Python + AI: Retrieval Augmented Generation скачать в хорошем качестве

Python + AI: Retrieval Augmented Generation

In our third Python + AI session, we'll explore one of the most popular techniques used with LLMs: Retrieval Augmented Generation. RAG is an approach that sends context to the LLM so that it can provide well-grounded answers for a particular domain. The RAG approach can be used with many kinds of data sources like CSVs, webpages, documents, databases. In this session, we'll walk through RAG flows in Python, starting with a simple flow and culminating in a full-stack RAG application based on Azure AI Search. 📌 This session is a part of a series. Learn more here: https://aka.ms/PythonAI/2 Explore the slides and episode resources: https://aka.ms/pythonai/resources Check out the demos: https://aka.ms/python-openai-demos Chapters: 00:04 – Welcome & Housekeeping 01:02 – Introduction to the Python & AI Series 01:45 – What is Retrieval Augmented Generation (RAG)? 04:35 – Why RAG Matters: LLM Limitations 06:30 – Fine-Tuning vs. RAG: Cost & Practicality 08:06 – Real-World RAG Examples (Copilot, ChatGPT) 09:29 – RAG 101: How It Works 12:05 – Demo: Basic RAG with CSV & OpenAI 18:16 – Multi-Turn RAG for Conversational AI 20:44 – Query Rewriting for Better Search 25:16 – Ingesting PDFs for RAG 34:01 – RAG on Documents with Citations 37:11 – Adding Vector Search to Improve Results 40:10 – Hybrid Search: Keyword + Vector + Reranking 47:23 – End-to-End RAG with PostgreSQL 50:15 – End-to-End RAG with Azure AI Search 55:16 – Data Ingestion Pipeline with Azure Tools 58:40 – RAG App Architecture & Components 1:02:45 – Q&A: Flowcharts, Embeddings, Metadata 1:10:48 – Ensuring Reproducibility in RAG 1:14:15 – Optimizing Context & Cost in Azure AI Search 1:18:46 – Evaluating RAG Quality 1:21:17 – Summarizing Large PDFs with LLMs 1:22:45 – Cost-Saving Tips for Azure AI Search 1:25:00 – Bonus Demo: Voice RAG 1:26:00 – Wrap-Up & Next Steps #MicrosoftReactor #learnconnectbuild [eventID:26295]