Note: The feature previously known as AI Search is now referred to as AI Semantic Search. This update reflects a shift to a large language model (LLM)-based system.
The information in this document remains accurate for both AI Semantic Search and the earlier AI Search RNN (legacy) version. If your implementation still uses the RNN-based model, you can continue to rely on the details provided here. Functionally, the concepts and integrations described have not changed.

Fredhopper AI Semantic Search is designed to enhance your on-site search experience by delivering relevant results even when customer queries don’t align directly with product data. It is not intended to replace your standard search configuration, but to complement it. AI Semantic Search steps in where standard methods alone may not suffice.

Why use AI Semantic Search?

Fredhopper’s standard search is robust and highly configurable, returning accurate results based on structured product attributes. However, some customer queries, especially long or imprecise ones, may not yield ideal results through traditional methods alone. AI Semantic Search fills this gap.

Key Benefits

• Reduction of zero-result pages: AI Semantic Search activates when traditional search methods return no or very few results, helping ensure customers always see relevant items.

• Optimization based on customer behavior: The system connects past search terms with the items users clicked on, learning what customers actually want.

• Support of multiple languages: The model is trained per language, ensuring accurate behavior in international and multilingual contexts.

• Coverage of long-tail searches: AI search excels at interpreting complex or uncommon queries that don’t directly map to product attributes, improving search coverage for niche or detailed requests.

Example

Consider a customer who searches for “Dress shirt for a summer wedding”.

Standard search might match on “dress shirt” but could miss important contextual keywords like “summer” or “wedding” if these aren’t present in the product data. AI Semantic Search, by contrast, identifies patterns from previous searches and customer interactions to return appropriate items such as, light-colored linen shirts suitable for warm-weather events, even if these don't explicitly contain the search phrase.

Next Steps

To enable AI Semantic Search your catalog must align with the specifications outlined here.