Этот материал находится в платной подписке. Оформи премиум подписку и смотри или слушай Developing LLM Apps with LangChain, а также все другие курсы, прямо сейчас!
Премиум
  1. Урок 1. 00:05:25
    Introduction
  2. Урок 2. 00:07:16
    Introduction to LangChain
  3. Урок 3. 00:07:06
    Setting Up the Environment: LangChain, Python-dotenv
  4. Урок 4. 00:06:30
    ChatModels: GPT-3.5-Turbo and GPT-4
  5. Урок 5. 00:04:57
    Caching LLM Responses
  6. Урок 6. 00:02:58
    LLM Streaming
  7. Урок 7. 00:05:36
    Prompt Templates
  8. Урок 8. 00:05:55
    ChatPromptTemplate
  9. Урок 9. 00:06:56
    Simple Chains
  10. Урок 10. 00:07:15
    Sequential Chains
  11. Урок 11. 00:04:01
    Introduction to LangChain Agents
  12. Урок 12. 00:07:41
    LangChain Agents in Action: Python REPL
  13. Урок 13. 00:11:08
    LangChain Tools: DuckDuckGo and Wikipedia
  14. Урок 14. 00:13:30
    Creating a React Agent
  15. Урок 15. 00:04:50
    Testing the React Agent
  16. Урок 16. 00:01:53
    Short Recap of Embeddings
  17. Урок 17. 00:06:58
    Introduction to Vector Databases
  18. Урок 18. 00:04:27
    Authenticating to Pinecone
  19. Урок 19. 00:09:32
    Working with Pinecone Indexes
  20. Урок 20. 00:08:43
    Working with Vectors
  21. Урок 21. 00:06:44
    Namespaces
  22. Урок 22. 00:09:20
    Splitting and Embedding Text Using LangChain
  23. Урок 23. 00:08:50
    Inserting the Embeddings into a Pinecone Index
  24. Урок 24. 00:07:54
    Asking Questions (Similarity Search)
  25. Урок 25. 00:04:21
    Getting a Gemini API Key
  26. Урок 26. 00:05:14
    Gemini Multimodal Models: Nano, Pro, and Ultra
  27. Урок 27. 00:04:31
    Installing the Python Libraries for Gemini and Authenticating to Gemini
  28. Урок 28. 00:06:02
    Integrating Gemini with LangChain
  29. Урок 29. 00:06:32
    Using a System Prompt and Enabling Streaming
  30. Урок 30. 00:14:13
    Multimodal AI With Gemini
  31. Урок 31. 00:06:09
    Project Introduction
  32. Урок 32. 00:07:28
    Loading Your Custom (Private) PDF Documents
  33. Урок 33. 00:05:13
    Loading Different Document Formats
  34. Урок 34. 00:04:38
    Public and Private Service Loaders
  35. Урок 35. 00:06:39
    Chunking Strategies and Splitting the Documents
  36. Урок 36. 00:13:34
    Embedding and Uploading to a Vector Database (Pinecone)
  37. Урок 37. 00:10:34
    Asking and Getting Answers
  38. Урок 38. 00:11:11
    Using Chroma as a Vector DB
  39. Урок 39. 00:09:26
    Adding Memory to the RAG System (Chat History)
  40. Урок 40. 00:08:10
    Using a Custom Prompt