LLM Quick Tools ⚡

A lightweight dual-purpose library for:

1. Prompt Evaluation - Score and improve LLM inputs
2. Mock LLM - Simulate API responses during development

Installation

pip install llm-quick-tools

1. Prompt Scoring 🔍

Evaluate prompt quality across multiple dimensions.

Quick Start

from llm_quick_tools import PromptEvaluator

evaluator = PromptEvaluator()
scores = evaluator.evaluate(
    "Explain quantum computing to a 5-year-old",
    task="education"
)

print(scores)

Output:

{
    'length': 0.38,        # Optimal 20-100 chars
    'clarity': 0.9,        # Sentence structure
    'toxicity': 0.02,      # Harmful content risk
    'task_alignment': 0.8  # Relevance to education
}

Scoring Metrics

2. Mock LLM 🤖

Simulate LLM responses without API calls.

Response Modes

from llm_quick_tools import MockLLM

# Initialize with different modes
echo_llm = MockLLM(mode="echo")
template_llm = MockLLM(mode="template")

Mode Comparison

Template Management

# Add custom templates
template_llm.add_template(
    "contact support",
    "Email us at help@company.com"
)

# Load from JSON
template_llm.load_templates("path/to/templates.json")

# Generate responses
print(template_llm.generate("How to contact support?"))
# Output: "Email us at help@company.com"

Pre-Loaded Templates

{
    "hello": "Hi! How can I help?",
    "goodbye": "Have a nice day!",
    "pricing": "Our plans start at $9.99/mo",
    "refund": "Refunds take 5-7 business days",
    "tech support": "Try restarting your device"
}

Advanced Usage

Combined Workflow

# 1. Evaluate prompt
scores = evaluator.evaluate("Tell me a joke about AI")

# 2. Generate mock response
if scores['toxicity'] < 0.1:
    response = template_llm.generate("Tell me a joke about AI")
else:
    response = "I can't comply with that request"

Custom Template JSON

// custom_templates.json
{
    "feature request": "Added to our roadmap",
    "bug report": "We'll investigate this issue",
    "order {} status": "Order #{} ships in 2 days"
}

Use Cases

• Testing - Verify LLM integration logic
• Development - Prototype before API integration
• Education - Teach prompt engineering concepts
• CI/CD - Run deterministic tests in pipelines

Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/AmazingFeature)
3. Commit changes (git commit -m 'Add feature')
4. Push (git push origin feature/AmazingFeature)
5. Open a Pull Request

License

MIT © Aryan