🧠 Prompt Engineering Techniques

A structured collection of Prompt Engineering strategies implemented using Large Language Models (LLMs).

This repository demonstrates foundational to advanced prompting patterns including reasoning-based approaches and automation workflows.

---

🚀 Repository Overview

This repo explores different prompting strategies used to improve LLM performance and reasoning capability.

The repository includes:

• One-Shot Prompting
• Few-Shot Prompting
• Chain-of-Thought (CoT) Prompting
• Chain-of-Thought Automation Agent

Each technique is implemented with practical examples and structured outputs.

---

📂 Project Structure

prompt-engineering-techniques/
│
├── one_shot_prompting.py
├── few_shot_prompting.py
├── cot_prompting.py
└── cot_automation_agent.py

---

🧠 Techniques Implemented

1️⃣ One-Shot Prompting

Provides a single example to guide the model’s response.

Use case:

• Simple pattern learning
• Controlled output structure

---

2️⃣ Few-Shot Prompting

Provides multiple examples before the actual query.

Use case:

• Better context learning
• Improved consistency
• Format control

---

3️⃣ Chain-of-Thought Prompting

Encourages the model to reason step-by-step before producing the final answer.

Workflow: START → PLAN → OUTPUT

Use case:

• Mathematical problems
• Logical reasoning
• Multi-step queries

---

4️⃣ Chain-of-Thought Automation

An advanced reasoning agent that:

• Breaks problems into steps
• Calls external tools
• Maintains structured JSON output
• Automates reasoning cycles

Includes:

• Tool calling
• Pydantic structured parsing
• Iterative reasoning loop

---

🛠 Tech Stack

• Python
• OpenAI SDK
• Pydantic
• Requests
• JSON-based structured outputs

---

⚙️ Setup & Installation

1. Clone the repository:

git clone https://github.com/your-username/prompt-engineering-techniques.git

2. Create virtual environment:

python -m venv .venv

3. Activate environment:

.venv\Scripts\activate   (Windows)

4. Install dependencies:

pip install -r requirements.txt

5. Create a .env file (IMPORTANT)

In the root folder of the project, create a file named:
.env

Add your Google API key inside it:
GOOGLE_API_KEY=your_api_key_here

6. Run any file:

python one_shot_prompting.py

---

🎯 Learning Objectives

This repository demonstrates:

• Prompt design patterns
• Reasoning enhancement techniques
• Structured output parsing
• Tool-calling agents
• Iterative LLM workflows