SmartFAQs.ai
Back to Learn
Intermediate

Manhattan Distance

A similarity metric, also known as L1 norm, that calculates the distance between two high-dimensional vectors by summing the absolute differences of their coordinates. In RAG pipelines, it serves as an alternative to Euclidean distance for vector retrieval, often providing more robust performance in high-dimensional spaces where individual feature axes have independent significance.

Definition

A similarity metric, also known as L1 norm, that calculates the distance between two high-dimensional vectors by summing the absolute differences of their coordinates. In RAG pipelines, it serves as an alternative to Euclidean distance for vector retrieval, often providing more robust performance in high-dimensional spaces where individual feature axes have independent significance.

Disambiguation

Measures distance along a grid (taxicab geometry) rather than 'as the crow flies' (Euclidean) or by angle (Cosine).

Visual Metaphor

"A taxi driver navigating a strictly rectangular city grid where diagonal shortcuts are impossible, forcing travel only along horizontal and vertical streets."

Key Tools
FaissPineconeMilvusscikit-learnWeaviate
Related Connections

Conceptual Overview

A similarity metric, also known as L1 norm, that calculates the distance between two high-dimensional vectors by summing the absolute differences of their coordinates. In RAG pipelines, it serves as an alternative to Euclidean distance for vector retrieval, often providing more robust performance in high-dimensional spaces where individual feature axes have independent significance.

Disambiguation

Measures distance along a grid (taxicab geometry) rather than 'as the crow flies' (Euclidean) or by angle (Cosine).

Visual Analog

A taxi driver navigating a strictly rectangular city grid where diagonal shortcuts are impossible, forcing travel only along horizontal and vertical streets.

Related Articles