{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/350eed0ce28c43e297ea78e6ede7d694\" frameborder=\"0\" width=\"1280\" height=\"960\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":960,"width":1280,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":960,"thumbnail_width":1280,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/350eed0ce28c43e297ea78e6ede7d694-1691250207409.gif","duration":497.376,"title":"DeepChat: A Modern Recommender System for Recipes 👨‍🍳","description":"Hi, my name is Amir, and I'm excited to talk about my project DeepChat, a modern recommender system for recipes. As a foodie, I often browse the internet for recipes I love and wanted to find similar ones more efficiently. To achieve this, I harnessed the power of state-of-the-art natural language processing and embedding models. In this video, I'll explain the steps I took, including scraping over 520,000 recipes, cleaning and enhancing the data, and using OpenAI's embedding models. I'll also demonstrate the app I created, DeepChef, where you can find similar recipes by simply copying and pasting the text. Join me on this journey to revolutionize recipe recommendations!"}