Prompt flow devkit

Welcome to join us to make prompt flow better by participating discussions, opening issues, submitting PRs.

Introduction

The promptflow-devkit is a subpackage of promptflow. It contains features like :

Create and iteratively develop flow
- Debug and iterate your flows, especially the interaction with LLMs with ease.
- Provide Tracing collector and UI to help user achieve comprehensive observability of their LLM applications.
Evaluate flow quality and performance
- Evaluate your flow's quality and performance with larger datasets.
- Integrate the testing and evaluation into your CI/CD system to ensure quality of your flow.
Streamlined development cycle for production
- Deploy your flow to the serving platform you choose or integrate into your app's code base easily.

NOTE:

For users seeking a minimal dependency to execute a flow in serving or cloud run scenarios, consider installing the promptflow-core package. This package equips you with the fundamental features necessary for executing a flow in prompt flow.
For users need to leverage the cloud version of prompt flow in Azure AI, please install the promptflow-azure package.

Reach the full change log here.

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Table of built distributions (wheels) for promptflow-devkit 1.18.5
File	Interpreter	ABI	Platform	Reset
promptflow_devkit-1.18.5-py3-none-any.whl 7.0 MB May 1, 2026	Python 3	none	any	Details

Download URL	promptflow_devkit-1.18.5-py3-none-any.whl
Size	7.0 MB
Tags	Python 3
SHA-256 checksum How to use checksums	`f12a2baac5953556de5969fb29e244ea54359f9b8a9aea5e01550e47d22b49fe`
BLAKE2b-256 checksum How to use checksums	`bb9f7219c09ef4e33da5d3ae2292f7b0ce884206d602a2533639b46b3f6facaf`
Upload date	May 1, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.9.25`