{"version":"1.0","type":"rich","provider_name":"Acast","provider_url":"https://acast.com","height":250,"width":700,"html":"<iframe src=\"https://embed.acast.com/$/68a595f43b6c865497e10d7f/6ab25af2d00a4eacd510aa79?\" frameBorder=\"0\" width=\"700\" height=\"250\"></iframe>","title":"How RAG Works: Turn Internal Knowledge Into Better AI Answers","description":"<p>Your business already has the answers. The problem is that nobody can find them. But RAG (retrieval-augmented generation), can help with that.</p><p><br></p><p>In this week’s episode, Jess and Kyle unpack RAG — retrieval-augmented generation — the method that lets an AI model retrieve relevant information from a defined set of documents, databases or research before it generates an answer.</p><p><br></p><p>From product information and policies to research archives, client documentation and company knowledge, RAG can give an AI assistant the context it needs to answer questions using the information you have chosen.</p><p><br></p><p>They cover how RAG works, why it differs from fine-tuning, the role of chunking, embeddings, vector databases and citations (but don't be worried by the jargon!), and how to start with a smaller RAG project before building something more sophisticated.</p><p><br></p><p>They also discuss the biggest AI news story of the year, and the practical AI governance decisions businesses can make now.</p><p><br></p><p><strong>You’ll learn:</strong></p><p><br></p><p><br></p><ul><li>What RAG is and how retrieval-augmented generation works</li><li>The difference between RAG and AI fine-tuning</li><li>How AI retrieves relevant context from business documents and databases</li><li>Chunking, embeddings, vector databases, semantic search and citations — explained without the technical overload</li><li>Why current, well-structured documentation matters for reliable AI answers</li><li>Common RAG problems, including outdated information, duplicate documents and missing context</li><li>How to start with a smaller RAG project before building a more sophisticated AI knowledge base or internal AI assistant</li></ul><p><br></p><p><br></p><p>Nishma Patel Robb: <a href=\"https://www.linkedin.com/in/nishmapatelrobb/\" rel=\"noopener noreferrer\" target=\"_blank\">https://www.linkedin.com/in/nishmapatelrobb/</a></p><p><br></p><p>Timestamps:</p><p><br></p><p>00:43 What We've Been Up To This Week</p><p>03:29 What Is RAG (Retrieval Augmented Generation)</p><p>07:23 Why General Chatbots Get Your Business Wrong</p><p>10:03 How RAG Works Under the Hood</p><p>11:49 Chunking: How RAG Breaks Your Documents Into Pieces</p><p>12:59 Embeddings and the Vector Database, Explained</p><p>15:23 Citations: How RAG Shows Its Sources</p><p>16:13 RAG vs Fine-Tuning: What's the Difference</p><p>18:25 Real-World RAG: Onboarding and Shared Team Knowledge</p><p>23:06 Real-World RAG: Making a News Archive Searchable</p><p>30:18 Optimizing Onboarding Processes with AI</p><p>30:54 Why RAG Is Really a Documentation Problem</p><p>31:30 The Importance of Documentation in RAG Systems</p><p>33:22 Creating a Single Source of Truth</p><p>34:51 Ensuring Consistency in Data</p><p>36:23 Understanding AI Limitations and Hallucinations: RAG Failure Modes</p><p>40:34 How RAG Handles Conflicting Documents and Version Control</p><p>43:30 Abstention: Why RAG Should Admit It Doesn't Know</p><p>44:59 How to Build a Simple RAG With Claude, ChatGPT or NotebookLM</p><p>48:24 Scaling RAG Systems for Larger Teams</p><p>49:25 Takeaways</p><p>51:03 AI News: Dario Amodei on Slowing the AI Frontier</p><p><br></p><p><strong>Resources:</strong></p><p><br></p><ul><li><a href=\"https://towardsdatascience.com/the-ultimate-guide-to-rags-each-component-dissected-3cd51c4c0212/\" rel=\"noopener noreferrer\" target=\"_blank\">https://towardsdatascience.com/the-ultimate-guide-to-rags-each-component-dissected-3cd51c4c0212/</a></li><li><a href=\"https://bytevagabond.com/post/how-to-build-enterprise-ai-rag/\" rel=\"noopener noreferrer\" target=\"_blank\">https://bytevagabond.com/post/how-to-build-enterprise-ai-rag/</a></li><li><a href=\"https://medium.com/aingineer/a-complete-guide-to-implementing-hybrid-rag-86c0febba474\" rel=\"noopener noreferrer\" target=\"_blank\">https://medium.com/aingineer/a-complete-guide-to-implementing-hybrid-rag-86c0febba474</a></li><li><a href=\"https://arxiv.org/html/2403.01432v3\" rel=\"noopener noreferrer\" target=\"_blank\">https://arxiv.org/html/2403.01432v3</a></li><li><a href=\"https://www.ibm.com/think/topics/multimodal-rag\" rel=\"noopener noreferrer\" target=\"_blank\">https://www.ibm.com/think/topics/multimodal-rag</a></li><li><a href=\"https://memgraph.com/blog/what-is-rag\" rel=\"noopener noreferrer\" target=\"_blank\">https://memgraph.com/blog/what-is-rag</a></li></ul><p><br></p><p>Get in Touch</p><p><a href=\"mailto:hello@earlyadoptr.ai\" rel=\"noopener noreferrer\" target=\"_blank\">hello@earlyadoptr.ai</a></p><p>TikTok: @early_adoptr</p><p>Instagram: @early_adoptr</p><p>YouTube: @early_adoptr</p><p>LinkedIn: <a href=\"https://www.linkedin.com/company/early-adoptr/\" rel=\"noopener noreferrer\" target=\"_blank\">https://www.linkedin.com/company/early-adoptr/</a></p><p><a href=\"https://open.acast.com/networks/6893a474b5f8d99f359a9350/shows/68a595f43b6c865497e10d7f/episodes/www.earlyadoptr.ai\" rel=\"noopener noreferrer\" target=\"_blank\">www.earlyadoptr.ai </a></p>","author_name":"Early Adoptr"}