| GitHub Repository |
Client Classes
Client classes are the main entry point to using a package. They contain several variations of Java methods for each of the API's methods.
| Client | Description |
|---|---|
| com. |
Service Description: A service for managing Vertex AI's Endpoints.
This class provides the ability to make remote calls to the backing service through method calls that map to API methods. Sample code to get started: |
| com. |
Service Description: Service for LLM related utility functions.
This class provides the ability to make remote calls to the backing service through method calls that map to API methods. Sample code to get started: |
| com. |
Service Description: A service for online predictions and explanations.
This class provides the ability to make remote calls to the backing service through method calls that map to API methods. Sample code to get started: |
Settings Classes
Settings classes can be used to configure credentials, endpoints, and retry settings for a Client.
| Settings | Description |
|---|---|
| com. |
Settings class to configure an instance of EndpointServiceClient.
The default instance has everything set to sensible defaults: |
| com. |
Settings class to configure an instance of LlmUtilityServiceClient.
The default instance has everything set to sensible defaults: |
| com. |
Settings class to configure an instance of PredictionServiceClient.
The default instance has everything set to sensible defaults: |
Classes
| Class | Description |
|---|---|
| com. |
|
| com. |
The generic reusable api auth config. |
| com. |
The API secret. |
| com. |
The API secret. |
| com. |
The generic reusable api auth config. |
| com. |
|
| com. |
Attribution that explains a particular prediction output. |
| com. |
Attribution that explains a particular prediction output. |
| com. |
A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines. |
| com. |
A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines. |
| com. |
The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count. |
| com. |
The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count. |
| com. |
The storage details for Avro input content. |
| com. |
The storage details for Avro input content. |
| com. |
A description of resources that are used for performing batch operations, are dedicated to a Model, and need manual configuration. |
| com. |
A description of resources that are used for performing batch operations, are dedicated to a Model, and need manual configuration. |
| com. |
The BigQuery location for the output content. |
| com. |
The BigQuery location for the output content. |
| com. |
The BigQuery location for the input content. |
| com. |
The BigQuery location for the input content. |
| com. |
Content blob. It's preferred to send as text |
| com. |
Content blob. It's preferred to send as text |
| com. |
Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input |
| com. |
Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input |
| com. |
A list of boolean values. |
| com. |
A list of boolean values. |
| com. |
A resource used in LLM queries for users to explicitly specify what to cache and how to cache. |
| com. |
A resource used in LLM queries for users to explicitly specify what to cache and how to cache. |
| com. |
Metadata on the usage of the cached content. |
| com. |
Metadata on the usage of the cached content. |
| com. |
|
| com. |
Builder for projects/{project}/locations/{location}/cachedContents/{cached_content}. |
| com. |
|
| com. |
A response candidate generated from the model. |
| com. |
A response candidate generated from the model. |
| com. |
Source attributions for content. |
| com. |
Source attributions for content. |
| com. |
A collection of source attributions for a piece of content. |
| com. |
A collection of source attributions for a piece of content. |
| com. |
Configurations (e.g. inference timeout) that are applied on your endpoints. |
| com. |
Configurations (e.g. inference timeout) that are applied on your endpoints. |
| com. |
Result of executing the [ExecutableCode].
Always follows a part containing the [ExecutableCode]. |
| com. |
Result of executing the [ExecutableCode].
Always follows a part containing the [ExecutableCode]. |
| com. |
Request message for ComputeTokens RPC call. |
| com. |
Request message for ComputeTokens RPC call. |
| com. |
Response message for ComputeTokens RPC call. |
| com. |
Response message for ComputeTokens RPC call. |
| com. |
The Container Registry location for the container image. |
| com. |
The Container Registry location for the container image. |
| com. |
The base structured datatype containing multi-part content of a message.
A Content includes a role field designating the producer of the Content |
| com. |
The base structured datatype containing multi-part content of a message.
A Content includes a role field designating the producer of the Content |
| com. |
|
| com. |
RagCorpus status. |
| com. |
RagCorpus status. |
| com. |
Request message for [PredictionService.CountTokens][]. |
| com. |
Request message for [PredictionService.CountTokens][]. |
| com. |
Response message for [PredictionService.CountTokens][]. |
| com. |
Response message for [PredictionService.CountTokens][]. |
| com. |
Runtime operation information for EndpointService.CreateEndpoint. |
| com. |
Runtime operation information for EndpointService.CreateEndpoint. |
| com. |
Request message for EndpointService.CreateEndpoint. |
| com. |
Request message for EndpointService.CreateEndpoint. |
| com. |
The storage details for CSV output content. |
| com. |
The storage details for CSV output content. |
| com. |
The storage details for CSV input content. |
| com. |
The storage details for CSV input content. |
| com. |
A description of resources that are dedicated to a DeployedModel or DeployedIndex, and that need a higher degree of manual configuration. |
| com. |
A description of resources that are dedicated to a DeployedModel or DeployedIndex, and that need a higher degree of manual configuration. |
| com. |
Request message for EndpointService.DeleteEndpoint. |
| com. |
Request message for EndpointService.DeleteEndpoint. |
| com. |
Details of operations that perform deletes of any entities. |
| com. |
Details of operations that perform deletes of any entities. |
| com. |
Runtime operation information for EndpointService.DeployModel. |
| com. |
Runtime operation information for EndpointService.DeployModel. |
| com. |
Request message for EndpointService.DeployModel. |
| com. |
Request message for EndpointService.DeployModel. |
| com. |
Response message for EndpointService.DeployModel. |
| com. |
Response message for EndpointService.DeployModel. |
| com. |
A deployment of a Model. Endpoints contain one or more DeployedModels. |
| com. |
A deployment of a Model. Endpoints contain one or more DeployedModels. |
| com. |
Runtime status of the deployed model. |
| com. |
Runtime status of the deployed model. |
| com. |
|
| com. |
Request message for PredictionService.DirectPredict. |
| com. |
Request message for PredictionService.DirectPredict. |
| com. |
Response message for PredictionService.DirectPredict. |
| com. |
Response message for PredictionService.DirectPredict. |
| com. |
Request message for PredictionService.DirectRawPredict. |
| com. |
Request message for PredictionService.DirectRawPredict. |
| com. |
Response message for PredictionService.DirectRawPredict. |
| com. |
Response message for PredictionService.DirectRawPredict. |
| com. |
The input content is encapsulated and uploaded in the request. |
| com. |
The input content is encapsulated and uploaded in the request. |
| com. |
Represents the spec of disk options. |
| com. |
Represents the spec of disk options. |
| com. |
DNS peering configuration. These configurations are used to create DNS peering zones in the Vertex tenant project VPC, enabling resolution of records within the specified domain hosted in the target network's |
| com. |
DNS peering configuration. These configurations are used to create DNS peering zones in the Vertex tenant project VPC, enabling resolution of records within the specified domain hosted in the target network's |
| com. |
A list of double values. |
| com. |
A list of double values. |
| com. |
Describes the options to customize dynamic retrieval. |
| com. |
Describes the options to customize dynamic retrieval. |
| com. |
Request message for PredictionService.EmbedContent. |
| com. |
Request message for PredictionService.EmbedContent. |
| com. |
Response message for PredictionService.EmbedContent. |
| com. |
Response message for PredictionService.EmbedContent. |
| com. |
A list of floats representing an embedding. |
| com. |
A list of floats representing an embedding. |
| com. |
Represents a customer-managed encryption key spec that can be applied to a top-level resource. |
| com. |
Represents a customer-managed encryption key spec that can be applied to a top-level resource. |
| com. |
|
| com. |
Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations. |
| com. |
Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations. |
| com. |
|
| com. |
Builder for projects/{project}/locations/{location}/endpoints/{endpoint}. |
| com. |
Builder for projects/{project}/locations/{location}/publishers/{publisher}/models/{model}. |
| com. |
|
| com. |
|
| com. |
|
| com. |
|
| com. |
|
| com. |
|
| com. |
|
| com. |
A service for managing Vertex AI's Endpoints. |
| com. |
Base class for the server implementation of the service EndpointService. A service for managing Vertex AI's Endpoints. |
| com. |
|
| com. |
Builder for EndpointServiceSettings. |
| com. |
Tool to search public web data, powered by Vertex AI Search and Sec4 compliance. |
| com. |
Tool to search public web data, powered by Vertex AI Search and Sec4 compliance. |
| com. |
Example-based explainability that returns the nearest neighbors from the provided dataset. |
| com. |
Example-based explainability that returns the nearest neighbors from the provided dataset. |
| com. |
The Cloud Storage input instances. |
| com. |
The Cloud Storage input instances. |
| com. |
Overrides for example-based explanations. |
| com. |
Overrides for example-based explanations. |
| com. |
Restrictions namespace for example-based explanations overrides. |
| com. |
Restrictions namespace for example-based explanations overrides. |
| com. |
Code generated by the model that is meant to be executed, and the result returned to the model. |
| com. |
Code generated by the model that is meant to be executed, and the result returned to the model. |
| com. |
Request message for PredictionService.Explain. |
| com. |
Request message for PredictionService.Explain. |
| com. |
Response message for PredictionService.Explain. |
| com. |
Response message for PredictionService.Explain. |
| com. |
Explanation of a prediction (provided in PredictResponse.predictions) produced by the Model on a given |
| com. |
Explanation of a prediction (provided in PredictResponse.predictions) produced by the Model on a given |
| com. |
Metadata describing the Model's input and output for explanation. |
| com. |
Metadata describing the Model's input and output for explanation. |
| com. |
Metadata of the input of a feature. Fields other than |
| com. |
Metadata of the input of a feature. Fields other than |
| com. |
Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information |
| com. |
Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information |
| com. |
Visualization configurations for image explanation. |
| com. |
Visualization configurations for image explanation. |
| com. |
Metadata of the prediction output to be explained. |
| com. |
Metadata of the prediction output to be explained. |
| com. |
The ExplanationMetadata entries that can be overridden at online explanation time. |
| com. |
The ExplanationMetadata entries that can be overridden at online explanation time. |
| com. |
The input metadata entries to be overridden. |
| com. |
The input metadata entries to be overridden. |
| com. |
|
| com. |
Parameters to configure explaining for Model's predictions. |
| com. |
Parameters to configure explaining for Model's predictions. |
| com. |
|
| com. |
Specification of Model explanation. |
| com. |
Specification of Model explanation. |
| com. |
The ExplanationSpec entries that can be overridden at online explanation time. |
| com. |
The ExplanationSpec entries that can be overridden at online explanation time. |
| com. |
Configuration for faster model deployment. |
| com. |
Configuration for faster model deployment. |
| com. |
Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. |
| com. |
Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. |
| com. |
Noise sigma for a single feature. |
| com. |
Noise sigma for a single feature. |
| com. |
URI based data. |
| com. |
URI based data. |
| com. |
RagFile status. |
| com. |
RagFile status. |
| com. |
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. |
| com. |
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. |
| com. |
Function calling config. |
| com. |
Function calling config. |
| com. |
Structured representation of a function declaration as defined by the OpenAPI 3.0 specification. Included in this declaration are the function name, description, parameters and |
| com. |
Structured representation of a function declaration as defined by the OpenAPI 3.0 specification. Included in this declaration are the function name, description, parameters and |
| com. |
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 |
| com. |
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 |
| com. |
Raw media bytes for function response. Text should not be sent as raw bytes, use the 'text' field. |
| com. |
Raw media bytes for function response. Text should not be sent as raw bytes, use the 'text' field. |
| com. |
URI based data for function response. |
| com. |
URI based data for function response. |
| com. |
A datatype containing media that is part of a FunctionResponse message.
A FunctionResponsePart consists of data which has an associated datatype. A |
| com. |
A datatype containing media that is part of a FunctionResponse message.
A FunctionResponsePart consists of data which has an associated datatype. A |
| com. |
The Google Cloud Storage location where the output is to be written to. |
| com. |
The Google Cloud Storage location where the output is to be written to. |
| com. |
The Google Cloud Storage location for the input content. |
| com. |
The Google Cloud Storage location for the input content. |
| com. |
Configuration for GenAiAdvancedFeatures. |
| com. |
Configuration for GenAiAdvancedFeatures. |
| com. |
Configuration for Retrieval Augmented Generation feature. |
| com. |
Configuration for Retrieval Augmented Generation feature. |
| com. |
Request message for [PredictionService.GenerateContent]. |
| com. |
Request message for [PredictionService.GenerateContent]. |
| com. |
Response message for [PredictionService.GenerateContent]. |
| com. |
Response message for [PredictionService.GenerateContent]. |
| com. |
Content filter results for a prompt sent in the request. |
| com. |
Content filter results for a prompt sent in the request. |
| com. |
Usage metadata about response(s). |
| com. |
Usage metadata about response(s). |
| com. |
Generation config. |
| com. |
Generation config. |
| com. |
The configuration for routing the request to a specific model. |
| com. |
When automated routing is specified, the routing will be determined by the pretrained routing model and customer provided model routing preference. |
| com. |
When automated routing is specified, the routing will be determined by the pretrained routing model and customer provided model routing preference. |
| com. |
The configuration for routing the request to a specific model. |
| com. |
When manual routing is set, the specified model will be used directly. |
| com. |
When manual routing is set, the specified model will be used directly. |
| com. |
Config for thinking features. |
| com. |
Config for thinking features. |
| com. |
Generic Metadata shared by all operations. |
| com. |
Generic Metadata shared by all operations. |
| com. |
Request message for EndpointService.GetEndpoint |
| com. |
Request message for EndpointService.GetEndpoint |
| com. |
The Google Drive location for the input content. |
| com. |
The Google Drive location for the input content. |
| com. |
The type and ID of the Google Drive resource. |
| com. |
The type and ID of the Google Drive resource. |
| com. |
Tool to retrieve public maps data for grounding, powered by Google. |
| com. |
Tool to retrieve public maps data for grounding, powered by Google. |
| com. |
Tool to retrieve public web data for grounding, powered by Google. |
| com. |
Tool to retrieve public web data for grounding, powered by Google. |
| com. |
Grounding chunk. |
| com. |
Grounding chunk. |
| com. |
Chunk from Google Maps. |
| com. |
Chunk from Google Maps. |
| com. |
Protobuf type google.cloud.vertexai.v1.GroundingChunk.Maps.PlaceAnswerSources |
| com. |
Protobuf type google.cloud.vertexai.v1.GroundingChunk.Maps.PlaceAnswerSources |
| com. |
Encapsulates a review snippet. |
| com. |
Encapsulates a review snippet. |
| com. |
Chunk from context retrieved by the retrieval tools. |
| com. |
Chunk from context retrieved by the retrieval tools. |
| com. |
Chunk from the web. |
| com. |
Chunk from the web. |
| com. |
Metadata returned to client when grounding is enabled. |
| com. |
Metadata returned to client when grounding is enabled. |
| com. |
Source content flagging uri for a place or review. This is currently populated only for Google Maps grounding. |
| com. |
Source content flagging uri for a place or review. This is currently populated only for Google Maps grounding. |
| com. |
Grounding support. |
| com. |
Grounding support. |
| com. |
Config for image generation features. |
| com. |
Config for image generation features. |
| com. |
Config for importing RagFiles. |
| com. |
Config for importing RagFiles. |
| com. |
A list of int64 values. |
| com. |
A list of int64 values. |
| com. |
An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 |
| com. |
An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 |
| com. |
|
| com. |
The Jira source for the ImportRagFilesRequest. |
| com. |
The Jira source for the ImportRagFilesRequest. |
| com. |
JiraQueries contains the Jira queries and corresponding authentication. |
| com. |
JiraQueries contains the Jira queries and corresponding authentication. |
| com. |
Request message for EndpointService.ListEndpoints. |
| com. |
Request message for EndpointService.ListEndpoints. |
| com. |
Response message for EndpointService.ListEndpoints. |
| com. |
Response message for EndpointService.ListEndpoints. |
| com. |
|
| com. |
|
| com. |
|
| com. |
Service for LLM related utility functions. |
| com. |
Base class for the server implementation of the service LlmUtilityService. Service for LLM related utility functions. |
| com. |
|
| com. |
Builder for LlmUtilityServiceSettings. |
| com. |
|
| com. |
Builder for projects/{project}/locations/{location}. |
| com. |
Logprobs Result |
| com. |
Logprobs Result |
| com. |
Candidate for the logprobs token and score. |
| com. |
Candidate for the logprobs token and score. |
| com. |
Candidates with top log probabilities at each decoding step. |
| com. |
Candidates with top log probabilities at each decoding step. |
| com. |
Represents a mount configuration for Lustre file system. |
| com. |
Represents a mount configuration for Lustre file system. |
| com. |
|
| com. |
Specification of a single machine. |
| com. |
Specification of a single machine. |
| com. |
Represents token counting info for a single modality. |
| com. |
Represents token counting info for a single modality. |
| com. |
Configuration for Model Armor integrations of prompt and responses. |
| com. |
Configuration for Model Armor integrations of prompt and responses. |
| com. |
Aggregated explanation metrics for a Model over a set of instances. |
| com. |
Aggregated explanation metrics for a Model over a set of instances. |
| com. |
Configuration for a multi-speaker text-to-speech request. |
| com. |
Configuration for a multi-speaker text-to-speech request. |
| com. |
Runtime operation information for EndpointService.MutateDeployedModel. |
| com. |
Runtime operation information for EndpointService.MutateDeployedModel. |
| com. |
Request message for EndpointService.MutateDeployedModel. |
| com. |
Request message for EndpointService.MutateDeployedModel. |
| com. |
Response message for EndpointService.MutateDeployedModel. |
| com. |
Response message for EndpointService.MutateDeployedModel. |
| com. |
Neighbors for example-based explanations. |
| com. |
Neighbors for example-based explanations. |
| com. |
Represents a mount configuration for Network File System (NFS) to mount. |
| com. |
Represents a mount configuration for Network File System (NFS) to mount. |
| com. |
|
| com. |
|
| com. |
PSC config that is used to automatically create PSC endpoints in the user projects. |
| com. |
PSC config that is used to automatically create PSC endpoints in the user projects. |
| com. |
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 |
| com. |
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 |
| com. |
Partial argument value of the function call. |
| com. |
Partial argument value of the function call. |
| com. |
Represents the spec of persistent disk options. |
| com. |
Represents the spec of persistent disk options. |
| com. |
Configuration for a prebuilt voice. |
| com. |
Configuration for a prebuilt voice. |
| com. |
Request message for PredictionService.Predict. |
| com. |
Request message for PredictionService.Predict. |
| com. |
Configuration for logging request-response to a BigQuery table. |
| com. |
Configuration for logging request-response to a BigQuery table. |
| com. |
Response message for PredictionService.Predict. |
| com. |
Response message for PredictionService.Predict. |
| com. |
|
| com. |
|
| com. |
|
| com. |
A service for online predictions and explanations. |
| com. |
Base class for the server implementation of the service PredictionService. A service for online predictions and explanations. |
| com. |
|
| com. |
Builder for PredictionServiceSettings. |
| com. |
Preset configuration for example-based explanations |
| com. |
Preset configuration for example-based explanations |
| com. |
PrivateEndpoints proto is used to provide paths for users to send requests privately. To send request via private service access, use predict_http_uri, |
| com. |
PrivateEndpoints proto is used to provide paths for users to send requests privately. To send request via private service access, use predict_http_uri, |
| com. |
Represents configuration for private service connect. |
| com. |
Represents configuration for private service connect. |
| com. |
PscAutomatedEndpoints defines the output of the forwarding rule automatically created by each PscAutomationConfig. |
| com. |
PscAutomatedEndpoints defines the output of the forwarding rule automatically created by each PscAutomationConfig. |
| com. |
Configuration for PSC-I. |
| com. |
Configuration for PSC-I. |
| com. |
A RagChunk includes the content of a chunk of a RagFile, and associated metadata. |
| com. |
A RagChunk includes the content of a chunk of a RagFile, and associated metadata. |
| com. |
Represents where the chunk starts and ends in the document. |
| com. |
Represents where the chunk starts and ends in the document. |
| com. |
A RagCorpus is a RagFile container and a project can have multiple RagCorpora. |
| com. |
A RagCorpus is a RagFile container and a project can have multiple RagCorpora. |
| com. |
Config for the embedding model to use for RAG. |
| com. |
Config for the embedding model to use for RAG. |
| com. |
Config representing a model hosted on Vertex Prediction Endpoint. |
| com. |
Config representing a model hosted on Vertex Prediction Endpoint. |
| com. |
Config for RagEngine. |
| com. |
Config for RagEngine. |
| com. |
A RagFile contains user data for chunking, embedding and indexing. |
| com. |
A RagFile contains user data for chunking, embedding and indexing. |
| com. |
Specifies the size and overlap of chunks for RagFiles. |
| com. |
Specifies the size and overlap of chunks for RagFiles. |
| com. |
Specifies the fixed length chunking config. |
| com. |
Specifies the fixed length chunking config. |
| com. |
Specifies the parsing config for RagFiles. |
| com. |
Specifies the parsing config for RagFiles. |
| com. |
Document AI Layout Parser config. |
| com. |
Document AI Layout Parser config. |
| com. |
Specifies the advanced parsing for RagFiles. |
| com. |
Specifies the advanced parsing for RagFiles. |
| com. |
Specifies the transformation config for RagFiles. |
| com. |
Specifies the transformation config for RagFiles. |
| com. |
Configuration message for RagManagedDb used by RagEngine. |
| com. |
Basic tier is a cost-effective and low compute tier suitable for the following cases: * Experimenting with RagManagedDb. |
| com. |
Basic tier is a cost-effective and low compute tier suitable for the following cases: * Experimenting with RagManagedDb. |
| com. |
Configuration message for RagManagedDb used by RagEngine. |
| com. |
Scaled tier offers production grade performance along with autoscaling functionality. It is suitable for customers with large amounts of data or performance sensitive workloads. |
| com. |
Scaled tier offers production grade performance along with autoscaling functionality. It is suitable for customers with large amounts of data or performance sensitive workloads. |
| com. |
Disables the RAG Engine service and deletes all your data held within this service. This will halt the billing of the service. |
| com. |
Disables the RAG Engine service and deletes all your data held within this service. This will halt the billing of the service. |
| com. |
Specifies the context retrieval config. |
| com. |
Specifies the context retrieval config. |
| com. |
Config for filters. |
| com. |
Config for filters. |
| com. |
Config for ranking and reranking. |
| com. |
Config for ranking and reranking. |
| com. |
Config for LlmRanker. |
| com. |
Config for LlmRanker. |
| com. |
Config for Rank Service. |
| com. |
Config for Rank Service. |
| com. |
Config for the Vector DB to use for RAG. |
| com. |
Config for the Vector DB to use for RAG. |
| com. |
The config for the Pinecone. |
| com. |
The config for the Pinecone. |
| com. |
The config for the default RAG-managed Vector DB. |
| com. |
Config for ANN search. RagManagedDb uses a tree-based structure to partition data and |
| com. |
Config for ANN search. RagManagedDb uses a tree-based structure to partition data and |
| com. |
The config for the default RAG-managed Vector DB. |
| com. |
Config for KNN search. |
| com. |
Config for KNN search. |
| com. |
The config for the Vertex Vector Search. |
| com. |
The config for the Vertex Vector Search. |
| com. |
Request message for PredictionService.RawPredict. |
| com. |
Request message for PredictionService.RawPredict. |
| com. |
The configuration for the replicated voice to use. |
| com. |
The configuration for the replicated voice to use. |
| com. |
A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. |
| com. |
A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. |
| com. |
|
| com. |
Statistics information about resource consumption. |
| com. |
Statistics information about resource consumption. |
| com. |
Defines a retrieval tool that model can call to access external knowledge. |
| com. |
Defines a retrieval tool that model can call to access external knowledge. |
| com. |
Retrieval config. |
| com. |
Retrieval config. |
| com. |
Metadata related to retrieval in the grounding flow. |
| com. |
Metadata related to retrieval in the grounding flow. |
| com. |
Safety rating corresponding to the generated content. |
| com. |
Safety rating corresponding to the generated content. |
| com. |
Safety settings. |
| com. |
Safety settings. |
| com. |
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. |
| com. |
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. |
| com. |
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 |
| com. |
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 |
| com. |
Google search entry point. |
| com. |
Google search entry point. |
| com. |
Segment of the content. |
| com. |
Segment of the content. |
| com. |
|
| com. |
The SharePointSources to pass to ImportRagFiles. |
| com. |
The SharePointSources to pass to ImportRagFiles. |
| com. |
An individual SharePointSource. |
| com. |
An individual SharePointSource. |
| com. |
A set of Shielded Instance options. See Images using supported Shielded VM features. |
| com. |
A set of Shielded Instance options. See Images using supported Shielded VM features. |
| com. |
The Slack source for the ImportRagFilesRequest. |
| com. |
The Slack source for the ImportRagFilesRequest. |
| com. |
SlackChannels contains the Slack channels and corresponding access token. |
| com. |
SlackChannels contains the Slack channels and corresponding access token. |
| com. |
SlackChannel contains the Slack channel ID and the time range to import. |
| com. |
SlackChannel contains the Slack channel ID and the time range to import. |
| com. |
Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from |
| com. |
Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from |
| com. |
Configuration for a single speaker in a multi-speaker setup. |
| com. |
Configuration for a single speaker in a multi-speaker setup. |
| com. |
Configuration for Speculative Decoding. |
| com. |
Configuration for Speculative Decoding. |
| com. |
Draft model speculation works by using the smaller model to generate candidate tokens for speculative decoding. |
| com. |
Draft model speculation works by using the smaller model to generate candidate tokens for speculative decoding. |
| com. |
N-Gram speculation works by trying to find matching tokens in the previous prompt sequence and use those as speculation for generating new tokens. |
| com. |
N-Gram speculation works by trying to find matching tokens in the previous prompt sequence and use those as speculation for generating new tokens. |
| com. |
Configuration for speech generation. |
| com. |
Configuration for speech generation. |
| com. |
Request message for PredictionService.StreamDirectPredict. |
| com. |
Request message for PredictionService.StreamDirectPredict. |
| com. |
Response message for PredictionService.StreamDirectPredict. |
| com. |
Response message for PredictionService.StreamDirectPredict. |
| com. |
Request message for PredictionService.StreamDirectRawPredict. |
| com. |
Request message for PredictionService.StreamDirectRawPredict. |
| com. |
Response message for PredictionService.StreamDirectRawPredict. |
| com. |
Response message for PredictionService.StreamDirectRawPredict. |
| com. |
Request message for PredictionService.StreamRawPredict. |
| com. |
Request message for PredictionService.StreamRawPredict. |
| com. |
Request message for PredictionService.StreamingPredict. |
| com. |
Request message for PredictionService.StreamingPredict. |
| com. |
Response message for PredictionService.StreamingPredict. |
| com. |
Response message for PredictionService.StreamingPredict. |
| com. |
Request message for PredictionService.StreamingRawPredict. |
| com. |
Request message for PredictionService.StreamingRawPredict. |
| com. |
Response message for PredictionService.StreamingRawPredict. |
| com. |
Response message for PredictionService.StreamingRawPredict. |
| com. |
A list of string values. |
| com. |
A list of string values. |
| com. |
The storage details for TFRecord output content. |
| com. |
The storage details for TFRecord output content. |
| com. |
A tensor value type. |
| com. |
A tensor value type. |
| com. |
Tokens info with a list of tokens and the corresponding list of token ids. |
| com. |
Tokens info with a list of tokens and the corresponding list of token ids. |
| com. |
Tool details that the model may use to generate response.
A Tool is a piece of code that enables the system to interact with |
| com. |
Tool details that the model may use to generate response.
A Tool is a piece of code that enables the system to interact with |
| com. |
Tool that executes code generated by the model, and automatically returns the result to the model. |
| com. |
Tool that executes code generated by the model, and automatically returns the result to the model. |
| com. |
Tool to support computer use. |
| com. |
Tool to support computer use. |
| com. |
GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google. |
| com. |
GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google. |
| com. |
Tool config. This config is shared for all tools provided in the request. |
| com. |
Tool config. This config is shared for all tools provided in the request. |
| com. |
|
| com. |
|
| com. |
Runtime operation information for EndpointService.UndeployModel. |
| com. |
Runtime operation information for EndpointService.UndeployModel. |
| com. |
Request message for EndpointService.UndeployModel. |
| com. |
Request message for EndpointService.UndeployModel. |
| com. |
Response message for EndpointService.UndeployModel. |
| com. |
Response message for EndpointService.UndeployModel. |
| com. |
Request message for EndpointService.UpdateEndpointLongRunning. |
| com. |
Request message for EndpointService.UpdateEndpointLongRunning. |
| com. |
Runtime operation information for EndpointService.UpdateEndpointLongRunning. |
| com. |
Runtime operation information for EndpointService.UpdateEndpointLongRunning. |
| com. |
Request message for EndpointService.UpdateEndpoint. |
| com. |
Request message for EndpointService.UpdateEndpoint. |
| com. |
Config for uploading RagFile. |
| com. |
Config for uploading RagFile. |
| com. |
Tool to support URL context. |
| com. |
Tool to support URL context. |
| com. |
Metadata related to url context retrieval tool. |
| com. |
Metadata related to url context retrieval tool. |
| com. |
Context of the a single url retrieval. |
| com. |
Context of the a single url retrieval. |
| com. |
Usage metadata about the content generation request and response. This message provides a detailed breakdown of token usage and other relevant metrics. |
| com. |
Usage metadata about the content generation request and response. This message provides a detailed breakdown of token usage and other relevant metrics. |
| com. |
|
| com. |
Retrieve from Vertex AI Search datastore or engine for grounding. datastore and engine are mutually exclusive. See https://cloud.google.com/products/agent-builder |
| com. |
Retrieve from Vertex AI Search datastore or engine for grounding. datastore and engine are mutually exclusive. See https://cloud.google.com/products/agent-builder |
| com. |
Define data stores within engine to filter on in a search call and configurations for those data stores. For more information, see https://cloud.google.com/generative-ai-app-builder/docs/reference/rpc/google.cloud.discoveryengine.v1#datastorespec |
| com. |
Define data stores within engine to filter on in a search call and configurations for those data stores. For more information, see https://cloud.google.com/generative-ai-app-builder/docs/reference/rpc/google.cloud.discoveryengine.v1#datastorespec |
| com. |
Config for the Vertex AI Search. |
| com. |
Config for the Vertex AI Search. |
| com. |
|
| com. |
Retrieve from Vertex RAG Store for grounding. |
| com. |
Retrieve from Vertex RAG Store for grounding. |
| com. |
The definition of the Rag resource. |
| com. |
The definition of the Rag resource. |
| com. |
Metadata describes the input video content. |
| com. |
Metadata describes the input video content. |
| com. |
Configuration for a voice. |
| com. |
Configuration for a voice. |
| com. |
An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: |
| com. |
An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: |