{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"The Scrimba Podcast","title":"What Is Retrieval-Augmented Generation and How to Make AI Work for You, with Guil Hernandez","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/d93a350a\"></iframe>","width":"100%","height":180,"duration":1585,"description":"🎙 About the episode\n\nMeet Guil Hernandez 🇺🇸! He is a developer and educator with over 15 years of experience in tech. He's also a Scrimba teacher who is a part of the team bringing you the AI Engineer Path, and in this episode, he's helping us understand retrieval-augmented generation.\nIn the previous episode, Tom Chant helped us understand the world of AI models. Today, Guil will further teach us how these models work under the hood. AI models don't understand the world like we do. When we interact with them, they turn our inputs into mathematical representations known as embeddings. By creating our own embeddings, we can teach AI to do what we want it to.\nToday, we're getting an introduction about making a model aware of your own data source so that that data can be considered for the AI output. For example, using the techniques you'll learn from Guil in this episode, you could connect a model to your customer support conversations so that the model knows what is necessary to answer unique questions about your (or your client's) business.\nThis is the third episode of our series on AI engineering, introducing Scrimba's AI Engineer Path. This path is your gateway to unlocking the full potential of AI for your projects. \n\n🔗 Connect with Guil\n🐦 Twitter\n🌐  Website\n👩‍🚀 Github\n⏰ Timestamps\nGuil focuses on RAG and embeddings (01:42)\nRAG makes a foundation model aware of your data (03:14)\nSpotify has been using RAG since 2014 (05:56)\nHow embedding works: embedding model + vector database + generative model (09:00)\nYou're enhancing content retrieved from a database with a generative model (10:26)\nA foundation model can't just understand text (10:34)\nWhat's a vector database? (12:35)\nCan we make an AI chatbot for the Scrimba podcast? (15:05)\nYou can chunk the files directly at OpenAI now! (16:49)\nOpenAI's Assistants API (17:33)\nAI is evolving quickly (19:07)\nAssistants API does RAG (19:55)\nWhat is fine-tuning? (20:39)\nDifferences between RAG and fine-tuning (21:14)...","thumbnail_url":"https://img.transistorcdn.com/3qNz-AxOjZ6Oiowf_zRLRsZeOxv5p7FYbB0-kA5vS6A/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9zaG93/LzE1Njg5LzE3MDE4/MDIzOTYtYXJ0d29y/ay5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}