Documentation Index
Fetch the complete index at:https://docs.recombee.com/llms.txt
Use this file to discover all available pages before exploring further.
Other Resources
To see a complete guide for AI assistants carrying out a Recombee integration, go to:https://docs.recombee.com/ai_assistant_guide.md
To access the entire documentation in a single Markdown file, go to:https://docs.recombee.com/llms-full.txt
Every page has a Markdown twin: append .md to its URL (for example https://docs.recombee.com/getting_started.md), or request the normal URL with the header Accept: text/markdown.

Visit recombee.com Start Free

Learn
Integrate
Configure
Measure & Optimize
API Reference

Learn

Learn
Concepts & Glossary

Concepts & Glossary

This page describes the basic terminology that is used across this documentation.

Catalog: A list of entities (Users or Items) along with their properties.

Items: The content, products, or other entities that Recombee recommends or returns in search results.

Item Properties: Attributes that describe Items, such as title, category, price, availability, or publication date.

Users: Users who interact with Items and get recommendations.

User Properties: Optional attributes that describe Users, such as language, country, or subscription type.

Series: Ordered collections of Items, used mainly in the video domain to represent shows, seasons, and episodes.

Interactions: Events that record how Users engage with Items, such as views, purchases, ratings, or bookmarks.

recommId: A unique identifier of a recommendation request, used to attribute subsequent Interactions to the recommendation that caused them.

Scenario: A specific place on a website, in an application, or in an email where recommendations or search results are presented. Each Scenario can be configured to match the intended behavior for the use case.

Logic: The recommendation model ensemble used to compute recommendations or search results in a Scenario.

Business Rules: Rules that adapt recommendation results to business requirements.

Filters: Rules that determine which Items can appear in the results.

Boosters: Rules that make the recommender prefer some Items over others.

Constraint: A rule that controls how frequently Items sharing a condition can appear in recommendation results.

ReQL: Recombee Query Language, used to create custom Filters, Boosters, and advanced Item Segmentations.

Item Segmentation: A way to group Items into Segments based on their properties. The Segments can then be used to recommend the top categories, genres, artists, or a personalized ordering of homepage sections to users and can also be used in analytics.

Insights: Analytics in the Recombee Admin UI for exploring recommendation and Interaction data.

SDKs: Lightweight client libraries for integrating the Recombee API in various server-side and client-side programming languages.

Widget SDKs: Customizable components for adding Recombee recommendations and search to JavaScript or React applications.

No-Code Widgets: Recommendation and search components created in a visual editor in the Recombee Admin UI and added to a website using an embed code.

Getting Started

© Copyright 2026, Recombee s.r.o

docs.recombee.com

On this page

Catalog
Items
Item Properties
Users
User Properties
Series
Interactions
recommId
Scenario
Logic
Business Rules
Filters
Boosters
Constraint
ReQL
Item Segmentation
Insights
SDKs
Widget SDKs
No-Code Widgets