Skip to main content

Documentation Index

Fetch the complete documentation index at: https://86d.app/docs/llms.txt

Use this file to discover all available pages before exploring further.

The recommendations module surfaces products tailored to each shopper. With an LLM key configured (OPENAI_API_KEY, GEMINI_API_KEY, or OPENROUTER_API_KEY), recommendations use embeddings and the shopper’s recently-viewed and order history. Without a key, the module falls back to a rule-based recommender (shared category, shared tags, co-purchase frequency). Source: modules/recommendations · npm: @86d-app/recommendations

​
Installation

86d module add recommendations

​
Configuration

recommendations({
  provider: "openai",       // "openai" | "gemini" | "openrouter" | "rule-based"
  model: "gpt-4o-mini",
  cacheMinutes: "60",
});

​
Store endpoints

MethodPathDescription
GET/recommendations/for-product/:id”Customers also liked” for a product
GET/recommendations/for-customerPersonalized for the authenticated shopper
GET/recommendations/trendingTrending products globally

​
Components

  • <ProductRecommendations productId={id} />: drop on product detail pages.
  • <PersonalizedShelf />: home or account-page shelf.
  • <TrendingProducts />: editorial shelf.
  • Recently viewed: one of the inputs to personalization.
  • Search: shares the embeddings backend when both are configured.