Tutorials
New
Exploring Reasoning LLMs and Their Real-World Applications
LLMs have excelled in writing, coding, and problem-solving tasks and prompts based on the data sets they were trained with. However, these models fall short when used to solve complex puzzles because they respond with the information they were trained with and lack the ability to self-correct. Recent LLMs, like OpenAI's o1 models, have proven
Read more ->
12 min read
Building an NPX Script for Project Setup
Setting up a new project can be tedious and repetitive from multiple angles. As end-users, we are learning a new platform, new paradigms, and maybe a new framework to build our next dream project. As a company, we want to get our potential users up and running as quickly as possible and make it easy
Read more ->
9 min read
Using a Speech Language Model That Can Listen While Speaking
Traditional speech language models like Siri or Alexa use turn-taking as the primary interaction style. Although these systems can detect single human voices, they cannot be interrupted in real time. Let's discover an advanced AI speech dialogue system that integrates listening and speaking capabilities to engage in conversations in real time, allowing seamless to-and-fro communication
Read more ->
8 min read
Building In-App Notifications in Next.js
Wonder how apps keep users engaged with real-time in-app notifications? In-app notifications are a powerful tool for user retention and engagement. They keep users informed about important updates or activities, encourage users to return to the app regularly, and personalize the user experience based on individual preferences and behavior. However, implementing an effective in-app notification
Read more ->
8 min read
Using Prompt Engineering to Refine a Large Language Model for Content Moderation
In our previous blog post, we created an agent using OpenAI GPT that can understand whether or not messages contain spam. We connected it to the Stream Chat API so that incoming messages in chat can be automatically flagged and reviewed by moderators using Stream Moderation Dashboard. To enhance the accuracy of our agent and
Read more ->
16 min read
Build an LLM-Powered Agent for Real-Time Content Moderation
Maintaining a safe and engaging chat environment is crucial for any online community. In this post, we'll demonstrate the practical application of Large Language Models (LLMs) in content moderation, showcasing how advanced AI can enhance community interactions by effectively managing unwanted content. We’ll also introduce essential tools and guide you through setting up a real-time
Read more ->
12 min read
How To Secure a Vite-Powered React App With Seald End-to-End Encryption
When sending messages across a chat app, one way to ensure the data and conversations are not intercepted is to build proper security to shield people who use the app. This article dives into how to implement strong end-to-end (E2EE) encryption in your app to protect users. We will integrate Seald’s E2EE into Stream’s Chat
Read more ->
17 min read
Secure Data and Safeguard App Users With End-to-End Encryption
Have you ever wondered about the cost and wreaking havoc data breaches cause worldwide every year? Let’s look at how end-to-end encryption eliminates this concern. In securing web and mobile applications, developers generally use traditional methods such as Transport Layer Security (TLS), Encryption at Rest, Encryption in Transit, etc. Although these approaches are acceptable, the
Read more ->
7 min read