grompt 0.2.1

Git for prompts - Manage LLM prompts with version control

Grompt - Git for Prompts

Version, test, and manage LLM prompts separately from code.

Grompt lets you store prompts as YAML files, version them with git, test them with real data, and use them in your code by ID. Change prompts without deploying code.

---

Why Grompt?

Problem: Prompts buried in code are hard to version, test, and optimize. Solution: Prompts as files, referenced by ID.

Benefits:

• ✅ Change prompts without touching code
• ✅ Version prompts with git
• ✅ Test prompts with real data
• ✅ Track which version is in production

---

Installation

Install Grompt via pip:

pip install grompt

For development installation:

pip install -e ".[dev]"

---

Quick Start

1. Initialize Grompt

Initialize Grompt in your project root. This creates a .grompt config file and a prompts directory.

grompt init

2. Create a Prompt

Create a new prompt named code-review.

grompt add code-review --template "Review this code:\n{{ code }}"

This creates prompts/code-review.yaml.

3. Test it with Data

Run the prompt with sample data to verify the output.

grompt test code-review --var code="def hello(): pass"

4. Use in Python

Load and use the prompt in your application.

import grompt

# Load the prompt
prompt = grompt.load("code-review")

# Render with variables
rendered = prompt.render(
    code="def add(a,b): return a+b"
)
print(rendered)

---

Documentation

• Defining Prompts - Learn how to create prompts with variables, system messages, and more.
• Using Prompts - How to use prompts in your CLI and Python code.
• Testing Prompts - Creating test cases and running tests.
• Variable Validation - Ensuring inputs match expected schemas.
• CLI Reference - Complete command-line interface documentation.
• Python API - API reference for integrating Grompt.
• Configuration - Global configuration options.
• Best Practices - Tips for managing prompts effectively.
• Examples - Real-world usage examples.

---

License

MIT