SemanticFinder now offers an easier way of pre-indexing files. Just like in all ML-flows the embedding calculation is the computation-intense part, so if you do this beforehand and load it in your browser, calculating cosine similarity is trivial (for a few thousand iterations).<p>It has the nice side-effect that this also allows for external computation of embeddings where you might have faster hardware than you're client device.<p>One could add so many features like adding full-text search by checking if the index contains certain keywords.<p>GitHub: <a href="https://github.com/do-me/SemanticFinder">https://github.com/do-me/SemanticFinder</a><p>In a way, your browser can become the vector DB.