microsoft /promptflow
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
★ 11,265⑂ 1,127👁 110⑃ 3,188● 722▤ 42
More from this author
+0
Daily
+5
Weekly
+12
Monthly
11,265
stars
1,127
forks
110
watchers
3,188
prs
722
issues
42
releases
README
Prompt flow
[!WARNING]
Prompt flow in Microsoft Foundry and Azure Machine Learning will be retired on April 20, 2027. Prompt flow is no longer recommended for new development. Migrate existing Prompt flow applications and deployments to Microsoft Agent Framework before April 20, 2027.
Prompt flow container images are no longer receiving updates, including security and package updates. This applies to Prompt flow runtime images, including promptflow-runtime, promptflow-runtime-stable, and promptflow-python.
After April 20, 2027, Prompt flow, including the web authoring experience in Microsoft Foundry and Azure Machine Learning, the VS Code extensions, and related Prompt flow container images, will no longer be supported or available.
If your application depends on Prompt flow deployments or runtime images, plan to move those workloads to supported alternatives such as Microsoft Agent Framework before the retirement date. For migration guidance, see the Prompt flow migration guide and migration code samples.
Welcome to join us to make prompt flow better by
participating discussions,
opening issues,
submitting PRs.
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 makes prompt engineering much easier and enables you to build LLM apps with production quality.
With prompt flow, you will be able to:
- Create and iteratively develop flow
- Create executable flows that link LLMs, prompts, Python code and other tools together.
- Debug and iterate your flows, especially tracing interaction with LLMs with ease.
- 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.
- (Optional but highly recommended) Collaborate with your team by leveraging the cloud version of Prompt flow in Azure AI.
------
Installation
To get started quickly, you can use a pre-built development environment. Click the button below to open the repo in GitHub Codespaces, and then continue the readme!
If you want to get started in your local environment, first install the packages:
Ensure you have a python environment, python=3.9, --name open_ai_connection
For Azure OpenAI key, establish the connection by running the command, using the azure_openai.yaml file:
sh
pf connection create --file ./my_chatbot/azure_openai.yaml --set api_key= api_base= --name open_ai_connection
Chat with your flow
In the my_chatbot folder, there's a flow.dag.yaml file that outlines the flow, including inputs/outputs, nodes, connection, and the LLM model, etc
Note that in the chat noTop issues
#3931Request: Please release promptflow-tools42 comments · 2025-01-20#1317C# Flow Creation22 comments · 2023-11-29#2102[Feature Request]: Using Managed Identity (RBAC) instead of basic key autentication for Connections15 comments · 2024-02-25#3528[Feature Request] Have option to return trace as part of out put of a PromptFlow when deployed as endpoint12 comments · 2024-07-09#3555[FeatureAsk] Instantiating a model config for Azure OAI using AAD instead of `api_key`11 comments · 2024-07-17#1899[Feature Request] Logging statements are not present in log output10 comments · 2024-01-31#3209[Feature Request] Improve compatibility between PromptFlow and Python modules with relative imports9 comments · 2024-05-10#944[Feature Request] Allow any combination of variants to be selected for a run9 comments · 2023-10-27
Discussions
#4234PromptFlow CLI included in AgentManager's tool catalog0 comments · 2026-10-18#4222Recording a prompty flow and replaying it offline — and one misleading error message0 comments · 2026-09-12#4206How Ontora's (a prestigious YC company) Interview-to-Map Architecture Works — A Technical Reconstruction0 comments · 2026-07-31#4182Open source LLM evaluation: accuracy + cost + hallucination for flow evaluation0 comments · 2026-06-08#4127[招聘] Prompt工程师 + AI Infra工程师 | AI营销决策引擎 | 北大/康奈尔/TikTok背景团队 | 杭州0 comments · 2026-04-06#4096ORCH — CLI runtime I built for orchestrating long-running coding agents with state machine + retries0 comments · 2026-03-17#4094ORCH — CLI runtime for orchestrating AI agent teams (Claude Code, Codex, Cursor)0 comments · 2026-03-17#3998promptflow fails to create connection in python 3.12.10, which is perfectly working in ptyhon 3.10.14 in Docker container,1 comments · 2025-04-16
Latest release
promptflow 1.17.1 promptflow_1.17.1 2025-01-09We are pleased to announce the release of promptflow 1.17.1. This release includes some new features, bug fixes, and improvements. We recommend that all users upgrade to this version. See the CHANGELOG for a list of all the changes. The release will be available via PyPI: bash pip install --upgrade promptflow Please report any issues with the release on the promptflow issue tracker. Thanks to all the contributors who made this release possible.