While we can’t eliminate hallucinations entirely, there are still things we can do to reduce the chances of hallucinations showing up in our model’s responses.
In this post, we will build a real-time FAQ chatbot for a tax management SaaS using Gemini 2.5 Flash and NestJS with Server-Sent Events (SSE) to stream replies to the user. You'll learn how to set up Gemini and understand how context caching works.
Agentic workflows provide dynamic ways to interact with and analyze documents. The Telerik Document Processing Libraries now have these AI tools ready to use!
We often describe AI models as “thinking,” but what is actually happening when an AI model “thinks”? When it’s drafting a response to us, how does it know what to say?