Photo credit AI feels magical right now, and it is moving fast with new frameworks every week, new patterns every month. And there is a lot of noise about agents specifically, including some mixed signals. From "agents are just LLM wrappers", to "agents are fully autonomous," and "agents will replace everything", none of it is particularly useful when you are trying to build something real. The magic looks good on paper until it meets real systems.

Photo credit I’ve been working with a Goodreads book dataset for a while now, and my next goal was to generate vector embeddings for 2.3 million book descriptions using Neo4j’s new Cypher AI procedures and a local Ollama model. I figured it’d be pretty straightforward - set up the config, write a query, let it run. What could go wrong? Turns out…​quite a bit. What I expected to be a few query tweaks turned into a multi-step adventure through configuration quirks, batching strategies, query optimization, and a crash course in how tokens actually work.

Photo credit When text-to-query approaches (specifically, text2cypher) first entered the scene, I was a bit uncertain how it was useful, especially when existing models were hit-or-miss on result accuracy. It would be hard to justify the benefits over a human expert in the domain and query language. However, as technologies have evolved over the last couple of years, I’ve started to see how a text-to-query approach adds flexibility to rigid applications that could previously only answer a set of pre-defined questions with limited parameters.