FulfillmentResult
Spec for fulfillment result.
explanationstring
Output only. Explanation for fulfillment score.
scorefloat
Output only. Fulfillment score.
confidencefloat
Output only. Confidence for fulfillment score.
FulfillmentSpec
Spec for fulfillment metric.
versionint32
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.
namestring
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.
namestring
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.
descriptionstring
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.
namestring
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_prefixstring
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.
GenerateContentRequest
Request message for [PredictionService.GenerateContent].
modelstring
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.
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.
labelsmap<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_versionstring
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_messagestring
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_countint32
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_countint32
Number of tokens in the response(s).
total_token_countint32
Total token count for prompt and response candidates.
GenerationConfig
Generation config.
stop_sequences[]string
Optional. Stop sequences.
response_mime_typestring
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.
temperaturefloat
Optional. Controls the randomness of predictions.
top_pfloat
Optional. If specified, nucleus sampling will be used.
top_kfloat
Optional. If specified, top-k sampling will be used.
candidate_countint32
Optional. Number of candidates to generate.
max_output_tokensint32
Optional. The maximum number of output tokens to generate per message.
response_logprobsbool
Optional. If true, export the logprobs results in response.
logprobsint32