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