Vector Database from Scratch What is it
This project is an end-to-end implementation of a vector database built from scratch, focusing on how modern similarity search systems work internally.
It starts with a simple brute-force exact nearest neighbor (ENN) approach and progressively evolves into more advanced techniques such as clustering-based indexing and approximate nearest neighbor (ANN) search.
The goal is to build a system that can store high-dimensional embeddings and efficiently retrieve the most similar vectors for a given query.