dasini.net – Diary of a MySQL expert

In this latest post, the final part of my series on building an AI-powered search engine with HeatWave GenAI, I dive into enhancing AI-powered search by embedding full article content into HeatWave.

By cleaning HTML, chunking content, generating embeddings, and running semantic similarity searches directly within HeatWave, we unlock highly relevant, context-rich search results.
If you’re building smart search engines or working with RAG pipelines, you’ll find practical tips and SQL-powered techniques you can apply right away.

This series demonstrates the powerful capabilities of HeatWave GenAI for building sophisticated, in-database AI-driven search solutions. Check out the article to level up your understanding of semantic search!

In this part 2 we focused on enhancing search relevance. We introduced reranking techniques using weighted distances of titles and excerpts to refine initial search results. Then we delved into leveraging article summaries for more effective semantic search, utilizing HeatWave’s capability to execute JavaScript stored procedures for sanitizing HTML content and generating these summaries. Finally, we demonstrated how to create embeddings from these summaries and perform similarity searches, showcasing HeatWave GenAI’s power for advanced information retrieval directly within the database.