Welcome to part three of our series on using Temporal to improve the reliability of applications built around LLMs like the one that powers ChatGPT. In part one, you learned how to use Temporal to clone a repo and ingest its documentation into an RAG Database for use with your LLM. Part two taught you how to use context injection to give users more accurate answers to prompts made against that documentation. In this post, you’ll use Temporal and another LLM to automatically test the accuracy of your application’s answers to the prompts from part two.
Loading
One of the most impressive parts of a DoneJS application is Server Side Rendering (SSR). You can write your code once and it will render both on an SSR-enabled web server and in the browser. You’ve probably noticed, while building your DoneJS app, that it’s a generally seamless experience. However, you’ll eventually run into a situation where the code on the server doesn't execute the way you would expect. Let’s take a look at why that’s the case, then I’ll show you a neat little DoneJS utility that makes it easy to debug these situations when they appear.
Marshall Thompson
Developer