Improve AI accuracy and reliability with RAG [Pt 3]

From the creator

Enhance your AI's accuracy and reliability with Retrieval Augmented Generation (RAG)! Learn how combining retrievers and generators provides precise, up-to-date answers using your own data. You'll see how using sourced data instead of relying on the model's training data can improve user trust, while also making your AI more grounded in the context you provide. Links: - Serverless AI chat demo: https://github.com/Azure-Samples/serverless-chat-langchainjs - Implement RAG training: https://learn.microsoft.com/training/modules/use-own-data-azure-openai/ - Create your AI chat with RAG workshop: https://aka.ms/ws/openai-rag-qdrant Watch this series' playlist: https://aka.ms/genai-js All slides and code samples: https://github.com/microsoft/generative-ai-with-javascript Chapters: 00:00 Introduction 00:10 Challenges with AI Outputs 00:36 Understanding Retrieval-Augmented Generation (RAG) 01:04 Benefits of RAG 01:53 How RAG Works 02:19 Implementation of RAG 03:50 Practical Example: Contonso Real Estate Company 05:32 Conclusion and Next Steps 👩‍💻👨‍💻 Great devs don’t build alone. ⏱️ In a fast-paced dev world, there’s no time to hunt for help. That’s why we created the Azure AI Foundry Developer Community — your one-stop hub for: 🌐 A vibrant forum for Q&A + code 🎙️ DevBlogs with the latest updates 🎮 Real-time Discord chats, events & learning 🔗 Azure AI Foundry Developer Forum: https://aka.ms/azureaifoundry/forum Azure AI Foundry Discord Server: https://aka.ms/azureaifoundry/discord

Published 2024-10-15 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.