Build App With GPT-4 (Vision), Using Clarifai Platform lablab-ai#420

tutorials/en/the-art-of-intelligent-browsing-mastering-selenium-with-gpt-vision-api.mdx

@@ -2,11 +2,19 @@
 title: "The Art of Intelligent Browsing: Mastering Selenium with GPT Vision API"
 description: "Dive into the world of automated web interactions and AI-powered analysis with our comprehensive tutorial. You'll learn how to build an Interactive Media App using Streamlit, Clarifai, and OpenAI's GPT Vision API. This guide covers everything from setting up your environment to integrating advanced AI for tasks such as image recognition, and text-to-speech, culminating in the creation of engaging, intelligent browsing experiences."
 authorUsername: "sanchayt743"
+image: "https://i.postimg.cc/G24VmT8G/Tutorial-image-template.png"
+
 ---
 # Build an App with GPT-4 (Vision) Using Clarifai Platform: A Beginner-Friendly Tutorial 🌟
 
 Welcome to the exciting world of GPT-4 Vision! I am Sanchay Thalnerkar and I will guide you through building an app with the remarkable capabilities of GPT-4's vision features, using the Clarifai platform. 🚀
 
+**For Visual Learners:**
+
+If you learn best through visual aids, I've got you covered! Check out the [companion video tutorial](https://youtu.be/GTK2pl93VJ0?si=udDrLQCMYVB4TKUN) where I walk you through each step of building the app. The video is a great way to see the concepts applied in real-time. 🎥
+
+---
+
 ## Introduction to GPT-4 Vision 👁️‍🗨️
 
 GPT-4, the latest iteration in OpenAI's series of models, has taken a giant leap by integrating vision capabilities. This means it can now process and understand visual information, like recognizing objects, interpreting scenes, and even deciphering text within images.