Этот материал находится в платной подписке. Оформи премиум подписку и смотри или слушай RAG: Beyond Basics, а также все другие курсы, прямо сейчас!
Премиум
  1. Урок 1. 00:04:59
    What is RAG? Why we NEED it?
  2. Урок 2. 00:04:04
    Setting up Virtual Environment
  3. Урок 3. 00:03:52
    Setting Up API Keys
  4. Урок 4. 00:04:01
    Deep Dive into RAG Pipeline Structure
  5. Урок 5. 00:06:18
    Demystifying Embedding Models and Vector Storage
  6. Урок 6. 00:03:10
    Google Colab Setup
  7. Урок 7. 00:02:11
    End-to-End RAG Pipeline - Code Time
  8. Урок 8. 00:02:36
    Loading and Processing PDF Files
  9. Урок 9. 00:06:49
    How Chunking Works
  10. Урок 10. 00:02:07
    Focus on Parsing than Chunking
  11. Урок 11. 00:05:28
    Chunk Size as Function of Text Embedding Models
  12. Урок 12. 00:04:38
    The Retrieval in RAG
  13. Урок 13. 00:05:13
    Putting Everything Together - 1st Iteration of RAG
  14. Урок 14. 00:01:13
    RAG: Advanced Techniques
  15. Урок 15. 00:06:41
    Improving RAG with Re-ranking for Precise Information Retrieval - Part 1
  16. Урок 16. 00:07:32
    Re-Ranking with GPT-4, ColBERT, and Cohere
  17. Урок 17. 00:08:14
    Improving Information Retrieval with Query Expansion using LLMs
  18. Урок 18. 00:08:02
    Enhancing Search with Hypothetical Documents Embedding Technique
  19. Урок 19. 00:06:55
    Enhancing Document Retrieval with Ensemble Techniques
  20. Урок 20. 00:08:25
    Hierarchical Chunking - Exploring the Parent Document Retriever
  21. Урок 21. 00:12:05
    From Notebook to working Scripts
  22. Урок 22. 00:05:02
    Creating Streamlit UI App
  23. Урок 23. 00:04:43
    Private and local Chat with PDFs
  24. Урок 24. 00:03:58
    The Recap
  25. Урок 25. 00:09:31
    Contextual Retrieval - Adding Context to Your Chunks
  26. Урок 26. 00:09:26
    Contextual Retrieval - Implementation
  27. Урок 27. 00:13:35
    Multimodal RAG - Working with Images and Tables