promptflow

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

What is promptflow?

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

Overview of promptflow

What it is

Prompt flow is a suite of development tools designed to streamline the end-to-end development cycle of LLM-based AI applications, from ideation, prototyping, testing, evaluation to production deployment and monitoring. It is no longer recommended for new development; existing applications should be migrated to Microsoft Agent Framework before April 20, 2027. Prompt flow container images are no longer receiving updates.

Key features

  • Create executable flows that link LLMs, prompts, Python code and other tools together.
  • Debug and iterate flows, especially tracing interaction with LLMs.
  • Evaluate flow quality and performance with larger datasets.
  • Integrate testing and evaluation into CI/CD systems.
  • Deploy flows to a serving platform or integrate into app code.
  • Collaborate with team using the cloud version in Azure AI (optional).

Use cases

  • Prototyping and iterating on LLM-based applications.
  • Testing and evaluating flow quality and performance.
  • Production deployment and monitoring of LLM apps.
  • Integrating LLM workflows into CI/CD pipelines.

Getting started

See the repository README for installation instructions.

License and pricing

MIT License, open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/microsoftpromptflow.svg)](https://yunodb.com/tools/microsoftpromptflow?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/microsoftpromptflow?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/microsoftpromptflow.svg" alt="Featured on YunoDB" height="20"></a>