promptlab 0.1.0

PromptLab is a free, lightweight, open-source experimentation tool for Gen AI applications.

PromptLab

A free, lightweight, open-source experimentation tool for Gen AI applications

📋 Table of Contents

• Overview
• Features
• Installation
• Quick Start
• Core Concepts
• Documentation
• Supported Models
• Examples
• Articles & Tutorials
• Contributing
• License

Overview 🔍

PromptLab is a free, lightweight, open-source experimentation tool for Gen AI applications. It streamlines prompt engineering, making it easy to set up experiments, evaluate prompts, and track them in production - all without requiring any cloud services or complex infrastructure.

With PromptLab, you can:

• Create and manage prompt templates with versioning
• Build and maintain evaluation datasets
• Run experiments with different models and prompts
• Evaluate model and prompt performance using built-in and custom metrics
• Compare experiment results side-by-side
• Deploy optimized prompts to production

Features ✨

• Truly Lightweight: No cloud subscription, no additional servers, not even Docker - just a simple Python package
• Easy to Adopt: No ML or Data Science expertise required
• Self-contained: No need for additional cloud services for tracking or collaboration
• Seamless Integration: Works within your existing web, mobile, or backend project
• Flexible Evaluation: Use built-in metrics or bring your own custom evaluators
• Web Interface: Compare experiments and track assets through a web interface
• Multiple Model Support: Works with Azure OpenAI, Ollama, DeepSeek and more. You can also bring your ownd model.
• Version Control: Automatic versioning of all assets for reproducibility
• Async Support: Run experiments and invoke models asynchronously for improved performance

Installation 📦

pip install promptlab

It's recommended to use a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install promptlab

Quick Start 🚀

Check the quick start example here - samples/quickstart

Core Concepts 🧩

Tracer

Tracer is responsible for persisting and updating assets and experiments in the storage layer. At present, only SQLite is supported.

Assets

Immutable artifacts used in experiments, with automatic versioning:

• Prompt Templates: Prompts with optional placeholders for dynamic content
• Datasets: JSONL files containing evaluation data

Experiments

Evaluate prompts against datasets using specified models and metrics.

PromptLab Studio

A web interface for visualizing experiments and comparing results.

Documentation 📖

For comprehensive documentation, visit our Documentation Page.

Supported Models 🤖

• Azure OpenAI: Connect to Azure-hosted OpenAI models
• Ollama: Run experiments with locally-hosted models
• OpenRouter: Access a wide range of AI models (OpenAI, Anthropic, DeepSeek, Mistral, etc.) via OpenRouter API
• Custom Models: Integrate your own model implementations

Examples 📚

• Quickstart: Getting started with PromptLab
• Asset versioning: Versioning Prompts and Datasets
• Custom Metric: Creating custom evaluation metrics
• Async Example: Using async functionality with Ollama and OpenRouter models for improved performance
• Custom Model: Bring your own model for evaluation

Articles & Tutorials 📝

• Evaluating prompts locally with Ollama and PromptLab
• Creating custom prompt evaluation metrics with PromptLab

CI/CD 🔄

PromptLab uses GitHub Actions for continuous integration and testing:

• Unit Tests: Run unit tests for all components of PromptLab
• Integration Tests: Run integration tests that test the interaction between components
• Performance Tests: Run performance tests to ensure performance requirements are met

The tests are organized into the following directories:

• tests/unit/: Unit tests for individual components
• tests/integration/: Tests that involve multiple components working together
• tests/performance/: Tests that measure performance
• tests/fixtures/: Common test fixtures and utilities

You can find more information about the CI/CD workflows in the .github/workflows directory.

Contributing 👥

Contributions are welcome! Please feel free to submit a Pull Request.

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

License 📄

This project is licensed under the MIT License - see the LICENSE file for details.