🎯 Lecture Goal

Learn the two core principles of prompt engineering and how to apply them with practical tactics.

🔧 Setup with Groq API

pip install groq

from groq import Groq

client = Groq(api_key="YOUR_GROQ_API_KEY")  # or set env var GROQ_API_KEY

def get_completion(prompt, model="llama3-8b-8192"):
    messages = [{"role": "user", "content": prompt}]
    response = client.chat.completions.create(
        model=model,
        messages=messages,
        temperature=0
    )
    return response.choices[0].message.content

💡 Groq models to use: llama3-8b-8192, llama3-70b-8192, mixtral-8x7b-32768

📝 Key Concepts

✏️ Principle 1 — Write Clear & Specific Instructions

Clear ≠ Short. Longer prompts often give better results.

Tactic 1 — Use Delimiters

Clearly separate input text from instructions to avoid prompt injection.

text = """You should express what you want a model to do by providing \
instructions that are as clear and specific as you can possibly make them."""

prompt = f"""
Summarize the text delimited by triple backticks into a single sentence.

"""

print(get_completion(prompt))

> Delimiters: ` ``` `, `"""`, `< >`, `---`, XML tags, section titles

---

#### Tactic 2 — Ask for Structured Output

prompt = """

Generate a list of 3 made-up book titles with authors and genres.