Pros of Prompt-Engineering-Guide

• More comprehensive coverage of advanced techniques
• Includes practical examples and case studies
• Regular updates with the latest developments in prompt engineering

Cons of Prompt-Engineering-Guide

• Less beginner-friendly structure
• Fewer interactive elements and exercises
• More text-heavy, which may be overwhelming for some learners

Code Comparison

Learn_Prompting:

def generate_prompt(topic):
    return f"Write a short essay about {topic}."

response = openai.Completion.create(
    engine="text-davinci-002",
    prompt=generate_prompt("artificial intelligence"),
    max_tokens=150
)

Prompt-Engineering-Guide:

from langchain import PromptTemplate

template = """
Write a short essay about {topic}.
Include at least three key points and a conclusion.
"""

prompt = PromptTemplate(
    input_variables=["topic"],
    template=template
)

result = llm(prompt.format(topic="artificial intelligence"))

Both repositories offer valuable resources for learning prompt engineering, but they cater to slightly different audiences. Learn_Prompting is more accessible for beginners, while Prompt-Engineering-Guide provides a deeper dive into advanced techniques and current trends in the field.

Pros of awesome-chatgpt-prompts

• Extensive collection of ready-to-use prompts for various scenarios
• Community-driven with frequent updates and contributions
• Simple, easy-to-navigate structure

Cons of awesome-chatgpt-prompts

• Lacks in-depth explanations or tutorials on prompt engineering
• Limited focus on advanced techniques or strategies
• Minimal organization or categorization of prompts

Code Comparison

Learn_Prompting:

def few_shot(examples, new_input):
    prompt = "Examples:\n"
    for ex in examples:
        prompt += f"Input: {ex['input']}\nOutput: {ex['output']}\n\n"
    prompt += f"Input: {new_input}\nOutput:"
    return prompt

awesome-chatgpt-prompts:

# Act as a Linux Terminal
I want you to act as a linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English, I will do so by putting text inside curly brackets {like this}. My first command is pwd

Pros of openai-cookbook

• Official resource from OpenAI, ensuring up-to-date and accurate information
• Comprehensive coverage of OpenAI's APIs and models
• Includes practical examples and use cases for various applications

Cons of openai-cookbook

• Focused solely on OpenAI's offerings, limiting broader AI/ML exploration
• May lack community-driven content and diverse perspectives
• Less emphasis on prompt engineering techniques and strategies

Code Comparison

Learn_Prompting example:

prompt = f"""
Summarize the text below in 50 words or less:

{text}
"""
response = openai.Completion.create(engine="text-davinci-002", prompt=prompt, max_tokens=60)

openai-cookbook example:

response = openai.ChatCompletion.create(
    model="gpt-3.5-turbo",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": f"Summarize this text in 50 words: {text}"}
    ]
)

Both repositories offer valuable resources for working with AI language models. Learn_Prompting provides a broader perspective on prompt engineering across various platforms, while openai-cookbook focuses specifically on OpenAI's offerings with official, in-depth guidance. The choice between them depends on whether you're looking for a comprehensive view of prompt engineering or specialized knowledge of OpenAI's ecosystem.

Pros of Awesome-Prompt-Engineering

• More comprehensive collection of prompt engineering resources
• Includes a wider range of topics, such as tools, papers, and courses
• Regularly updated with new content and contributions

Cons of Awesome-Prompt-Engineering

• Less structured learning path for beginners
• Lacks in-depth explanations and tutorials
• May be overwhelming due to the sheer amount of information

Code Comparison

While both repositories primarily focus on curating resources rather than providing code examples, Learn_Prompting does include some code snippets in its tutorials. Here's a brief comparison:

Learn_Prompting:

prompt = f"""
Summarize the text below in 50 words or less:

{text}
"""
response = openai.Completion.create(
    engine="text-davinci-002",
    prompt=prompt,
    max_tokens=60
)

Awesome-Prompt-Engineering: No specific code examples are provided in the main repository.

Both repositories serve as valuable resources for prompt engineering, with Learn_Prompting offering a more structured learning experience and Awesome-Prompt-Engineering providing a comprehensive collection of resources for various skill levels and interests.

Pros of prompt-engine

• Developed and maintained by Microsoft, potentially offering more robust support and resources
• Focuses on providing a structured framework for building prompt-based applications
• Includes tools for prompt management and version control

Cons of prompt-engine

• Less comprehensive educational content compared to Learn_Prompting
• May have a steeper learning curve for beginners in prompt engineering
• Primarily targets developers rather than a broader audience interested in learning about prompts

Code Comparison

Learn_Prompting (example from documentation):

from learn_prompting import Prompt

prompt = Prompt("Translate the following English text to French: {text}")
result = prompt.format(text="Hello, how are you?")
print(result)

prompt-engine (example from documentation):

import { PromptTemplate } from '@microsoft/prompt-engine';

const template = new PromptTemplate('Translate the following English text to French: {{text}}');
const result = template.format({ text: 'Hello, how are you?' });
console.log(result);

Both repositories provide tools for working with prompts, but prompt-engine offers a more structured approach with TypeScript support, while Learn_Prompting focuses on educational content and Python implementation.