Этот материал находится в платной подписке. Оформи премиум подписку и смотри или слушай AI Engineering Bootcamp: Building AI Applications (LangChain, LLM APIs + more), а также все другие курсы, прямо сейчас!
Премиум
  • Урок 1. 00:02:02
    AI Engineering Bootcamp: Building AI Applications with LLM APIs, LangChain + much more!Using Jupyter Notebook
  • Урок 2. 00:09:24
    Using Jupyter Notebook
  • Урок 3. 00:10:07
    Using Virtual Environments (venv)
  • Урок 4. 00:08:50
    Getting Started with the requests and httpx Libraries in Python
  • Урок 5. 00:04:39
    Handling HTTP Errors
  • Урок 6. 00:09:59
    Managing HTTP Authentication and Headers (OpenAI API)
  • Урок 7. 00:03:55
    Setting Up the Environment: Jupyter Notebook and Pandas
  • Урок 8. 00:06:09
    Introduction to Pandas: Series and DataFrames
  • Урок 9. 00:06:38
    Importing and Exporting Data: Working with CSV Files
  • Урок 10. 00:07:47
    Exporting Data to Different Formats: Excel, JSON, SQL, YAML
  • Урок 11. 00:06:05
    Modifying Data: Adding and Dropping Columns and Rows
  • Урок 12. 00:05:43
    Accessing Data: Using df.iloc[] and df.loc[]
  • Урок 13. 00:06:15
    Sampling and Previewing Data: Using df.sample() and df.head()
  • Урок 14. 00:07:15
    Filtering Data: Masks and pandas.Series.between()
  • Урок 15. 00:07:11
    Sorting Data: Understanding Pandas Sorting Methods
  • Урок 16. 00:04:44
    Handling Missing Data
  • Урок 17. 00:04:54
    Aggregations and Grouping Data
  • Урок 18. 00:04:33
    Project: Analyzing Website Traffic Data
  • Урок 19. 00:06:59
    Time Series Data Manipulation in Pandas
  • Урок 20. 00:08:32
    Foundations of LLMs and Generative AI
  • Урок 21. 00:05:26
    Tokens, Context Windows and Cost
  • Урок 22. 00:09:23
    Exploring LLM APIs: AI as a Service
  • Урок 23. 00:06:06
    OpenAI Playground, Google AI Studio, and Anthropic Workbench
  • Урок 24. 00:09:03
    Challenges and Limitations of LLMs
  • Урок 25. 00:10:06
    The State of AI: Present and Future – The Good and the Bad
  • Урок 26. 00:06:41
    Pretraining Data (Internet)
  • Урок 27. 00:06:07
    Tokenization
  • Урок 28. 00:09:26
    Training the Neural Network
  • Урок 29. 00:08:26
    Post-Training: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL)
  • Урок 30. 00:05:30
    Reinforcement Learning (RL)
  • Урок 31. 00:07:32
    Becoming Better than Humans: AGI and ASI with RL
  • Урок 32. 00:06:23
    Reinforcement Learning with Human Feedback (RLHF)
  • Урок 33. 00:07:37
    How to Deal With Hallucinations
  • Урок 34. 00:07:49
    Using Tools: Internet Search, Interpreter, and Deep Search
  • Урок 35. 00:09:51
    Big Ideas Recap (Core Summary)
  • Урок 36. 00:08:17
    Authenticating to OpenAI using Python Dotenv
  • Урок 37. 00:06:58
    Chat Completions Endpoint
  • Урок 38. 00:04:31
    Developer Message
  • Урок 39. 00:04:31
    Streaming API Responses
  • Урок 40. 00:06:44
    Using Local Base64 Images as Input
  • Урок 41. 00:02:05
    Using Online Images as Input
  • Урок 42. 00:06:14
    Chat Completion API Parameters: Temperature and Seed
  • Урок 43. 00:09:50
    Chat Completion API Parameters: Top P, Max_Tokens, Penalties
  • Урок 44. 00:07:56
    Diving into OpenAI’s Reasoning Models (o1 and o3)
  • Урок 45. 00:05:26
    Best Practices for Prompting Reasoning Models
  • Урок 46. 00:05:48
    Transcriptions with Whisper
  • Урок 47. 00:03:12
    Translations with Whisper
  • Урок 48. 00:07:03
    Text-to-Speech (TTS) API
  • Урок 49. 00:10:50
    Generating Original Images Using the DALL-E 3
  • Урок 50. 00:03:05
    Creating Variations of Images with DALL-E
  • Урок 51. 00:05:40
    Editing Images with DALL-E
  • Урок 52. 00:02:41
    Intro to Prompt Engineering
  • Урок 53. 00:04:13
    Tactic 1: Position Instruction Clearly with Delimiters
  • Урок 54. 00:06:38
    Tactic 2: Provide Detailed Instructions for the Context
  • Урок 55. 00:07:46
    Tactic 3: Use the Rich Text Format (RTF)
  • Урок 56. 00:08:13
    Tactic 4: Few Shot Prompting
  • Урок 57. 00:05:17
    Tactic 5: Specify the Steps Required to Complete a Task
  • Урок 58. 00:02:13
    Tactic 6: Give Models Time to Think
  • Урок 59. 00:05:38
    Other Tactics and Principles for Better Prompting
  • Урок 60. 00:03:07
    Avoid Hallucinations Using Guarding
  • Урок 61. 00:02:07
    Summary
  • Урок 62. 00:02:32
    Project Introduction
  • Урок 63. 00:05:39
    Creating a Daily Meal Plan Using OpenAI API
  • Урок 64. 00:08:43
    Creating the Prompt
  • Урок 65. 00:03:24
    Running the Program
  • Урок 66. 00:11:54
    Generating Original Images for the Recipes using DALL-E
  • Урок 67. 00:10:24
    Narrate the Meals using the Text-to-Speech Model
  • Урок 68. 00:09:51
    Setting Up the Python SDK and Authenticating for Gemini API
  • Урок 69. 00:04:15
    Generating Text From Text Prompts
  • Урок 70. 00:02:59
    Streaming Gemini Responses
  • Урок 71. 00:05:49
    Generating Text From Images
  • Урок 72. 00:06:12
    Gemini API Generation Parameters: Controlling How the Model Generates Responses
  • Урок 73. 00:10:14
    Gemini API Generation Parameters Explained
  • Урок 74. 00:07:54
    Building Chat Conversations
  • Урок 75. 00:07:19
    Project: Building a Conversational Agent Using Gemini Pro
  • Урок 76. 00:05:43
    System Instructions
  • Урок 77. 00:06:09
    The File API: Prompting with Media Files
  • Урок 78. 00:06:42
    Tokens
  • Урок 79. 00:04:21
    Prompting with Audio
  • Урок 80. 00:05:54
    Project Requirements
  • Урок 81. 00:05:23
    Building the Application
  • Урок 82. 00:01:49
    Testing the Application
  • Урок 83. 00:02:49
    Streamlit: Transform Your Jupyter Notebooks into Interactive Web Apps
  • Урок 84. 00:11:20
    Creating the Web App Layout With Streamlit
  • Урок 85. 00:05:20
    Saving and Displaying the History Using the Streamlit Session State
  • Урок 86. 00:02:57
    Exercise: Imposter Syndrome
  • Урок 87. 00:00:57
    Project Introduction
  • Урок 88. 00:06:18
    Getting Images Using a Generator
  • Урок 89. 00:09:35
    Renaming Images Using Gemini
  • Урок 90. 00:05:06
    LangChain Demo
  • Урок 91. 00:05:10
    Introduction to LangChain
  • Урок 92. 00:08:43
    Working with the OpenAI Models
  • Урок 93. 00:04:57
    Caching LLM Responses
  • Урок 94. 00:02:58
    LLM Streaming
  • Урок 95. 00:05:36
    Prompt Templates
  • Урок 96. 00:05:55
    ChatPromptTemplate
  • Урок 97. 00:07:48
    Understanding Chains
  • Урок 98. 00:04:31
    Installing the Python Libraries for Gemini and Authenticating to Gemini
  • Урок 99. 00:06:02
    Integrating Gemini with LangChain
  • Урок 100. 00:06:32
    Using a System Prompt and Enabling Streaming
  • Урок 101. 00:14:13
    Multimodal AI With Gemini
  • Урок 102. 00:11:08
    LangChain Tools: DuckDuckGo and Wikipedia
  • Урок 103. 00:13:30
    Creating a React Agent
  • Урок 104. 00:04:50
    Testing the React Agent
  • Урок 105. 00:03:16
    Intro to OpenAI's Text Embeddings
  • Урок 106. 00:05:54
    Generating Simple Embeddings
  • Урок 107. 00:04:52
    Embedding the Dataset for Similarity Searches
  • Урок 108. 00:05:12
    Estimating Embedding Costs With Tiktoken
  • Урок 109. 00:07:05
    Performing Semantic Searches
  • Урок 110. 00:06:09
    Project Introduction
  • Урок 111. 00:07:28
    Loading Your Custom (Private) PDF Documents
  • Урок 112. 00:05:13
    Loading Different Document Formats
  • Урок 113. 00:04:38
    Public and Private Service Loaders
  • Урок 114. 00:06:39
    Chunking Strategies and Splitting the Documents
  • Урок 115. 00:09:02
    Intro to Vector Stores and Authenticating to Pinecone
  • Урок 116. 00:09:32
    Working with Pinecone Indexes
  • Урок 117. 00:08:43
    Working with Vectors
  • Урок 118. 00:06:44
    Pinecone Namespaces
  • Урок 119. 00:13:53
    Embedding and Uploading to a Vector Database (Pinecone)
  • Урок 120. 00:11:43
    Asking and Getting Answers
  • Урок 121. 00:11:11
    Using Chroma as a Vector DB
  • Урок 122. 00:09:26
    Adding Memory to the RAG System (Chat History)
  • Урок 123. 00:08:10
    Using a Custom Prompt
  • Урок 124. 00:04:20
    Introduction to Agents and ReAct
  • Урок 125. 00:02:42
    Creating the Agent Class
  • Урок 126. 00:02:31
    Creating the ReAct Prompt
  • Урок 127. 00:02:41
    Creating the Tools
  • Урок 128. 00:06:06
    Testing the Agent
  • Урок 129. 00:07:01
    Automating the Agent
  • Урок 130. 00:05:43
    LangGraph Concepts and Core Components
  • Урок 131. 00:05:30
    Building a Chatbot
  • Урок 132. 00:02:13
    Visualizing the Graph
  • Урок 133. 00:01:32
    Running the Chatbot
  • Урок 134. 00:08:29
    Tavily AI
  • Урок 135. 00:08:17
    Enhancing the ChatBot with Tools
  • Урок 136. 00:07:06
    Adding Memory to the Chatbot
  • Урок 137. 00:02:14
    Intro to Reflection
  • Урок 138. 00:04:16
    Generate
  • Урок 139. 00:02:33
    Reflect and Repeat
  • Урок 140. 00:03:44
    Define the Graph - Part 1
  • Урок 141. 00:02:49
    Define the Graph - Part 2
  • Урок 142. 00:03:55
    Running the App
  • Урок 143. 00:03:29
    Intro to LangSmith
  • Урок 144. 00:01:55
    Setting Up LangSmith
  • Урок 145. 00:06:17
    Tracing with LangSmith
  • Урок 146. 00:03:51
    Tracing the Reflective Agentic App
  • Урок 147. 00:01:48
    Project Overview
  • Урок 148. 00:07:39
    Defining the Agent State and the Prompts
  • Урок 149. 00:09:39
    Implementing Agents and Nodes
  • Урок 150. 00:01:27
    Defining the Conditional Edge
  • Урок 151. 00:04:25
    Defining the Graph
  • Урок 152. 00:04:07
    Running the App
  • Урок 153. 00:02:51
    Tracing the App with LangSmith
  • Урок 154. 00:02:16
    Note
  • Урок 155. 00:03:34
    Application Overview
  • Урок 156. 00:12:44
    Extracting Data from ArXiv with Pandas
  • Урок 157. 00:04:53
    Downloading Research Papers
  • Урок 158. 00:09:54
    Loading, Splitting and Expanding Data
  • Урок 159. 00:05:35
    Building a Knowledge Base for RAG
  • Урок 160. 00:07:17
    Creating a Pinecone Index
  • Урок 161. 00:05:04
    Loading the Knowledge Base and Deploying to Pinecone
  • Урок 162. 00:05:13
    Developing Custom Tools
  • Урок 163. 00:08:01
    Implementing the ArXiv Fetch Tool
  • Урок 164. 00:03:29
    Unlocking Web Search with Google SerpAPI
  • Урок 165. 00:04:26
    Building Google SerpAPI Tools
  • Урок 166. 00:06:20
    Creating RAG Tools
  • Урок 167. 00:02:18
    Implementing the Final Answer Generation Tool
  • Урок 168. 00:11:02
    06_14 Initializing the Oracle LLM
  • Урок 169. 00:03:33
    Testing the Ecosystem
  • Урок 170. 00:08:34
    Building a Decision-Making Pipeline
  • Урок 171. 00:03:25
    Defining the Agent State
  • Урок 172. 00:06:36
    Defining the Graph
  • Урок 173. 00:04:27
    Generating Reports
  • Урок 174. 00:05:20
    Building the Final Research Report
  • Урок 175. 00:06:23
    Concluding the Project
  • Урок 176. 00:06:17
    Understanding Python Modules
  • Урок 177. 00:07:57
    The OS Module
  • Урок 178. 00:04:11
    Advanced Import Techniques and Best Practices
  • Урок 179. 00:06:24
    Using __name__ == '__main__' for Modular and Reusable Code
  • Урок 180. 00:08:35
    Mastering Python Package Management with pip
  • Урок 181. 00:01:18
    Thank You!