Few-Shot Prompt Templates: Copy, Paste, and Customize for Your Niche

Welcome to your go-to resource for ready-to-use few-shot prompt templates. We've compiled a collection of templates designed for a variety of niches, enabling you to quickly leverage the power of LLMs. Simply copy, paste, and customize these templates to fit your specific needs.

(1) Sentiment Analysis & Text Classification:

• Template:

Input: "This movie was absolutely fantastic! I loved every minute."
Sentiment: Positive

Input: "The food was terrible, and the service was even worse."
Sentiment: Negative

Input: "The report was informative, but a bit dry."
Sentiment: Neutral

Input: "[Your Text Here]"
Sentiment:

• Customization:
  • Replace [Your Text Here] with the text you want to analyze.
  • Adjust the example inputs and sentiments to match your specific domain or industry.
• Niche Examples:
  • Customer reviews (e-commerce)
  • Social media posts (marketing)
  • Product feedback (development)

(2) Translation:

• Template:

English: "Hello, how are you?"
Spanish: "Hola, ¿cómo estás?"

English: "Thank you very much."
Spanish: "Muchas gracias."

English: "Where is the nearest restaurant?"
Spanish: "¿Dónde está el restaurante más cercano?"

English: "[Your English Text Here]"
Spanish:

• Customization:
  • Replace [Your English Text Here] with the text you want to translate.
  • Change the languages to suit your needs.
• Niche Examples:
  • Legal documents (legal)
  • Technical manuals (engineering)
  • Website localization (web development)

(3) Code Generation:

• Template:

Input: "Create a Python function to add two numbers."
Output:
def add_numbers(a, b):
    return a + b

Input: "Generate a JavaScript function to reverse a string."
Output:
function reverseString(str) {
  return str.split('').reverse().join('');
}

Input: "[Your Code Request Here]"
Output:

• Customization:
  • Replace [Your Code Request Here] with your desired code request.
  • Change the coding language as needed.
• Niche Examples:
  • Web development (front-end, back-end)
  • Data science (data manipulation)
  • Scripting (automation)

(4) Creative Writing:

• Template:

Style: Short, descriptive poem
Example: "The wind whispers low, trees dance in the night, stars softly glow."

Style: Humorous short story
Example: "The squirrel, convinced he was a spy, hid acorns in his neighbor's mailbox."

Style: Formal business letter
Example: "Dear Sir/Madam, I am writing to inquire about..."

Style: "[Your Desired Style Here]"
Example: "[Your Writing Prompt Here]"

• Customization:
  • Replace [Your Desired Style Here] and [Your Writing Prompt Here] with your specific requirements.
• Niche Examples:
  • Marketing copy (advertising)
  • Blog posts (content creation)
  • Screenplays (entertainment)

(5) Question Answering/Chatbot responses:

• Template:

Question: "What is the capital of France?"
Answer: "The capital of France is Paris."

Question: "How do I reset my password?"
Answer: "To reset your password, click on the 'Forgot Password' link."

Question: "[Your Question Here]"
Answer:

• Customization:
  • Replace [Your Question Here] with the question you want answered.
  • Customize the examples to fit the tone of the chatbot.
• Niche Examples:
  • Customer support (e-commerce)
  • Technical support (software)
  • Information retrieval (research)

(6) Data Extraction:

• Template:

Text: "Name: John Doe, Age: 30, Email: [email protected]"
Extracted: "Name: John Doe, Age: 30, Email: [email protected]"

Text: "Product: Laptop, Price: $1200, Manufacturer: Dell"
Extracted: "Product: Laptop, Price: $1200, Manufacturer: Dell"

Text: "[Your Text Here]"
Extracted:

• Customization:
  • Replace [Your Text Here] with the data you want to extract.
  • Adjust the examples to fit the data format you are working with.
• Niche Examples:
  • Resume parsing (HR)
  • Invoice processing (accounting)
  • Web scraping (data analysis)

Tips for Success:

• Experiment: Don't be afraid to experiment with different prompts and examples.
• Iterate: Refine your prompts based on the LLM's output.
• Context is Key: Provide enough context for the LLM to understand the task.
• Clear Instructions: Give clear and concise instructions.