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 list of recommended `Documents` in the `results` field, along with an `attributionToken` for tracking model performance and a list of `missingIds` for any requested documents that could not be found."],["The `RecommendationResult` provides details for each recommended document, including its `id`, the `document` itself (if requested), and `metadata` such as a recommendation `score`."],["The `attributionToken` is crucial for accurate tracking of the recommendation model's performance, and should be included in the `UserEvent` logs."],["The `validateOnly` field in the response indicates whether the `validate_only` parameter in the `RecommendRequest` was set."],["The `metadata` field within `RecommendationResult` may contain additional document annotations, and most notably, a `score` representing the recommendation's quality if requested."]]],[]]
