Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Centroid Clustering for Vector Search
Learn how to accelerate semantic vector search by pre‑clustering embeddings with k‑means centroids, then narrowing queries to relevant clusters for faster matching.
Vector search is a powerful tool for semantic natural language search, but it can be computationally intensive and slow to run on some platforms. In this demo I will show how k-means clustering similar to that used in FAISS to speed up your own vector search implementation regardless of platform. This works by pre-clustering your vectors into groups with a central vector point and searching these groups based on the central vector match score with the user query.
Vector search engine for federal grants, powered by GPT-4o-mini.