A list of recommended Documents. The order represents the ranking (from the most relevant Document to the least).
attributionToken
string
A unique attribution token. This should be included in the UserEvent logs resulting from this recommendation, which enables accurate attribution of recommendation model performance.
missingIds[]
string
IDs of documents in the request that were missing from the default Branch associated with the requested ServingConfig.
[[["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 2025-02-28 UTC."],[[["The `Recommend` method returns a response message containing a list of recommended documents (`results`), an attribution token (`attributionToken`), IDs of any missing documents (`missingIds`), and a boolean indicating if the request was for validation only (`validateOnly`)."],["Each recommended document in the `results` list is represented by a `RecommendationResult`, which includes the document's ID (`id`), the full document object (`document`) if requested, and additional metadata (`metadata`) like the recommendation score."],["The `attributionToken` is a unique identifier that should be logged in `UserEvent` logs to track and attribute the performance of the recommendation model."],["The `missingIds` field indicates which requested document IDs were not found in the default branch associated with the serving configuration."],["The metadata field can include additional information, such as the recommendation score, which is available if requested."]]],[]]