Recommenders
Create recommender
Create a new Spark recommender for a specific shop and product feed. Training starts automatically after creation.
POST
string
required
The shop (e-commerce platform) identifier. Max 64 characters, allowed characters: letters, digits,
., _, -.integer
required
The product feed ID to use for recommendations.
string
Optional human-readable name of the recommender. Max 191 characters.
string[]
Optional list of product identifiers (SKUs) to exclude from the recommendations. Max 1000 items, each unique and max 255 characters. Omit the field for no product filter.
string[]
Optional list of category names to exclude from the recommendations. Max 1000 items, each unique and max 255 characters. Omit the field for no category filter.
integer[]
Optional list of calendar month numbers (
1–12) that restrict which purchase history is used for training. Values must be unique, max 12 items. Omit the field to use the full purchase history.After creation the recommender status will be
created and training will start automatically in the background.
Each account can have at most 5 recommenders; creating a 6th returns a 422 error. Deleting a recommender never recycles its sequence_number.
This endpoint is rate limited to 2 requests per minute.