prompt-engineering

# Prompt Engineering

Master the art of crafting effective prompts for LLMs.

## Quick Start

### Basic Prompt Structure
```python
# Simple completion prompt
prompt = """
You are a helpful assistant specialized in {domain}.

Task: {task_description}

Context: {relevant_context}

Instructions:
1. {instruction_1}
2. {instruction_2}

Output format: {desired_format}
"""

# Using OpenAI
from openai import OpenAI
client = OpenAI()

response = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "system", "content": system_prompt},
        {"role": "user", "content": user_prompt}
    ]
)
```

### Few-Shot Learning
```python
few_shot_prompt = """
Classify the sentiment of the following reviews.

Examples:
Review: "This product exceeded my expectations!"
Sentiment: Positive

Review: "Terrible quality, broke after one day."
Sentiment: Negative

Review: "It's okay, nothing special."
Sentiment: Neutral

Now classify:
Review: "{user_review}"
Sentiment:
"""
```

## Core Techniques

### Chain of Thought (CoT)
```python
cot_prompt = """
Solve this step by step:

Problem: {problem}

Let's think through this carefully:
1. First, identify what we know...
2. Then, determine what we need to find...
3. Apply the relevant formula/logic...
4. Calculate the result...

Final Answer:
"""
```

### Self-Consistency
```python
# Generate multiple reasoning paths
responses = []
for _ in range(5):
    response = generate_with_cot(prompt, temperature=0.7)
    responses.append(response)

# Take majority vote
final_answer = majority_vote(responses)
```

### ReAct Pattern
```python
react_prompt = """
Answer the following question using the ReAct framework.

Question: {question}

Use this format:
Thought: [Your reasoning about what to do next]
Action: [The action to take: Search, Calculate, or Lookup]
Observation: [The result of the action]
... (repeat Thought/Action/Observation as needed)
Thought: I now have enough information to answer.
Final Answer: [Your answer]
"""
```