prompty

What it is and what it does

Prompty is a Python runtime that executes LLM prompts stored in a standardized `.prompty` file format. The format combines YAML metadata (model configuration, sample inputs, authors) with prompt templates written in Jinja2, allowing you to define and version control prompts separately from application code. The runtime loads these files, interpolates variables, and routes execution to the appropriate LLM API (Azure OpenAI, OpenAI, or serverless models via Azure AI Inference).

The package is designed to accelerate prompt engineering workflows by providing observability through a pluggable tracing system—built-in tracers write execution details to console or JSON files, and you can integrate OpenTelemetry or custom hooks. It includes a CLI tool for running prompts directly from the command line and a VS Code extension for interactive prompt development. Dependencies are minimal: pyyaml for config parsing, jinja2 for templating, python-dotenv for environment variables, click for CLI, and aiofiles for async file operations.

Use it for:

• Run and iterate on LLM prompts defined in `.prompty` files without embedding them in Python code, enabling non-developers to edit prompts via VS Code.
• Trace and debug LLM API calls and prompt execution with built-in console or JSON output, or integrate with OpenTelemetry for centralized observability.
• Execute prompts from the command line with environment variable injection, useful for CI/CD pipelines or batch prompt testing.
• Switch between Azure OpenAI, OpenAI, and serverless model endpoints by changing configuration in the `.prompty` file without code changes.
• Build reusable prompt libraries with version control, sample inputs, and metadata for team collaboration on prompt engineering.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Prompty is a Python runtime for executing LLM prompts defined in a language-agnostic `.prompty` file format, with built-in support for Azure OpenAI, OpenAI, and serverless model invokers, plus tracing and CLI tooling.

Yes, with conditions. Install if you need a structured, version-controlled way to manage and execute LLM prompts across multiple endpoints (Azure, OpenAI, serverless) with built-in tracing and CLI support. The low install friction and active maintenance are favorable. However, verify the status of the two known vulnerabilities (GHSA-wxhm-2mq7-7697, PYSEC-2026-3538) before deploying to production, and confirm whether optional invoker dependencies require explicit extras installation.

Install

prompty on PyPI

pip install prompty

uv add prompty

poetry add prompty

Installing prompty

Before you install

Low install friction with a pure-Python wheel and five lightweight runtime dependencies. The package is actively maintained with recent commits and a steady release cadence since July 2024.

License in practice

MIT license permits unrestricted use, modification, and distribution with minimal restrictions, making it suitable for commercial and open-source projects alike.

Quickstart

pip install prompty

import prompty
import prompty.azure

response = prompty.execute("path/to/prompt.prompty")
print(response)

Requires Python >= 3.9. To use Azure OpenAI invoker, install with: pip install "prompty[azure]". Prompty files must reference a valid LLM endpoint via environment variables or configuration.

Verify before relying

• Whether the two known vulnerabilities (GHSA-wxhm-2mq7-7697, PYSEC-2026-3538) affect the current version or have been patched.
• Whether optional dependencies (e.g., for Azure or OpenAI invokers) are automatically installed or require explicit extras installation.
• Performance characteristics and latency overhead of the tracing mechanism in production workloads.

Package facts

Evidence: prompty-0.1.50-py3-none-any.whl

Tags

More Artificial Intelligence packages