Stay organized with collections
Save and categorize content based on your preferences.
Full name: projects.locations.featureOnlineStores.featureViews.streamingFetchFeatureValues
Bidirectional streaming RPC to fetch feature values under a FeatureView. Requests may not have a one-to-one mapping to responses and responses may be returned out-of-order to reduce latency.
Endpoint
post
https://{service-endpoint}/v1beta1/{featureView}:streamingFetchFeatureValues
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-06-27 UTC."],[],[],null,["# Method: featureViews.streamingFetchFeatureValues\n\n**Full name**: projects.locations.featureOnlineStores.featureViews.streamingFetchFeatureValues\n\nBidirectional streaming RPC to fetch feature values under a FeatureView. Requests may not have a one-to-one mapping to responses and responses may be returned out-of-order to reduce latency. \n\n### Endpoint\n\npost `https:``/``/{service-endpoint}``/v1beta1``/{featureView}:streamingFetchFeatureValues` \nWhere `{service-endpoint}` is one of the [supported service endpoints](/vertex-ai/docs/reference/rest#rest_endpoints).\n\n### Path parameters\n\n`featureView` `string` \nRequired. FeatureView resource format `projects/{project}/locations/{location}/featureOnlineStores/{featureOnlineStore}/featureViews/{featureView}`\n\n### Request body\n\nThe request body contains data with the following structure:\nFields `dataKeys[]` `object (`[FeatureViewDataKey](/vertex-ai/docs/reference/rest/v1beta1/FeatureViewDataKey)`)` \n`dataFormat` `enum (`[FeatureViewDataFormat](/vertex-ai/docs/reference/rest/v1beta1/FeatureViewDataFormat)`)` \nSpecify response data format. If not set, keyvalue format will be used. \n\n### Response body\n\nResponse message for [FeatureOnlineStoreService.StreamingFetchFeatureValues](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.featureOnlineStores.featureViews/streamingFetchFeatureValues#google.cloud.aiplatform.v1beta1.FeatureOnlineStoreService.StreamingFetchFeatureValues).\n\nIf successful, the response body contains data with the following structure:\nFields `status` `object (`[Status](/vertex-ai/docs/reference/rest/Shared.Types/ListOperationsResponse#Status)`)` \nResponse status. If OK, then [StreamingFetchFeatureValuesResponse.data](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.featureOnlineStores.featureViews/streamingFetchFeatureValues#body.StreamingFetchFeatureValuesResponse.FIELDS.data) will be populated. Otherwise [StreamingFetchFeatureValuesResponse.data_keys_with_error](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.featureOnlineStores.featureViews/streamingFetchFeatureValues#body.StreamingFetchFeatureValuesResponse.FIELDS.data_keys_with_error) will be populated with the appropriate data keys. The error only applies to the listed data keys - the stream will remain open for further \\[FeatureOnlineStoreService.StreamingFetchFeatureValuesRequest\\]\\[\\] requests.\n`data[]` `object (`[FetchFeatureValuesResponse](/vertex-ai/docs/reference/rest/v1beta1/FetchFeatureValuesResponse)`)` \n`dataKeysWithError[]` `object (`[FeatureViewDataKey](/vertex-ai/docs/reference/rest/v1beta1/FeatureViewDataKey)`)`"]]