Это пробный урок. Оформите подписку, чтобы получить доступ ко всем материалам курса. Премиум

  1. Урок 1. 00:03:13
    01 Intro to Real World RAG
  2. Урок 2. 00:04:07
    02 Real World RAG Use-Cases from Top Companies
  3. Урок 3. 00:05:58
    03 How RAG Works - A High Level Overview
  4. Урок 4. 00:13:37
    04 Project Setup and Vibe Coding the Chat UI
  5. Урок 5. 00:10:43
    05 Gather and Clean Documents For Embedding
  6. Урок 6. 00:06:03
    06 Open Source Alternatives to Llama Parse
  7. Урок 7. 00:04:35
    07 All About Chunking for RAG
  8. Урок 8. 00:16:17
    08 Chunk the MDN Docs for our Project
  9. Урок 9. 00:05:15
    09 Compare Embedding Models for RAG
  10. Урок 10. 00:03:19
    010 Compare Vector Databases for RAG
  11. Урок 11. 00:12:02
    011 Use AI Agent to Setup a Postgres Database and Drizzle
  12. Урок 12. 00:14:21
    012 Update the Database Schema for Documents and Chunks
  13. Урок 13. 00:09:05
    013 Use AI Agent to Create Database Seed to Store Documents
  14. Урок 14. 00:14:44
    014 Create Embeddings and Store in a Vector Database
  15. Урок 15. 00:05:52
    015 Retrieve Semantically Related Content
  16. Урок 16. 00:06:18
    016 What is Cosine Similarity and Top-K in RAG
  17. Урок 17. 00:16:02
    017 Augment Generative AI Input with Related Content
  18. Урок 18. 00:08:31
    018 Documenting RAG App Scripts and Service Functionality
  19. Урок 19. 00:13:25
    019 Hook up the RAG Pipeline to the Web App