Automated Topical Authority Clustering Using Embeddings & Python

Group thousands of search keywords into distinct topical silos to prevent internal keyword cannibalization.

Prerequisites

Python
Pandas
OpenAI API key

Step 1: Step 1: Generating Semantic Vector Embeddings for Search Queries

Map your keyword CSV through text-embedding-3-small to project all queries into high-dimensional vector space.

Step 2: Step 2: HDBSCAN Density Clustering for Natural Pillars

Cluster the vectors with HDBSCAN to discover authentic semantic clusters without pre-specifying cluster counts.