Blogs›Qdrant›Relevance Score Boosting and Decay Functions
Qdrant enhances its relevance scoring capabilities by detailing the implementation and usage of decay functions (Linear, Exponential, Gaussian) within its score boosting functionality. These functions allow numeric payload fields or similarity scores to influence search relevance by transforming values into a 0.0-1.0 scale based on a target value and decay parameters (scale, midpoint). The post provides examples for use cases like time-based relevance, distance-based relevance, and price sensitivity. Version 1.17 introduces Relevance Feedback Query, a scalable, vector-native approach to incorporating relevance feedback by using lightweight feedback on a few top results to create context pairs of more- and less-relevant examples. These pairs adjust the scoring function during the next retrieval pass by modifying how similarity is computed, leading to improved recall without retraining models. Weighted Reciprocal Rank Fusion (RRF) is also introduced to allow assigning weights to different rankers.
2/20/2026
Introduced Relevance Feedback Query, a new method to improve search result quality by incorporating user feedback on result relevance. This feature uses context pairs of positive and negative examples to adjust the scoring function during retrieval, enhancing recall without retraining models. Also introduced Weighted Reciprocal Rank Fusion (RRF) to allow assigning weights to different rankers in hybrid search.
9/1/2025
This post introduces and explains Qdrant's Linear, Exponential, and Gaussian decay functions for score boosting. It details the purpose of these functions in transforming numeric properties into relevance scores, defines the parameters (x, target, scale, midpoint) and their roles, and provides practical examples for their application. It also addresses the limitation of not being able to dynamically set decay parameters for score normalization when input ranges are unknown.