llm-prompt-engine 1.1.0

Safe LLM prompt templating with validation guards

Prompt Template Engine

A Python template engine designed for safe LLM prompt management with built-in validation guards and variable constraints.

Features

• Template Registration: Register named templates with validation guards
• Variable Guards: Enforce min/max length, regex patterns, choices, and custom validators
• Safe Rendering: Automatic variable substitution with error checking
• Random Rendering: Pick random templates for A/B testing or variety
• Template Lookup: Check existence and list all registered templates

Installation

pip install prompt-template-engine

Quick Start

from prompt_template_engine import TemplateEngine, GuardCondition

engine = TemplateEngine()

engine.add_template("hello", "Hello, {name}!", {"name": GuardCondition(name="name", min_length=1)})

result = engine.render("hello", {"name": "World"})
# Returns: "Hello, World!"

API Reference

TemplateEngine

The main engine class for registering and rendering templates.

engine = TemplateEngine()
engine.add_template(name, template_str, guards)
engine.render(name, variables)
engine.has_template(name)
engine.get_template(name)
engine.list_templates()
engine.random()
engine.random_render(variables)

GuardCondition

A dataclass defining validation rules for template variables:

• name: Variable name
• min_length / max_length: String length constraints
• regex: Regular expression pattern
• choices: Allowed string values
• validator: Custom validation function

TemplateTemplate

A reusable template with name, body, and associated guards.

License

MIT