使用 Gemini API 构建 AI 应用程序
上次更新时间：2024-11-02
课程售价: 2.9 元
联系右侧微信客服充值或购买课程
课程内容
- 01. Introduction (免费)
- 02. What We're Using (免费)
- 03. Jupyter Notebook
- 04. Google Colab
- 05. Getting a Gemini API Key
- 06. Installing the Python SDK for Gemini API and Authenticating to Gemini
- 07. Gemini Multimodal Models Nano, Pro, and Ultra
- 08. Google AI Studio Freeform Prompts With Gemini Pro Vision
- 09. Google AI Studio Using Variables and Parameters in the Prompt
- 10. Generating Text From Text Inputs Gemini Pro
- 11. Streaming Model Responses
- 12. Generating Text From Image and Text Inputs Gemini Pro Vision
- 13. Gemini API Generation Parameters Controlling How the Model Generates Responses
- 14. Gemini API Generation Parameters Explained
- 15. Building Chat Conversations
- 16. Project Building a Conversational Agent Using Gemini Pro
- 17. Introduction to Gemini 1.5 Pro
- 18. System Instructions
- 19. The File API Prompting with Media Files
- 20. Tokens
- 21. Prompting with Audio
- 22. Project Requirements
- 23. Building the Application
- 24. Testing the Application
- 25. Streamlit Transform Your Jupyter Notebooks into Interactive Web Apps
- 26. Creating the Web App Layout With Streamlit
- 27. Saving and Displaying the History Using the Streamlit Session State
- 28. Project Introduction
- 29. Getting Images Using a Generator
- 30. Renaming Images Using Gemini Pro Vision
- 31. Intro to Prompt Engineering the Gemini API
- 32. Tactic 1 - Position Instructions Clearly With Delimiters
- 33. Tactic 2 - Provide Detailed Instructions for the Context, Outcome, or Length
- 34. Tactic 3 - Specify the Response Format
- 35. Tactic 4 - Few-Shot Prompting
- 36. Tactic 5 - Specify the Steps Required to Complete a Task
- 37. Tactic 6 - Give Models Time to _Think_
- 38. Other Tactics for Better Prompting and Avoiding Hallucinations
- 39. Prompt Engineering Summary
课程内容
39个讲座
- 01. Introduction (免费)
- 02. What We're Using (免费)
- 03. Jupyter Notebook
- 04. Google Colab
- 05. Getting a Gemini API Key
- 06. Installing the Python SDK for Gemini API and Authenticating to Gemini
- 07. Gemini Multimodal Models Nano, Pro, and Ultra
- 08. Google AI Studio Freeform Prompts With Gemini Pro Vision
- 09. Google AI Studio Using Variables and Parameters in the Prompt
- 10. Generating Text From Text Inputs Gemini Pro
- 11. Streaming Model Responses
- 12. Generating Text From Image and Text Inputs Gemini Pro Vision
- 13. Gemini API Generation Parameters Controlling How the Model Generates Responses
- 14. Gemini API Generation Parameters Explained
- 15. Building Chat Conversations
- 16. Project Building a Conversational Agent Using Gemini Pro
- 17. Introduction to Gemini 1.5 Pro
- 18. System Instructions
- 19. The File API Prompting with Media Files
- 20. Tokens
- 21. Prompting with Audio
- 22. Project Requirements
- 23. Building the Application
- 24. Testing the Application
- 25. Streamlit Transform Your Jupyter Notebooks into Interactive Web Apps
- 26. Creating the Web App Layout With Streamlit
- 27. Saving and Displaying the History Using the Streamlit Session State
- 28. Project Introduction
- 29. Getting Images Using a Generator
- 30. Renaming Images Using Gemini Pro Vision
- 31. Intro to Prompt Engineering the Gemini API
- 32. Tactic 1 - Position Instructions Clearly With Delimiters
- 33. Tactic 2 - Provide Detailed Instructions for the Context, Outcome, or Length
- 34. Tactic 3 - Specify the Response Format
- 35. Tactic 4 - Few-Shot Prompting
- 36. Tactic 5 - Specify the Steps Required to Complete a Task
- 37. Tactic 6 - Give Models Time to _Think_
- 38. Other Tactics for Better Prompting and Avoiding Hallucinations
- 39. Prompt Engineering Summary