Prompt Engineering Guide 中文版

提示词工程指南（Prompt Engineering Guide）是由 DAIR.AI 发起，由 南昌大学人工智能工业研究院、 NCUHOME 及中文开源社区共同翻译和改进的教程项目，旨在帮助研发和行业内相关人员了解提示工程。提示工程技能有助于更好地了解大型语言模型（LLM）的能力和局限性。研究人员利用提示工程提高 LLM 在各种常见和复杂任务（如问题解答和算术推理）中的能力。开发人员使用提示工程来设计与 LLM 和其他工具相连接的强大而有效的提示技术。

鉴于人们对使用 LLMs 进行开发的浓厚兴趣，我们创建了这一新的提示工程指南，其中包含与 LLMs 提示工程相关的所有最新论文、学习指南、讲座、参考资料和工具。

以传播 AI 技术和研究成果为目标，我们欢迎大家的贡献！大家可以查找页面上的编辑按钮参与贡献。

查看许可信息.

本项目受多个开源项目启发，包括：

• OpenAI CookBook
• Pretrain, Prompt, Predic
• Learn Prompting。

感谢以上开源项目的贡献。

🌐 Prompt Engineering Guide (Web Version)

Guides

You can also find the most up-to-date guides on our new website https://prompt-guide.ncuos.com/.

• Prompt Engineering - Introduction
  • Prompt Engineering - LLM Settings
  • Prompt Engineering - Basics of Prompting
  • Prompt Engineering - Prompt Elements
  • Prompt Engineering - General Tips for Designing Prompts
  • Prompt Engineering - Examples of Prompts
• Prompt Engineering - Techniques
  • Prompt Engineering - Zero-Shot Prompting
  • Prompt Engineering - Few-Shot Prompting
  • Prompt Engineering - Chain-of-Thought Prompting
  • Prompt Engineering - Self-Consistency
  • Prompt Engineering - Generate Knowledge Prompting
  • Prompt Engineering - Prompt Chaining
  • Prompt Engineering - Tree of Thoughts (ToT)
  • Prompt Engineering - Retrieval Augmented Generation
  • Prompt Engineering - Automatic Reasoning and Tool-use (ART)
  • Prompt Engineering - Automatic Prompt Engineer
  • Prompt Engineering - Active-Prompt
  • Prompt Engineering - Directional Stimulus Prompting
  • Prompt Engineering - Program-Aided Language Models
  • Prompt Engineering - ReAct Prompting
  • Prompt Engineering - Multimodal CoT Prompting
  • Prompt Engineering - Graph Prompting
• Prompt Engineering - Applications
  • Prompt Engineering - Function Calling
  • Prompt Engineering - Generating Data
  • Prompt Engineering - Generating Synthetic Dataset for RAG
  • Prompt Engineering - Takling Generated Datasets Diversity
  • Prompt Engineering - Generating Code
  • Prompt Engineering - Graduate Job Classification Case Study
• Prompt Engineering - Prompt Hub
  • Prompt Engineering - Classification
  • Prompt Engineering - Coding
  • Prompt Engineering - Creativity
  • Prompt Engineering - Evaluation
  • Prompt Engineering - Information Extraction
  • Prompt Engineering - Image Generation
  • Prompt Engineering - Mathematics
  • Prompt Engineering - Question Answering
  • Prompt Engineering - Reasoning
  • Prompt Engineering - Text Summarization
  • Prompt Engineering - Truthfulness
  • Prompt Engineering - Adversarial Prompting
• Prompt Engineering - Models
  • Prompt Engineering - ChatGPT
  • Prompt Engineering - Code Llama
  • Prompt Engineering - Flan
  • Prompt Engineering - Gemini
  • Prompt Engineering - GPT-4
  • Prompt Engineering - LLaMA
  • Prompt Engineering - Mistral 7B
  • Prompt Engineering - Mixtral
  • Prompt Engineering - OLMo
  • Prompt Engineering - Phi-2
  • Prompt Engineering - Model Collection
• Prompt Engineering - Risks and Misuses
  • Prompt Engineering - Adversarial Prompting
  • Prompt Engineering - Factuality
  • Prompt Engineering - Biases
• Prompt Engineering - Papers
  • Prompt Engineering - Overviews
  • Prompt Engineering - Approaches
  • Prompt Engineering - Applications
  • Prompt Engineering - Collections
• Prompt Engineering - Tools
• Prompt Engineering - Notebooks
• Prompt Engineering - Datasets
• Prompt Engineering - Additional Readings

Running the guide locally

To run the guide locally, for example to check the correct implementation of a new translation, you will need to:

1. Install Node >=18.0.0
2. Install pnpm if not present in your system. Check here for detailed instructions.
3. Install the dependencies: pnpm i next react react-dom nextra nextra-theme-docs
4. Boot the guide with pnpm dev
5. Browse the guide at http://localhost:3000/

License

MIT License

如果您认为这里缺少某些内容，请随时打开 PR。随时欢迎反馈和建议。只需打开一个问题！