Tutorials

JavaScript is the foundation of the modern web. Without it, you don’t have the rich interaction you expect from websites, like real-time updates, video, or chat. But JS brings a problem: bloat. Modern web apps often ship megabytes of JavaScript to the browser. This slows initial page load and hurts performance, especially for mobile devices.

Many people (especially developers) want to use the new DeepSeek R1 thinking model but are concerned about sending their data to DeepSeek. Read this article to learn how to use and run the DeepSeek R1 reasoning model locally and without the Internet or using a trusted hosting service. You run the model offline, so your

AI agent chats are mostly a 1:1 experience. But that misses a clear opportunity--having an AI member of your team. If every team member was participating in a chat with AI, you could collaborate as a group, create shared knowledge bases, or solve problems together more efficiently. So, let's build that. We're going to extend

Integrating AI into enterprise applications often challenges getting accurate and efficient results from LLMs. The main reason is that LLMs are trained on large datasets rather than specifically on your enterprise's data. These challenges may usually include hallucinations, outdated information presentation, and more. This article explores the integration of AI agents, or, Agentic Retrieval Augmented

In the previous article, we extended our API with endpoints to create and retrieve notes and integrated the new endpoints into the application. In this article, we will extend our application with full-stack functionality for editing and deleting notes. Editing Notes Adding the API Request Before creating the API, let's set up a dependency to

In the previous article, we extended our application with authentication and integrated it with the API. Now, will start building a note-taking application. We will focus on adding full-stack functionality for creating and viewing notes. Adding Dependencies Before building, let's add a few dependencies on the client side. Run the following command in a terminal

When dealing with internet video calls, many things can negatively impact call quality. Improving call quality when issues occur requires understanding how specific metrics impact your user’s experience. To help you better understand what is going on, Stream offers a comprehensive video statistics page on our dashboard. With our statistics dashboard, you can quickly inspect

In this post, we will see how to build a Python server allowing frontend chat SDKs to start and stop an AI agent for a channel in Stream Chat. Building polished AI assistants can be challenging. Features like streaming responses, table components, and code generation require complex implementation across SDKs and the backend. To ease