Agent Platform API
Build, scale, govern, and optimize sophisticated agents and models.
Fork copies the collection into your workspace, without the publisher's secrets, so you can add your own key and send requests. Star saves it to your starred APIs (Account › Marketplace) and helps others find it.
Overview
Build, scale, govern, and optimize sophisticated agents and models.
Endpoints 284
batchPredictionJobs
- GETLists BatchPredictionJobs in a Location.
/v1/batchPredictionJobs?filter=string&pageSize=0&pageToken=string&parent=string&readMask=stringLists BatchPredictionJobs in a Location. - POSTCreates a BatchPredictionJob
/v1/batchPredictionJobs?parent=stringCreates a BatchPredictionJob. A BatchPredictionJob once created will right away be attempted to start.
tuningJobs.operations
- GETGets the latest state of a long-running operation
/v1/:nameGets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service. - DELETEDeletes a long-running operation
/v1/:nameDeletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If… - POSTStarts asynchronous cancellation on a long-running operation
/v1/:name:cancelStarts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the… - GETLists operations that match the specified filter in the request
/v1/:name/operations?filter=string&pageSize=0&pageToken=string&returnPartialSuccess=trueLists operations that match the specified filter in the request. If the server doesn't support this method, it returns UNIMPLEMENTED. - POSTWaits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest…
/v1/:name:wait?timeout=stringWaits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state. If the operation is already done,…
reasoningEngines
- PATCHUpdates a reasoning engine.
/v1/:name?updateMask=stringUpdates a reasoning engine. - POSTAsync query using a reasoning engine.
/v1/:name:asyncQueryAsync query using a reasoning engine. - POSTCancels an AsyncQueryReasoningEngine operation.
/v1/:name:cancelAsyncQueryCancels an AsyncQueryReasoningEngine operation. - POSTExecutes code statelessly.
/v1/:name:executeCodeExecutes code statelessly. - GETLists reasoning engines in a location.
/v1/reasoningEngines?filter=string&pageSize=0&pageToken=string&parent=stringLists reasoning engines in a location. - POSTCreates a reasoning engine.
/v1/reasoningEngines?parent=stringCreates a reasoning engine.
projects.locations.featureOnlineStores.operations
- GETLists operations that match the specified filter in the request
/v1/:name:wait?filter=string&pageSize=0&pageToken=string&returnPartialSuccess=trueLists operations that match the specified filter in the request. If the server doesn't support this method, it returns UNIMPLEMENTED.
datasets
- GETLists Datasets in a Location.
/v1/datasets?filter=string&orderBy=string&pageSize=0&pageToken=string&parent=string&readMask=stringLists Datasets in a Location. - POSTCreates a Dataset.
/v1/datasets?parent=stringCreates a Dataset.
projects.locations.datasets.datasetVersions
- GETLists DatasetVersions in a Dataset.
/v1/:parent/datasetVersions?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists DatasetVersions in a Dataset. - POSTCreate a version from a Dataset.
/v1/:parent/datasetVersionsCreate a version from a Dataset. - GETRestores a dataset version.
/v1/:name:restoreRestores a dataset version.
publishers.models
- POSTReturn a list of tokens based on the input text.
/v1/:endpoint:computeTokensReturn a list of tokens based on the input text. - POSTPerform a token counting.
/v1/:endpoint:countTokensPerform a token counting. - POSTFetch an asynchronous online prediction operation.
/v1/:endpoint:fetchPredictOperationFetch an asynchronous online prediction operation. - POSTGenerate content with multimodal inputs.
/v1/:model:generateContentGenerate content with multimodal inputs. - POSTaiplatform.publishers.models.predict
/v1/:endpoint:predict - POSTaiplatform.publishers.models.predictLongRunning
/v1/:endpoint:predictLongRunning - POSTGenerate content with multimodal inputs with streaming support.
/v1/:model:streamGenerateContentGenerate content with multimodal inputs with streaming support.
projects.locations.endpoints.chat
- POSTExposes an OpenAI-compatible endpoint for chat completions.
/v1/:endpoint/chat/completionsExposes an OpenAI-compatible endpoint for chat completions.
interactions
- GETFully typed proto, unary version of GetInteraction that returns Interaction proto.
/v1/:name:poll?lastEventId=string&stream=trueFully typed proto, unary version of GetInteraction that returns Interaction proto. - GETFully typed proto, streaming version of GetInteraction that returns Interaction proto.
/v1/:name:stream?lastEventId=string&stream=trueFully typed proto, streaming version of GetInteraction that returns Interaction proto.
media
- POSTUpload a file into a RagCorpus.
/v1/:parent/ragFiles:uploadUpload a file into a RagCorpus.
operations
- GETLists operations that match the specified filter in the request
/v1/operations?filter=string&name=string&pageSize=0&pageToken=string&returnPartialSuccess=trueLists operations that match the specified filter in the request. If the server doesn't support this method, it returns UNIMPLEMENTED.
projects.locations
- POSTAgentic Retrieval Ask API for RAG.
/v1/:parent:askContextsAgentic Retrieval Ask API for RAG. - POSTAsynchronous API to retrieves relevant contexts for a query.
/v1/:parent:asyncRetrieveContextsAsynchronous API to retrieves relevant contexts for a query. - POSTGiven an input prompt, it returns augmented prompt from vertex rag store to guide LLM towards generating grounded…
/v1/:parent:augmentPromptGiven an input prompt, it returns augmented prompt from vertex rag store to guide LLM towards generating grounded responses. - POSTGiven an input text, it returns a score that evaluates the factuality of the text
/v1/:parent:corroborateContentGiven 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… - POSTDeploys a model to a new endpoint.
/v1/:destination:deployDeploys a model to a new endpoint. - POSTEvaluates a dataset based on a set of given metrics.
/v1/:location:evaluateDatasetEvaluates a dataset based on a set of given metrics. - POSTEvaluates instances based on a given metric.
/v1/:location:evaluateInstancesEvaluates instances based on a given metric. - POSTGenerates rubrics for a given prompt
/v1/:location:generateInstanceRubricsGenerates rubrics for a given prompt. A rubric represents a single testable criterion for evaluation. One input prompt could have multiple rubrics This RPC… - POSTGenerates loss clusters from evaluation results
/v1/:location:generateLossClustersGenerates loss clusters from evaluation results. This is a statelss API method that would not modify the EvaluationSet resource. - POSTGenerates synthetic (artificial) data based on a description
/v1/:location:generateSyntheticDataGenerates synthetic (artificial) data based on a description - POSTGenerates user scenarios for agent evaluation.
/v1/:location:generateUserScenariosGenerates user scenarios for agent evaluation. - GETLists information about the supported locations for this service
/v1/:name/locations?extraLocationTypes=string&filter=string&pageSize=0&pageToken=stringLists information about the supported locations for this service. This method lists locations based on the resource scope provided in the… - POSTRetrieves relevant contexts for a query.
/v1/:parent:retrieveContextsRetrieves relevant contexts for a query.
projects.locations.agents
- GETLists the agents in a location that belong to the caller
/v1/:parent/agents?filter=string&orderBy=string&pageSize=0&pageToken=stringLists the agents in a location that belong to the caller. An agent belongs to the end user recorded as its owner when it was created, so the response holds… - POSTCreates an agent.
/v1/:parent/agentsCreates an agent.
projects.locations.reasoningEngines
- POSTGets the access control policy for a resource
/v1/:resource:getIamPolicy?options.requestedPolicyVersion=0Gets the access control policy for a resource. Returns an empty policy if the resource exists and does not have a policy set. - POSTSets the access control policy on the specified resource
/v1/:resource:setIamPolicySets the access control policy on the specified resource. Replaces any existing policy. Can return NOT_FOUND, INVALID_ARGUMENT, and PERMISSION_DENIED errors. - POSTReturns permissions that a caller has on the specified resource
/v1/:resource:testIamPermissions?permissions=stringReturns permissions that a caller has on the specified resource. If the resource does not exist, this will return an empty set of permissions, not a NOT_FOUND… - GETLists reasoning engines in a location.
/v1/:parent/reasoningEngines?filter=string&pageSize=0&pageToken=stringLists reasoning engines in a location. - POSTCreates a reasoning engine.
/v1/:parent/reasoningEnginesCreates a reasoning engine.
projects.locations.batchPredictionJobs
- GETLists BatchPredictionJobs in a Location.
/v1/:parent/batchPredictionJobs?filter=string&pageSize=0&pageToken=string&readMask=stringLists BatchPredictionJobs in a Location. - POSTCreates a BatchPredictionJob
/v1/:parent/batchPredictionJobsCreates a BatchPredictionJob. A BatchPredictionJob once created will right away be attempted to start.
projects.locations.cachedContents
- GETLists cached contents in a project
/v1/:parent/cachedContents?pageSize=0&pageToken=stringLists cached contents in a project - POSTCreates cached content, this call will initialize the cached content in the data storage, and users need to pay for…
/v1/:parent/cachedContentsCreates cached content, this call will initialize the cached content in the data storage, and users need to pay for the cache data storage.
projects.locations.customJobs
- GETLists CustomJobs in a Location.
/v1/:parent/customJobs?filter=string&pageSize=0&pageToken=string&readMask=stringLists CustomJobs in a Location. - POSTCreates a CustomJob
/v1/:parent/customJobsCreates a CustomJob. A created CustomJob right away will be attempted to be run.
projects.locations.dataLabelingJobs
- GETLists DataLabelingJobs in a Location.
/v1/:parent/dataLabelingJobs?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists DataLabelingJobs in a Location. - POSTCreates a DataLabelingJob.
/v1/:parent/dataLabelingJobsCreates a DataLabelingJob.
projects.locations.datasets
- GETLists Datasets in a Location.
/v1/:parent/datasets?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists Datasets in a Location. - POSTCreates a Dataset.
/v1/:parent/datasetsCreates a Dataset. - POSTImports data into a Dataset.
/v1/:name:importImports data into a Dataset. - GETSearches DataItems in a Dataset.
/v1/:dataset:searchDataItems?annotationFilters=string&annotationsFilter=string&annotationsLimit=0&dataItemFilter=string&dataLabelingJob=string&fieldMask=string&orderBy=string&orderByAnnotation.orderBy=string&orderByAnnotation.savedQuery=string&orderByDataItem=string&pageSize=0&pageToken=string&savedQuery=stringSearches DataItems in a Dataset.
projects.locations.models
- POSTExports a trained, exportable Model to a location specified by the user
/v1/:name:exportExports a trained, exportable Model to a location specified by the user. A Model is considered to be exportable if it has at least one supported export format. - POSTCopies an already existing Vertex AI Model into the specified Location
/v1/:parent/models:copyCopies an already existing Vertex AI Model into the specified Location. The source Model must exist in the same Project. When copying custom Models, the users… - DELETEDeletes a Model version
/v1/:name:deleteVersionDeletes a Model version. Model version can only be deleted if there are no DeployedModels created from it. Deleting the only version in the Model is not… - GETLists Models in a Location.
/v1/:parent/models?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists Models in a Location. - GETLists checkpoints of the specified model version.
/v1/:name:listCheckpoints?pageSize=0&pageToken=stringLists checkpoints of the specified model version. - GETLists versions of the specified model.
/v1/:name:listVersions?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists versions of the specified model. - POSTMerges a set of aliases for a Model version.
/v1/:name:mergeVersionAliasesMerges a set of aliases for a Model version. - POSTIncrementally update the dataset used for an examples model.
/v1/:model:updateExplanationDatasetIncrementally update the dataset used for an examples model. - POSTUploads a Model artifact into Vertex AI.
/v1/:parent/models:uploadUploads a Model artifact into Vertex AI.
projects.locations.datasets.dataItems
- GETLists DataItems in a Dataset.
/v1/:parent/dataItems?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists DataItems in a Dataset.
projects.locations.datasets.dataItems.annotations
- GETLists Annotations belongs to a dataitem.
/v1/:parent/annotations?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists Annotations belongs to a dataitem.
projects.locations.datasets.savedQueries
- GETLists SavedQueries in a Dataset.
/v1/:parent/savedQueries?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists SavedQueries in a Dataset.
projects.locations.deploymentResourcePools
- GETList DeploymentResourcePools in a location.
/v1/:parent/deploymentResourcePools?pageSize=0&pageToken=stringList DeploymentResourcePools in a location. - POSTCreate a DeploymentResourcePool.
/v1/:parent/deploymentResourcePoolsCreate a DeploymentResourcePool. - GETList DeployedModels that have been deployed on this DeploymentResourcePool.
/v1/:deploymentResourcePool:queryDeployedModels?pageSize=0&pageToken=stringList DeployedModels that have been deployed on this DeploymentResourcePool.
projects.locations.endpoints
- GETLists Endpoints in a Location.
/v1/:parent/endpoints?filter=string&gdcZone=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists Endpoints in a Location. - POSTCreates an Endpoint.
/v1/:parent/endpoints?endpointId=stringCreates an Endpoint. - POSTDeploys a Model into this Endpoint, creating a DeployedModel within it.
/v1/:endpoint:deployModelDeploys a Model into this Endpoint, creating a DeployedModel within it. - POSTPerform an unary online prediction request to a gRPC model server for Vertex first-party products and frameworks.
/v1/:endpoint:directPredictPerform an unary online prediction request to a gRPC model server for Vertex first-party products and frameworks. - POSTPerform an unary online prediction request to a gRPC model server for custom containers.
/v1/:endpoint:directRawPredictPerform an unary online prediction request to a gRPC model server for custom containers. - POSTPerform an online explanation
/v1/:endpoint:explainPerform an online explanation. If deployed_model_id is specified, the corresponding DeployModel must have explanation_spec populated. If deployed_model_id is… - POSTUpdates an existing deployed model
/v1/:endpoint:mutateDeployedModelUpdates an existing deployed model. Updatable fields include min_replica_count, max_replica_count, required_replica_count, autoscaling_metric_specs,… - POSTUndeploys a Model from an Endpoint, removing a DeployedModel from it, and freeing all resources it's using.
/v1/:endpoint:undeployModelUndeploys a Model from an Endpoint, removing a DeployedModel from it, and freeing all resources it's using. - POSTUpdates an Endpoint with a long running operation.
/v1/:name:updateUpdates an Endpoint with a long running operation.
projects.locations.publishers.models
- POSTPerform an online prediction with an arbitrary HTTP payload
/v1/:endpoint:rawPredictPerform an online prediction with an arbitrary HTTP payload. The response includes the following HTTP headers: * X-Vertex-AI-Endpoint-Id: ID of the Endpoint… - POSTPerform a server-side streaming online prediction request for Vertex LLM streaming.
/v1/:endpoint:serverStreamingPredictPerform a server-side streaming online prediction request for Vertex LLM streaming. - POSTPerform a streaming online prediction with an arbitrary HTTP payload.
/v1/:endpoint:streamRawPredictPerform a streaming online prediction with an arbitrary HTTP payload. - POSTGenerates embeddings directly from multiple contents.
/v1/:model:batchEmbedContentsGenerates embeddings directly from multiple contents. - POSTEmbed content with multimodal inputs.
/v1/:model:embedContentEmbed content with multimodal inputs.
projects.locations.endpoints.deployedModels.invoke
- POSTForwards arbitrary HTTP requests for both streaming and non-streaming cases
/v1/:endpoint/deployedModels/:deployedModelId/invoke/:invokeIdForwards arbitrary HTTP requests for both streaming and non-streaming cases. To use this method, invoke_route_prefix must be set to allow the paths that will…
projects.locations.endpoints.google.science
- POSTForwards arbitrary HTTP requests for both streaming and non-streaming cases
/v1/:endpoint/science/inference?deployedModelId=stringForwards arbitrary HTTP requests for both streaming and non-streaming cases. To use this method, invoke_route_prefix must be set to allow the paths that will…
projects.locations.publishers.models.invoke
- POSTForwards arbitrary HTTP requests for both streaming and non-streaming cases
/v1/:endpoint/invoke/:invokeIdForwards arbitrary HTTP requests for both streaming and non-streaming cases. To use this method, invoke_route_prefix must be set to allow the paths that will…
projects.locations.endpoints.openapi
- POSTForwards arbitrary HTTP requests for both streaming and non-streaming cases
/v1/:endpoint/completions?deployedModelId=stringForwards arbitrary HTTP requests for both streaming and non-streaming cases. To use this method, invoke_route_prefix must be set to allow the paths that will… - POSTForwards arbitrary HTTP requests for both streaming and non-streaming cases
/v1/:endpoint/embeddings?deployedModelId=stringForwards arbitrary HTTP requests for both streaming and non-streaming cases. To use this method, invoke_route_prefix must be set to allow the paths that will… - POSTForwards arbitrary HTTP requests for both streaming and non-streaming cases
/v1/:endpoint/responses?deployedModelId=stringForwards arbitrary HTTP requests for both streaming and non-streaming cases. To use this method, invoke_route_prefix must be set to allow the paths that will…
projects.locations.evaluationItems
- GETLists Evaluation Items.
/v1/:parent/evaluationItems?filter=string&orderBy=string&pageSize=0&pageToken=stringLists Evaluation Items. - POSTCreates an Evaluation Item.
/v1/:parent/evaluationItemsCreates an Evaluation Item.
projects.locations.evaluationMetrics
- GETLists EvaluationMetrics.
/v1/:parent/evaluationMetrics?filter=string&orderBy=string&pageSize=0&pageToken=stringLists EvaluationMetrics. - POSTCreates an EvaluationMetric.
/v1/:parent/evaluationMetrics?evaluationMetricId=stringCreates an EvaluationMetric.
projects.locations.evaluationRuns
- GETLists Evaluation Runs.
/v1/:parent/evaluationRuns?filter=string&orderBy=string&pageSize=0&pageToken=stringLists Evaluation Runs. - POSTCreates an Evaluation Run.
/v1/:parent/evaluationRunsCreates an Evaluation Run.
projects.locations.evaluationSets
- GETLists Evaluation Sets.
/v1/:parent/evaluationSets?filter=string&orderBy=string&pageSize=0&pageToken=stringLists Evaluation Sets. - POSTCreates an Evaluation Set.
/v1/:parent/evaluationSetsCreates an Evaluation Set. - POSTImports an Evaluation Set.
/v1/:parent/evaluationSets:importImports an Evaluation Set.
projects.locations.featureGroups
- GETLists FeatureGroups in a given project and location.
/v1/:parent/featureGroups?filter=string&orderBy=string&pageSize=0&pageToken=stringLists FeatureGroups in a given project and location. - POSTCreates a new FeatureGroup in a given project and location.
/v1/:parent/featureGroups?featureGroupId=stringCreates a new FeatureGroup in a given project and location.
projects.locations.featurestores.entityTypes.features
- POSTCreates a batch of Features in a given EntityType.
/v1/:parent/features:batchCreateCreates a batch of Features in a given EntityType. - GETLists Features in a given EntityType.
/v1/:parent/features?filter=string&latestStatsCount=0&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists Features in a given EntityType. - POSTCreates a new Feature in a given EntityType.
/v1/:parent/features?featureId=stringCreates a new Feature in a given EntityType.
projects.locations.featureOnlineStores
- GETLists FeatureOnlineStores in a given project and location.
/v1/:parent/featureOnlineStores?filter=string&orderBy=string&pageSize=0&pageToken=stringLists FeatureOnlineStores in a given project and location. - POSTCreates a new FeatureOnlineStore in a given project and location.
/v1/:parent/featureOnlineStores?featureOnlineStoreId=stringCreates a new FeatureOnlineStore in a given project and location.
projects.locations.featureOnlineStores.featureViews
- GETLists FeatureViews in a given FeatureOnlineStore.
/v1/:parent/featureViews?filter=string&orderBy=string&pageSize=0&pageToken=stringLists FeatureViews in a given FeatureOnlineStore. - POSTCreates a new FeatureView in a given FeatureOnlineStore.
/v1/:parent/featureViews?featureViewId=string&runSyncImmediately=trueCreates a new FeatureView in a given FeatureOnlineStore. - POSTBidirectional streaming RPC to directly write to feature values in a feature view
/v1/:featureView:directWriteBidirectional streaming RPC to directly write to feature values in a feature view. Requests may not have a one-to-one mapping to responses and responses may… - POSTFetch feature values under a FeatureView.
/v1/:featureView:fetchFeatureValuesFetch feature values under a FeatureView. - POSTRPC to generate an access token for the given feature view
/v1/:featureView:generateFetchAccessTokenRPC to generate an access token for the given feature view. FeatureViews under the same FeatureOnlineStore share the same access token. - POSTSearch the nearest entities under a FeatureView
/v1/:featureView:searchNearestEntitiesSearch the nearest entities under a FeatureView. Search only works for indexable feature view; if a feature view isn't indexable, returns Invalid argument… - POSTTriggers on-demand sync for the FeatureView.
/v1/:featureView:syncTriggers on-demand sync for the FeatureView.
projects.locations.featureOnlineStores.featureViews.featureViewSyncs
- GETLists FeatureViewSyncs in a given FeatureView.
/v1/:parent/featureViewSyncs?filter=string&orderBy=string&pageSize=0&pageToken=stringLists FeatureViewSyncs in a given FeatureView.
projects.locations.featurestores
- POSTBatch reads Feature values from a Featurestore
/v1/:featurestore:batchReadFeatureValuesBatch reads Feature values from a Featurestore. This API enables batch reading Feature values, where each read instance in the batch may read Feature values… - GETLists Featurestores in a given project and location.
/v1/:parent/featurestores?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists Featurestores in a given project and location. - POSTCreates a new Featurestore in a given project and location.
/v1/:parent/featurestores?featurestoreId=stringCreates a new Featurestore in a given project and location. - GETSearches Features matching a query in a given project.
/v1/:location/featurestores:searchFeatures?pageSize=0&pageToken=string&query=stringSearches Features matching a query in a given project.
projects.locations.featurestores.entityTypes
- GETLists EntityTypes in a given Featurestore.
/v1/:parent/entityTypes?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists EntityTypes in a given Featurestore. - POSTCreates a new EntityType in a given Featurestore.
/v1/:parent/entityTypes?entityTypeId=stringCreates a new EntityType in a given Featurestore. - POSTDelete Feature values from Featurestore
/v1/:entityType:deleteFeatureValuesDelete Feature values from Featurestore. The progress of the deletion is tracked by the returned operation. The deleted feature values are guaranteed to be… - POSTExports Feature values from all the entities of a target EntityType.
/v1/:entityType:exportFeatureValuesExports Feature values from all the entities of a target EntityType. - POSTImports Feature values into the Featurestore from a source storage
/v1/:entityType:importFeatureValuesImports Feature values into the Featurestore from a source storage. The progress of the import is tracked by the returned operation. The imported features are… - POSTReads Feature values of a specific entity of an EntityType
/v1/:entityType:readFeatureValuesReads Feature values of a specific entity of an EntityType. For reading feature values of multiple entities of an EntityType, please use… - POSTReads Feature values for multiple entities
/v1/:entityType:streamingReadFeatureValuesReads Feature values for multiple entities. Depending on their size, data for different entities may be broken up across multiple responses. - POSTWrites Feature values of one or more entities of an EntityType
/v1/:entityType:writeFeatureValuesWrites Feature values of one or more entities of an EntityType. The Feature values are merged into existing entities if any. The Feature values to be written…
projects.locations.hyperparameterTuningJobs
- GETLists HyperparameterTuningJobs in a Location.
/v1/:parent/hyperparameterTuningJobs?filter=string&pageSize=0&pageToken=string&readMask=stringLists HyperparameterTuningJobs in a Location. - POSTCreates a HyperparameterTuningJob
/v1/:parent/hyperparameterTuningJobsCreates a HyperparameterTuningJob
projects.locations.indexEndpoints
- GETLists IndexEndpoints in a Location.
/v1/:parent/indexEndpoints?filter=string&pageSize=0&pageToken=string&readMask=stringLists IndexEndpoints in a Location. - POSTCreates an IndexEndpoint.
/v1/:parent/indexEndpointsCreates an IndexEndpoint. - POSTDeploys an Index into this IndexEndpoint, creating a DeployedIndex within it.
/v1/:indexEndpoint:deployIndexDeploys an Index into this IndexEndpoint, creating a DeployedIndex within it. - POSTFinds the nearest neighbors of each vector within the request.
/v1/:indexEndpoint:findNeighborsFinds the nearest neighbors of each vector within the request. - POSTUpdate an existing DeployedIndex under an IndexEndpoint.
/v1/:indexEndpoint:mutateDeployedIndex?updateMask=stringUpdate an existing DeployedIndex under an IndexEndpoint. - POSTReads the datapoints/vectors of the given IDs
/v1/:indexEndpoint:readIndexDatapointsReads the datapoints/vectors of the given IDs. A maximum of 1000 datapoints can be retrieved in a batch. - POSTUndeploys an Index from an IndexEndpoint, removing a DeployedIndex from it, and freeing all resources it's using.
/v1/:indexEndpoint:undeployIndexUndeploys an Index from an IndexEndpoint, removing a DeployedIndex from it, and freeing all resources it's using.
projects.locations.indexes
- GETLists Indexes in a Location.
/v1/:parent/indexes?filter=string&pageSize=0&pageToken=string&readMask=stringLists Indexes in a Location. - POSTCreates an Index.
/v1/:parent/indexesCreates an Index. - POSTRemove Datapoints from an Index.
/v1/:index:removeDatapointsRemove Datapoints from an Index. - POSTAdd/update Datapoints into an Index.
/v1/:index:upsertDatapointsAdd/update Datapoints into an Index.
projects.locations.interactions
- POSTCreates an interaction.
/v1/projects/:projectsId/locations/:locationsId/interactions:createCreates an interaction. - POSTCreates an interaction and streams the response.
/v1/projects/:projectsId/locations/:locationsId/interactions:createStreamCreates an interaction and streams the response.
projects.locations.interactionsHttp
- POSTCancels an interaction by id
/v1/:name/cancelCancels an interaction by id. This only applies to background interactions that are still running. - POSTCreates a new interaction.
/v1/:parent/interactionsHttpCreates a new interaction.
projects.locations.memoryBanks
- POSTIngests events for a Memory Bank.
/v1/:parent:ingestEventsIngests events for a Memory Bank.
projects.locations.reasoningEngines.memories
- GETList Memories.
/v1/:parent/memories?filter=string&orderBy=string&pageSize=0&pageToken=stringList Memories. - POSTCreate a Memory.
/v1/:parent/memories?memoryId=stringCreate a Memory. - POSTGenerate memories.
/v1/:parent/memories:generateGenerate memories. - POSTPurge memories.
/v1/:parent/memories:purgePurge memories. - POSTRetrieve memories.
/v1/:parent/memories:retrieveRetrieve memories. - POSTRollback Memory to a specific revision.
/v1/:name:rollbackRollback Memory to a specific revision. - POSTIngests events for a Memory Bank.
/v1/:parent/memories:ingestEventsIngests events for a Memory Bank.
projects.locations.reasoningEngines.memories.revisions
- GETList Memory Revisions for a Memory.
/v1/:parent/revisions?filter=string&pageSize=0&pageToken=stringList Memory Revisions for a Memory.
projects.locations.metadataStores
- GETLists MetadataStores for a Location.
/v1/:parent/metadataStores?pageSize=0&pageToken=stringLists MetadataStores for a Location. - POSTInitializes a MetadataStore, including allocation of resources.
/v1/:parent/metadataStores?metadataStoreId=stringInitializes a MetadataStore, including allocation of resources.
projects.locations.metadataStores.artifacts
- GETLists Artifacts in the MetadataStore.
/v1/:parent/artifacts?filter=string&orderBy=string&pageSize=0&pageToken=stringLists Artifacts in the MetadataStore. - POSTCreates an Artifact associated with a MetadataStore.
/v1/:parent/artifacts?artifactId=stringCreates an Artifact associated with a MetadataStore. - POSTPurges Artifacts.
/v1/:parent/artifacts:purgePurges Artifacts. - GETRetrieves lineage of an Artifact represented through Artifacts and Executions connected by Event edges and returned as…
/v1/:artifact:queryArtifactLineageSubgraph?filter=string&maxHops=0Retrieves lineage of an Artifact represented through Artifacts and Executions connected by Event edges and returned as a LineageSubgraph.
projects.locations.metadataStores.contexts
- POSTAdds a set of Artifacts and Executions to a Context
/v1/:context:addContextArtifactsAndExecutionsAdds a set of Artifacts and Executions to a Context. If any of the Artifacts or Executions have already been added to a Context, they are simply skipped. - POSTAdds a set of Contexts as children to a parent Context
/v1/:context:addContextChildrenAdds a set of Contexts as children to a parent Context. If any of the child Contexts have already been added to the parent Context, they are simply skipped.… - GETLists Contexts on the MetadataStore.
/v1/:parent/contexts?filter=string&orderBy=string&pageSize=0&pageToken=stringLists Contexts on the MetadataStore. - POSTCreates a Context associated with a MetadataStore.
/v1/:parent/contexts?contextId=stringCreates a Context associated with a MetadataStore. - POSTPurges Contexts.
/v1/:parent/contexts:purgePurges Contexts. - GETRetrieves Artifacts and Executions within the specified Context, connected by Event edges and returned as a…
/v1/:context:queryContextLineageSubgraphRetrieves Artifacts and Executions within the specified Context, connected by Event edges and returned as a LineageSubgraph. - POSTRemove a set of children contexts from a parent Context
/v1/:context:removeContextChildrenRemove a set of children contexts from a parent Context. If any of the child Contexts were NOT added to the parent Context, they are simply skipped.
projects.locations.metadataStores.executions
- POSTAdds Events to the specified Execution
/v1/:execution:addExecutionEventsAdds Events to the specified Execution. An Event indicates whether an Artifact was used as an input or output for an Execution. If an Event already exists… - GETLists Executions in the MetadataStore.
/v1/:parent/executions?filter=string&orderBy=string&pageSize=0&pageToken=stringLists Executions in the MetadataStore. - POSTCreates an Execution associated with a MetadataStore.
/v1/:parent/executions?executionId=stringCreates an Execution associated with a MetadataStore. - POSTPurges Executions.
/v1/:parent/executions:purgePurges Executions. - GETObtains the set of input and output Artifacts for this Execution, in the form of LineageSubgraph that also contains…
/v1/:execution:queryExecutionInputsAndOutputsObtains the set of input and output Artifacts for this Execution, in the form of LineageSubgraph that also contains the Execution and connecting Events.
projects.locations.metadataStores.metadataSchemas
- GETLists MetadataSchemas.
/v1/:parent/metadataSchemas?filter=string&pageSize=0&pageToken=stringLists MetadataSchemas. - POSTCreates a MetadataSchema.
/v1/:parent/metadataSchemas?metadataSchemaId=stringCreates a MetadataSchema.
projects.locations.migratableResources
- POSTBatch migrates resources from ml.googleapis.com, automl.googleapis.com, and datalabeling.googleapis.com to Vertex AI.
/v1/:parent/migratableResources:batchMigrateBatch migrates resources from ml.googleapis.com, automl.googleapis.com, and datalabeling.googleapis.com to Vertex AI. - POSTSearches all of the resources in automl.googleapis.com, datalabeling.googleapis.com and ml.googleapis.com that can be…
/v1/:parent/migratableResources:searchSearches all of the resources in automl.googleapis.com, datalabeling.googleapis.com and ml.googleapis.com that can be migrated to Vertex AI's given location.
projects.locations.modelDeploymentMonitoringJobs
- GETLists ModelDeploymentMonitoringJobs in a Location.
/v1/:parent/modelDeploymentMonitoringJobs?filter=string&pageSize=0&pageToken=string&readMask=stringLists ModelDeploymentMonitoringJobs in a Location. - POSTCreates a ModelDeploymentMonitoringJob
/v1/:parent/modelDeploymentMonitoringJobsCreates a ModelDeploymentMonitoringJob. It will run periodically on a configured interval. - POSTSearches Model Monitoring Statistics generated within a given time window.
/v1/:modelDeploymentMonitoringJob:searchModelDeploymentMonitoringStatsAnomaliesSearches Model Monitoring Statistics generated within a given time window.
reasoningEngines.sandboxEnvironments
- POSTPauses the specific SandboxEnvironment.
/v1/:name:pausePauses the specific SandboxEnvironment. - POSTResumes the specific SandboxEnvironment.
/v1/:name:resumeResumes the specific SandboxEnvironment. - POSTChecks whether the caller is authorized to access the sandbox environment
/v1/:name:authorizeAccessChecks whether the caller is authorized to access the sandbox environment. Authorization is performed entirely by the API infrastructure from the… - GETLists SandboxEnvironments in a given reasoning engine.
/v1/:parent/sandboxEnvironments?filter=string&pageSize=0&pageToken=stringLists SandboxEnvironments in a given reasoning engine. - POSTCreates a SandboxEnvironment in a given reasoning engine.
/v1/:parent/sandboxEnvironmentsCreates a SandboxEnvironment in a given reasoning engine. - POSTExecutes using a sandbox environment.
/v1/:name:executeExecutes using a sandbox environment. - POSTSnapshots the specific SandboxEnvironment resource and creates a SandboxEnvironmentSnapshot resource.
/v1/:name:snapshotSnapshots the specific SandboxEnvironment resource and creates a SandboxEnvironmentSnapshot resource.
projects.locations.models.evaluations
- POSTImports an externally generated ModelEvaluation.
/v1/:parent/evaluations:importImports an externally generated ModelEvaluation. - GETLists ModelEvaluations in a Model.
/v1/:parent/evaluations?filter=string&pageSize=0&pageToken=string&readMask=stringLists ModelEvaluations in a Model.
projects.locations.models.evaluations.slices
- POSTImports a list of externally generated EvaluatedAnnotations.
/v1/:parent:batchImportImports a list of externally generated EvaluatedAnnotations. - GETLists ModelEvaluationSlices in a ModelEvaluation.
/v1/:parent/slices?filter=string&pageSize=0&pageToken=string&readMask=stringLists ModelEvaluationSlices in a ModelEvaluation.
projects.locations.nasJobs
- GETLists NasJobs in a Location.
/v1/:parent/nasJobs?filter=string&pageSize=0&pageToken=string&readMask=stringLists NasJobs in a Location. - POSTCreates a NasJob
/v1/:parent/nasJobsCreates a NasJob
projects.locations.nasJobs.nasTrialDetails
- GETList top NasTrialDetails of a NasJob.
/v1/:parent/nasTrialDetails?pageSize=0&pageToken=stringList top NasTrialDetails of a NasJob.
projects.locations.notebookExecutionJobs
- GETLists NotebookExecutionJobs in a Location.
/v1/:parent/notebookExecutionJobs?filter=string&orderBy=string&pageSize=0&pageToken=string&view=NOTEBOOK_EXECUTION_JOB_VIEW_UNSPECIFIEDLists NotebookExecutionJobs in a Location. - POSTCreates a NotebookExecutionJob.
/v1/:parent/notebookExecutionJobs?notebookExecutionJobId=stringCreates a NotebookExecutionJob.
projects.locations.notebookRuntimeTemplates
- GETLists NotebookRuntimeTemplates in a Location.
/v1/:parent/notebookRuntimeTemplates?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists NotebookRuntimeTemplates in a Location. - POSTCreates a NotebookRuntimeTemplate.
/v1/:parent/notebookRuntimeTemplates?notebookRuntimeTemplateId=stringCreates a NotebookRuntimeTemplate. - POSTSets the default NotebookRuntimeTemplate for a Location.
/v1/:parent/notebookRuntimeTemplates:setDefaultSets the default NotebookRuntimeTemplate for a Location.
projects.locations.notebookRuntimes
- POSTAssigns a NotebookRuntime to a user for a particular Notebook file
/v1/:parent/notebookRuntimes:assignAssigns a NotebookRuntime to a user for a particular Notebook file. This method will either returns an existing assignment or generates a new one. - GETLists NotebookRuntimes in a Location.
/v1/:parent/notebookRuntimes?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists NotebookRuntimes in a Location. - POSTStarts a NotebookRuntime.
/v1/:name:startStarts a NotebookRuntime. - POSTUpgrades a NotebookRuntime.
/v1/:name:upgradeUpgrades a NotebookRuntime.
projects.locations.studies.trials
- POSTStops a Trial.
/v1/:name:stopStops a Trial. - POSTAdds a measurement of the objective metrics to a Trial
/v1/:trialName:addTrialMeasurementAdds a measurement of the objective metrics to a Trial. This measurement is assumed to have been taken before the Trial is complete. - POSTChecks whether a Trial should stop or not
/v1/:trialName:checkTrialEarlyStoppingStateChecks whether a Trial should stop or not. Returns a long-running operation. When the operation is successful, it will contain a… - POSTMarks a Trial as complete.
/v1/:name:completeMarks a Trial as complete. - GETLists the Trials associated with a Study.
/v1/:parent/trials?pageSize=0&pageToken=stringLists the Trials associated with a Study. - POSTAdds a user provided Trial to a Study.
/v1/:parent/trialsAdds a user provided Trial to a Study. - POSTLists the pareto-optimal Trials for multi-objective Study or the optimal Trials for single-objective Study
/v1/:parent/trials:listOptimalTrialsLists the pareto-optimal Trials for multi-objective Study or the optimal Trials for single-objective Study. The definition of pareto-optimal can be checked in… - POSTAdds one or more Trials to a Study, with parameter values suggested by Vertex AI Vizier
/v1/:parent/trials:suggestAdds one or more Trials to a Study, with parameter values suggested by Vertex AI Vizier. Returns a long-running operation associated with the generation of…
projects.locations.onlineEvaluators
- POSTActivates an OnlineEvaluator.
/v1/:name:activateActivates an OnlineEvaluator. - GETLists the OnlineEvaluators for the given project and location.
/v1/:parent/onlineEvaluators?filter=string&orderBy=string&pageSize=0&pageToken=stringLists the OnlineEvaluators for the given project and location. - POSTCreates an OnlineEvaluator in the given project and location.
/v1/:parent/onlineEvaluatorsCreates an OnlineEvaluator in the given project and location. - POSTSuspends an OnlineEvaluator
/v1/:name:suspendSuspends an OnlineEvaluator. When an OnlineEvaluator is suspended, it won't run any evaluations until it is activated again.
projects.locations.persistentResources
- GETLists PersistentResources in a Location.
/v1/:parent/persistentResources?pageSize=0&pageToken=stringLists PersistentResources in a Location. - POSTCreates a PersistentResource.
/v1/:parent/persistentResources?persistentResourceId=stringCreates a PersistentResource. - POSTReboots a PersistentResource.
/v1/:name:rebootReboots a PersistentResource.
projects.locations.pipelineJobs
- POSTBatch cancel PipelineJobs
/v1/:parent/pipelineJobs:batchCancelBatch cancel PipelineJobs. Firstly the server will check if all the jobs are in non-terminal states, and skip the jobs that are already terminated. If the… - POSTBatch deletes PipelineJobs The Operation is atomic
/v1/:parent/pipelineJobs:batchDeleteBatch deletes PipelineJobs The Operation is atomic. If it fails, none of the PipelineJobs are deleted. If it succeeds, all of the PipelineJobs are deleted. - GETLists PipelineJobs in a Location.
/v1/:parent/pipelineJobs?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists PipelineJobs in a Location. - POSTCreates a PipelineJob
/v1/:parent/pipelineJobs?pipelineJobId=stringCreates a PipelineJob. A PipelineJob will run immediately when created.
projects.locations.publishers.files
- GETDownloads the contents of the given file
/v1/:name/contentDownloads the contents of the given file. Only files marked downloadable can be retrieved this way; user-uploaded files are not downloadable. - GETLists the files owned by the requesting project and location
/v1/:parent/publishers/:publishersId/files?limit=0&page=stringLists the files owned by the requesting project and location. Supports two mutually exclusive modes: paginated listing via an opaque page cursor, or batch… - POSTUploads a file that can be referenced by ID from subsequent Claude model requests.
/v1/:parent/publishers/:publishersId/filesUploads a file that can be referenced by ID from subsequent Claude model requests.
projects.locations.publishers.v1
- POSTForwards arbitrary HTTP requests for both streaming and non-streaming cases
/v1/:endpoint/v1/responses?deployedModelId=stringForwards arbitrary HTTP requests for both streaming and non-streaming cases. To use this method, invoke_route_prefix must be set to allow the paths that will…
projects.locations.publishers.v1.responses
- POSTForwards arbitrary HTTP requests for both streaming and non-streaming cases
/v1/:endpoint/v1/responses/compact?deployedModelId=stringForwards arbitrary HTTP requests for both streaming and non-streaming cases. To use this method, invoke_route_prefix must be set to allow the paths that will…
projects.locations.ragCorpora
- GETLists RagCorpora in a Location.
/v1/:parent/ragCorpora?pageSize=0&pageToken=stringLists RagCorpora in a Location. - POSTCreates a RagCorpus.
/v1/:parent/ragCorporaCreates a RagCorpus.
projects.locations.ragCorpora.ragFiles
- POSTImport files from Google Cloud Storage or Google Drive into a RagCorpus.
/v1/:parent/ragFiles:importImport files from Google Cloud Storage or Google Drive into a RagCorpus. - GETLists RagFiles in a RagCorpus.
/v1/:parent/ragFiles?pageSize=0&pageToken=stringLists RagFiles in a RagCorpus.
reasoningEngines.runtimeRevisions
- POSTQueries using a reasoning engine.
/v1/:name:queryQueries using a reasoning engine. - POSTStreams queries using a reasoning engine.
/v1/:name:streamQueryStreams queries using a reasoning engine.
reasoningEngines.sandboxEnvironmentSnapshots
- GETLists SandboxEnvironmentSnapshots in a given reasoning engine.
/v1/:parent/sandboxEnvironmentSnapshots?filter=string&pageSize=0&pageToken=stringLists SandboxEnvironmentSnapshots in a given reasoning engine.
reasoningEngines.sandboxEnvironmentTemplates
- GETLists SandboxEnvironmentTemplates in a given reasoning engine.
/v1/:parent/sandboxEnvironmentTemplates?filter=string&pageSize=0&pageToken=stringLists SandboxEnvironmentTemplates in a given reasoning engine. - POSTCreates a SandboxEnvironmentTemplate in a given reasoning engine.
/v1/:parent/sandboxEnvironmentTemplatesCreates a SandboxEnvironmentTemplate in a given reasoning engine.
projects.locations.reasoningEngines.sessions
- POSTAppends an event to a given session.
/v1/:name:appendEventAppends an event to a given session. - POSTCompacts the event history of a given Session, which may run an LLM summarization call and rewrite the full event…
/v1/:name:compactCompacts the event history of a given Session, which may run an LLM summarization call and rewrite the full event history. Compaction is a storage-side… - GETLists Sessions in a given reasoning engine.
/v1/:parent/sessions?filter=string&orderBy=string&pageSize=0&pageToken=stringLists Sessions in a given reasoning engine. - POSTCreates a new Session.
/v1/:parent/sessions?sessionId=stringCreates a new Session.
projects.locations.reasoningEngines.sessions.events
- GETLists Events in a given session.
/v1/:parent/events?filter=string&orderBy=string&pageSize=0&pageToken=stringLists Events in a given session.
projects.locations.schedules
- GETLists Schedules in a Location.
/v1/:parent/schedules?filter=string&orderBy=string&pageSize=0&pageToken=stringLists Schedules in a Location. - POSTCreates a Schedule.
/v1/:parent/schedulesCreates a Schedule.
projects.locations.semanticGovernancePolicies
- GETLists SemanticGovernancePolicies in a given location.
/v1/:parent/semanticGovernancePolicies?pageSize=0&pageToken=stringLists SemanticGovernancePolicies in a given location. - POSTCreates a SemanticGovernancePolicy.
/v1/:parent/semanticGovernancePolicies?semanticGovernancePolicyId=stringCreates a SemanticGovernancePolicy.
projects.locations.semanticGovernancePolicyEngine
- POSTDeprovisions the SemanticGovernancePolicyEngine, tearing down the associated tenant project, GKE cluster, and PSC…
/v1/:name:deprovisionDeprovisions the SemanticGovernancePolicyEngine, tearing down the associated tenant project, GKE cluster, and PSC service attachments. This operation is…
projects.locations.servingProfiles
- GETLists ServingProfiles in a Location.
/v1/:parent/servingProfiles?pageSize=0&pageToken=stringLists ServingProfiles in a Location. - POSTCreates a ServingProfile.
/v1/:parent/servingProfiles?servingProfileId=stringCreates a ServingProfile.
projects.locations.specialistPools
- GETLists SpecialistPools in a Location.
/v1/:parent/specialistPools?pageSize=0&pageToken=string&readMask=stringLists SpecialistPools in a Location. - POSTCreates a SpecialistPool.
/v1/:parent/specialistPoolsCreates a SpecialistPool.
projects.locations.studies
- GETLists all the studies in a region for an associated project.
/v1/:parent/studies?pageSize=0&pageToken=stringLists all the studies in a region for an associated project. - POSTCreates a Study
/v1/:parent/studiesCreates a Study. A resource name will be generated after creation of the Study. - POSTLooks a study up using the user-defined display_name field instead of the fully qualified resource name.
/v1/:parent/studies:lookupLooks a study up using the user-defined display_name field instead of the fully qualified resource name.
projects.locations.tensorboards
- GETReads multiple TensorboardTimeSeries' data
/v1/:tensorboard:batchRead?timeSeries=stringReads multiple TensorboardTimeSeries' data. The data point number limit is 1000 for scalars, 100 for tensors and blob references. If the number of data points… - GETLists Tensorboards in a Location.
/v1/:parent/tensorboards?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists Tensorboards in a Location. - POSTCreates a Tensorboard.
/v1/:parent/tensorboardsCreates a Tensorboard. - GETReturns the storage size for a given TensorBoard instance.
/v1/:tensorboard:readSizeReturns the storage size for a given TensorBoard instance. - GETReturns a list of monthly active users for a given TensorBoard instance.
/v1/:tensorboard:readUsageReturns a list of monthly active users for a given TensorBoard instance.
projects.locations.tensorboards.experiments
- POSTBatch create TensorboardTimeSeries that belong to a TensorboardExperiment.
/v1/:parent:batchCreateBatch create TensorboardTimeSeries that belong to a TensorboardExperiment. - GETLists TensorboardExperiments in a Location.
/v1/:parent/experiments?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists TensorboardExperiments in a Location. - POSTCreates a TensorboardExperiment.
/v1/:parent/experiments?tensorboardExperimentId=stringCreates a TensorboardExperiment. - POSTWrite time series data points of multiple TensorboardTimeSeries in multiple TensorboardRun's
/v1/:tensorboardExperiment:writeWrite time series data points of multiple TensorboardTimeSeries in multiple TensorboardRun's. If any data fail to be ingested, an error is returned.
projects.locations.tensorboards.experiments.runs
- POSTBatch create TensorboardRuns.
/v1/:parent/runs:batchCreateBatch create TensorboardRuns. - GETLists TensorboardRuns in a Location.
/v1/:parent/runs?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists TensorboardRuns in a Location. - POSTCreates a TensorboardRun.
/v1/:parent/runs?tensorboardRunId=stringCreates a TensorboardRun. - POSTWrite time series data points into multiple TensorboardTimeSeries under a TensorboardRun
/v1/:tensorboardRun:writeWrite time series data points into multiple TensorboardTimeSeries under a TensorboardRun. If any data fail to be ingested, an error is returned.
projects.locations.tensorboards.experiments.runs.timeSeries
- GETLists TensorboardTimeSeries in a Location.
/v1/:parent/timeSeries?filter=string&orderBy=string&pageSize=0&pageToken=string&readMask=stringLists TensorboardTimeSeries in a Location. - POSTCreates a TensorboardTimeSeries.
/v1/:parent/timeSeries?tensorboardTimeSeriesId=stringCreates a TensorboardTimeSeries. - POSTExports a TensorboardTimeSeries' data
/v1/:tensorboardTimeSeries:exportTensorboardTimeSeriesExports a TensorboardTimeSeries' data. Data is returned in paginated responses. - GETReads a TensorboardTimeSeries' data
/v1/:tensorboardTimeSeries:read?filter=string&maxDataPoints=0Reads a TensorboardTimeSeries' data. By default, if the number of data points stored is less than 1000, all data is returned. Otherwise, 1000 data points is… - GETGets bytes of TensorboardBlobs
/v1/:timeSeries:readBlobData?blobIds=stringGets bytes of TensorboardBlobs. This is to allow reading blob data stored in consumer project's Cloud Storage bucket without users having to obtain Cloud…
projects.locations.trainingPipelines
- GETLists TrainingPipelines in a Location.
/v1/:parent/trainingPipelines?filter=string&pageSize=0&pageToken=string&readMask=stringLists TrainingPipelines in a Location. - POSTCreates a TrainingPipeline
/v1/:parent/trainingPipelinesCreates a TrainingPipeline. A created TrainingPipeline right away will be attempted to be run.
projects.locations.tuningJobs
- GETLists tuning jobs in a location.
/v1/:parent/tuningJobs?filter=string&pageSize=0&pageToken=stringLists tuning jobs in a location. - POSTCreates a tuning job
/v1/:parent/tuningJobsCreates a tuning job. A created tuning job will be subsequently executed to start the model tuning process. - POSTRebase a tuned model
/v1/:parent/tuningJobs:rebaseTunedModelRebase a tuned model. A rebase operation takes a model that was previously tuned on a base model version, and retunes it on a new base model version. The…
v1
- POSTEvaluates a dataset based on a set of given metrics.
/v1:evaluateDatasetEvaluates a dataset based on a set of given metrics. - POSTEvaluates instances based on a given metric.
/v1:evaluateInstancesEvaluates instances based on a given metric. - POSTGenerates rubrics for a given prompt
/v1:generateInstanceRubricsGenerates rubrics for a given prompt. A rubric represents a single testable criterion for evaluation. One input prompt could have multiple rubrics This RPC…
API details
- Base URL
https://aiplatform.googleapis.com- Authentication
- OAuth 2.0 (authorization code flow) with 5 scopes
An API key in the key query parameter - Operations
- 284 operations on 225 pathsPOST 190GET 91DELETE 2PATCH 1
- Main resources
- projects.locations 13projects.locations.endpoints 9projects.locations.models 9projects.locations.featurestores.entityTypes 8projects.locations.studies.trials 8projects.locations.featureOnlineStores.featureViews 7projects.locations.indexEndpoints 7projects.locations.metadataStores.contexts 7projects.locations.reasoningEngines.memories 7publishers.models 7
- Response formats
application/json- Description format
- Google API Discovery, API version
v1 - Links
- Documentation · OpenAPI document
- Listed from
- Google API Discovery document (googleapis/discovery-artifact-manager) (Apache-2.0)
How to test the Agent Platform API in Swastik Codes
- Open the APISelect “Fork & run in Swastik Codes” on this page. Sign in or create a free account if asked.
- Fork it into your workspaceChoose a workspace. You get your own copy of the Agent Platform API collection, without the publisher's secrets.
- Add your credentialsThis API uses OAuth 2.0 (authorization code flow) with 5 scopes. Add yours in the collection's variables or an environment; the requests already reference it.
- Send a requestPick an endpoint, for example “Lists BatchPredictionJobs in a Location.” (GET /v1/batchPredictionJobs?filter=string&pageSize=0&pageToken=string&parent=string&readMask=string), and press Send. Check the response, add tests and run the whole collection with the runner.
Frequently asked questions
What is the Agent Platform API?
Build, scale, govern, and optimize sophisticated agents and models. It is listed under Developer tools and has 284 endpoints.
Who publishes the Agent Platform API?
It is listed from Google's public API description (an OpenAPI document), not published by Google on Swastik Codes. Anyone who controls googleapis.com can claim the profile by adding a DNS TXT record.
What is the base URL of the Agent Platform API?
Requests go to https://aiplatform.googleapis.com. Endpoint paths are added to this base URL.
How do I authenticate with the Agent Platform API?
It accepts 2 methods: OAuth 2.0 (authorization code flow) with 5 scopes; an API key in the key query parameter.
How many endpoints does the Agent Platform API have?
284 operations on 225 paths (190 POST, 91 GET, 2 DELETE, 1 PATCH). The largest groups are projects.locations, projects.locations.endpoints, projects.locations.models, projects.locations.featurestores.entityTypes.
Is forking the Agent Platform API free?
Yes. Forking copies the collection into your workspace for free. It has been starred 0 times and forked 0 times.