Get Verbose Item Recommendations
Retrieves item recommendations with detailed snippet metadata, including the full snippet text. Requires specifying a collection and tenant for the search.
Error Reference: Search & Recommendations
Authorizations
Body
Parameters for retrieving verbose item recommendations.
The prompt that the user enters into the application.
1The collection to search in.
1The minimum certainty threshold for snippets.
0 <= x <= 1Optional tenant to search. Required only when the selected collection is multi-tenant; invalid when the selected collection is not multi-tenant. Blank strings are normalized to no tenant.
A list of Publisher Names. Only publishers belonging to your organization are allowed.
1The maximum number of snippets to search through overall.
x >= 1The minimum number of snippets for an item to be returned.
x >= 1The type(s) of media for the items returned.
audio, video, book, article The maximum number of items to return. Items are ranked by cumulative certainty. If the available snippets span fewer items than this count, only those items are returned.
x >= 1Case-sensitive substring filters matched against each item's raw item_extra text. All entries must match (AND) for an item to be returned. Filtering is applied server-side, so paging operates on the filtered set. The wildcard characters * and ? are not permitted and return a 422 response.
The ordering applied to returned items. relevance ranks by cumulative certainty; publication_date orders by each item's best-effort parsed publication date, with items whose date is empty or unparseable always sorted last. publish_date is accepted as an alias for publication_date.
relevance, publication_date The sort direction, applied only when sort_by is publication_date. desc returns newest items first; asc returns oldest first.
asc, desc Response
Successful response returning a list of items with full snippet text.
The item's raw item_extra text. May be an empty string.

