Tutorials: Chat

If you are used to using the ChatGPT or Claude chat interfaces, you might think that these models have incredible memories, able to maintain knowledge of the conversation across multiple interactions. You're being tricked. The reality is that LLMs like Claude's have no inherent memory between calls. Each API request is stateless by design. When

Real-time language translation has become essential for global applications, communities, and businesses to break down language barriers and foster inclusive environments. In this article, I’ll explain how to implement real-time language translation in Stream applications using large language models (LLMs). By the end, you will understand how to: Authenticate users using a Stream token. Create

AI chatbots have become a familiar feature in many modern applications. Yet, practical questions remain: “How should we integrate a chatbot into our service?” To explore this question, I launched an experimental project: a sommelier chatbot. Wine is a domain rich with variety and unfamiliar terms—perfect for testing how helpful an AI assistant can be

Hiring the right candidate and finding the perfect job can be challenging. Recruiters need an efficient way to manage job postings, screen applicants, and conduct virtual interviews—all in one platform. In this tutorial, you will learn how to build a job application and interviewing platform using Next.js, Stream, and Firebase. This app will allow recruiters

An interesting quirk of large language models (LLMs) is that they aren’t all the same. ChatGPT tends to be better for analysis, but in the words of Paul Graham, “writes like a kid doing an assignment.” Claude is a much better writer but loves a little bit of hallucination. All other models have their strong

In our previous article, we discussed setting up your stream chat application with advanced search features using Elasticsearch. In this article, we will combine this power tool with visualization software to enhance our chat application’s features and capabilities. (Note: This guide assumes some familiarity with Node.js, Docker, and basic command-line usage.) Combining Stream Chat, Elasticsearch,

Large Language Models, although trained on large amounts of data, have limited domain-specific knowledge. This limitation makes them less effective for customer support chatbots or similar apps that require specific data. Retrieval Augmented Generation (RAG) solves this concern by allowing LLMs access to external knowledge sources for a more accurate response generation. This means that

Note: This article assumes you have basic Node.js knowledge and are comfortable with environment variables. The code snippets in this article were run on a Windows OS. This GitHub repo contains all the files used in this article. Recently, applications or websites have been built with some form of chat. Whether it is through social