点击任意处关闭 · Esc

Skip to content

AI 原生开放教材

Main Navigation

1. AI 基础与模型认知

2. 办公与知识工作

3. AI 编程与 Vibe Coding

4. 智能体工程

5. Harness 与编码 Agent

6. 上下文、记忆与技能

7. 个人智能体

8. 本地与端侧 AI

课程库来源总表关于

外观

Sidebar Navigation

Prompt Engineering Guide

Guides 🔮

Prompt Engineering - Introduction

Prompt Engineering - Basic Prompting

Prompt Engineering - Advanced Prompting

Prompt Engineering - Applications

Prompt Engineering - ChatGPT

Prompt Engineering - Adversarial Prompting

Prompt Engineering - Reliability

Prompt Engineering - Miscellaneous Topics

课程首页

Prompt Engineering Guide

pages

About

About

About

关于

Agents

LLM Applications & Guides

プロンプトアプリケーション

Prompting Applications

提示应用

Prompt Engineering Course

Prompt Engineering Courses

Datasets

データセット

数据集

Prompt Engineering Guide

Prompt Engineering Guide

프롬프트 엔지니어링 가이드

提示工程指南

Introduction

はじめに

Introduction

提示工程简介

Model Prompting Guides

モデル

Models

模型

Prompt Engineering Notebooks

Prompt Engineering Notebooks

Prompt Engineering Notebooks

Prompt Engineering笔记本

Papers

論文

Papers

论文

Prompt Hub

Prompt Hub

Prompt Hub

Prompt Hub

Additional Readings

参考文献

Additional Readings

阅读推荐

LLM Research Findings

LLM Research Findings

LLM Research Findings

LLM Research Findings

Risks & Misuses

リスクと誤用

Risks & Misuses

风险和误用

Services

Services

Prompting Techniques

プロンプトエンジニアリング技術

Prompting Techniques

提示技术

Tools & Libraries

ツール & ライブラリ

Tools & Libraries

工具和库

agents

AI Workflows vs. AI Agents

Agent Components

Context Engineering Deep Dive: Building a Deep Research Agent

Why Context Engineering?

Deep Agents

Function Calling in AI Agents

Introduction to AI Agents

applications

Generating Code

コード生成

Generating Code

代码生成

Context Caching with Gemini 1.5 Flash

Fine-Tuning with GPT-4o Models

Function Calling with LLMs

Function Calling with LLMs

LLMs의 Function Calling

在LLM中调用函数

Tackling Generated Datasets Diversity

Generating Data

データ生成

데이터 생성

生成数据

Prompt Function

Prompt Function

프롬프트 함수(Prompt Function)

提示函数

Generating Synthetic Dataset for RAG

Graduate Job Classification Case Study

ケーススタディ: 新卒にふさわしい仕事の分類

학위가 필요한 직업을 분류한 사례 연구

毕业生职位分类案例研究

guides

Prompt Engineering Guide

Context Engineering Guide

Prompt Engineering Guide

Prompt Engineering Guide

Prompt Engineering Guide

introduction

Basics of Prompting

プロンプトの基礎

프롬프트의 기초

基本概念

Elements of a Prompt

プロンプトの要素

프롬프트의 구성 요소

提示词要素

Examples of Prompts

プロンプトの例

프롬프트 예시

提示词示例

LLM Settings

LLMの設定

LLM 설정

模型设置

General Tips for Designing Prompts

プロンプトの設計に関する一般的なヒント

프롬프트 설계에 관한 일반적인 팁

设计提示的通用技巧

models

ChatGPT Prompt Engineering

ChatGPT プロンプトエンジニアリング

ChatGPT 프롬프트 엔지니어링

ChatGPT提示工程

Claude 3

Prompting Guide for Code Llama

Prompting Guide for Code Llama

Prompting Guide for Code Llama

Prompting Guide for Code Llama

LLM Collection

モデル一覧

모델 선택

Model Collection

Scaling Instruction-Finetuned Language Models

スケーリングされた指示によるファインチューニングされた言語モデル

지시에 따라 파인튜닝된(Instruction-Finetuned) 언어 모델 스케일링

扩展指令微调语言模型

Gemini Advanced

Gemini Advanced

Gemini Advanced

Gemini Advanced

Gemini 1.5 Pro

Gemini 1.5 Pro

Gemini 1.5 Pro

Gemini 1.5 Pro

Getting Started with Gemini

Gemini Prompting Guide

Gemini Prompting Guide

开始使用Gemini

Gemma

GPT-4

GPT-4

GPT-4

GPT-4

Grok-1

Kimi K2.5

Llama 3

Prompt Engineering Guide

Prompt Engineering Guide

Prompt Engineering Guide

Prompt Engineering Guide

Mistral 7B LLM

Mistral 7B LLM

Mistral 7B LLM

Mistral 7B LLM

Mistral Large

Mixtral 8x22B

Mixtral

Mixtral

Mixtral

Mixtral

OLMo

OLMo

OLMo

OLMo

Phi-2

Phi-2

Phi-2

Phi-2

Sora

Sora

Sora

Sora

prompts

Adversarial Prompting in LLMs

Adversarial Prompting in LLMs

大型语言模型中的对抗性提示

LLMs for Classification

LLMs for Classification

使用大型语言模型（LLMs）进行分类

LLMs for Code Generation

LLMs for Code Generation

LLMs for Code Generation

LLMs for Creativity

LLMs for Creativity

LLMs for Creativity

LLM Evaluation

LLM Evaluation

LLM Evaluation

Image Generation

Image Generation

Image Generation

Information Extraction with LLMs

Information Extraction with LLMs

Information Extraction with LLMs

Mathematical Understanding with LLMs

Mathematical Understanding with LLMs

Mathematical Understanding with LLMs

Question Answering with LLMs

Question Answering with LLMs

Question Answering with LLMs

Reasoning with LLMs

Reasoning with LLMs

Reasoning with LLMs

Text Summarization with LLMs

Text Summarization with LLMs

Text Summarization with LLMs

Truthfulness in LLMs

Truthfulness in LLMs

Truthfulness in LLMs

adversarial-prompting

Jailbreaking LLMs

LLMs越狱

Prompt Injection in LLMs

Prompt Injection in LLMs

Prompt Leaking in LLMs

LLMs中的提示泄露

classification

Few-Shot Sentiment Classification with LLMs

使用大型语言模型（LLMs）进行小样本情感分类

Sentiment Classification with LLMs

使用大型语言模型（LLMs）进行情感分类

coding

Generate Code Snippets with LLMs

Produce MySQL Queries using LLMs

Drawing TiKZ Diagram

creativity

Proof of Infinite Primes in Shakespeare Style

Interdisciplinary Tasks with LLMs

Inventing New Words

Rhyming with Proofs

evaluation

Evaluate Plato's Dialogue

image-generation

Draw a Person Using Alphabet Letters

information-extraction

Extract Model Names from Papers

mathematics

Evaluating Composite Functions

Adding Odd Numbers with LLMs

question-answering

Closed Domain Question Answering with LLMs

Open Domain Question Answering with LLMs

Science Question Answering with LLMs

reasoning

Indirect Reasoning with LLMs

Physical Reasoning with LLMs

text-summarization

Explain Concepts with LLMs

truthfulness

Identify Hallucination in LLM Responses

research

What is Groq?

Groq 是什么？

LM-Guided Chain-of-Thought

语言模型引导的思维链(CoT)

Efficient Infinite Context Transformers

高效处理无限长文本的Transformer模型

LLM Agents

LLM Agents

LLM Agents

大语言模型智能体简介

LLM Reasoning

大语言模型的推理能力

LLM In-Context Recall is Prompt Dependent

大型语言模型的上下文记忆受提示影响

LLM Tokenization

大语言模型（LLM）的标记化处理

Reducing Hallucination in Structured Outputs via RAG

利用 RAG 降低结构化输出中的虚假信息

How Faithful are RAG Models?

RAG 模型的忠实度如何？

Retrieval Augmented Generation (RAG) for LLMs

Retrieval Augmented Generation (RAG) for LLMs

Retrieval Augmented Generation (RAG) for LLMs

大语言模型的检索增强生成 (RAG) 方法

Best Practices and Lessons Learned on Synthetic Data for Language Models

语言模型合成数据的实用技巧与经验

Reasoning with Intermediate Revision and Search for LLMs

大语言模型的中间修订与搜索推理

Trustworthiness in LLMs

Trustworthiness in LLMs

Trustworthiness in LLMs

大语言模型的可信度探索

risks

Adversarial Prompting in LLMs

敵対的プロンプト（Adversarial Prompting）

적대적 프롬프팅

对抗性提示

Biases

バイアス

편향

偏见

Factuality

事実性

사실성

真实性

techniques

Active-Prompt

アクティブプロンプト

Active-Prompt

Active-Prompt

Automatic Prompt Engineer (APE)

自動プロンプトエンジニア（APE）

Automatic Prompt Engineer (APE)

自动提示工程师（APE）

Automatic Reasoning and Tool-use (ART)

Automatic Reasoning and Tool-use (ART)

Automatic Reasoning and Tool-use (ART)

自动推理并使用工具 (ART)

Self-Consistency

Self-Consistency（自己整合性）

Self-Consistency

自我一致性

Chain-of-Thought Prompting

Chain-of-Thoughtプロンプティング

Chain-of-Thought Prompting

Chain-of-Thought Prompting

Directional Stimulus Prompting

方向性刺激プロンプティング

Directional Stimulus Prompting

方向性刺激提示

Few-Shot Prompting

Few-Shotプロンプティング

Few-Shot Prompting

少样本提示

GraphPrompts

グラフプロンプト（GraphPrompts）

GraphPrompts

GraphPrompts

Generated Knowledge Prompting

知識生成プロンプティング

Generated Knowledge Prompting

生成知识提示

Meta Prompting

Multimodal CoT Prompting

マルチモーダルCoTプロンプティング

Multimodal CoT Prompting

多模态思维链提示方法

PAL (Program-Aided Language Models)

PAL（プログラム支援言語モデル）

PAL (프로그램지원언어모델)

PAL（程序辅助语言模型）

Prompt Chaining

Prompt Chaining

Prompt Chaining

链式提示

Retrieval Augmented Generation (RAG)

検索により強化された生成 (RAG)

Retrieval Augmented Generation (RAG)

检索增强生成 (RAG)

ReAct Prompting

ReAct

ReAct Prompting

ReAct 框架

Reflexion

Reflexion

Reflexion

自我反思（Reflexion）

Tree of Thoughts (ToT)

Tree of Thoughts (ToT)

Tree of Thoughts (ToT)

思维树 (ToT)

Zero-Shot Prompting

Zero-Shotプロンプティング

Zero-Shot Prompting

零样本提示

出处与许可

来源信息

本页目录

课程库›上下文、记忆与技能›Prompt Engineering Guide

Prompt Engineering Guide工程手册·英文原文 ↗原件 ↓仓库 ↗

LLM Research Findings

import ContentFileNames from 'components/ContentFileNames'

This page needs a translation! Feel free to contribute a translation by clicking the Edit this page button on the right.

Pager

上一篇LLM Research Findings

下一篇Risks & Misuses

AI 原生开放教材·GitHub 仓库·@faruheaisha·署名与许可编排与站点代码 MIT · 课程内容著作权归各上游作者