promptflow
Prompt flow Python SDK - build high-quality LLM apps
Decision gist · record as of 2026-08-14
Yes. Prompt flow is actively maintained, has no known vulnerabilities, installs with low friction, and is MIT-licensed. It directly addresses the full development lifecycle for LLM applications—from prototyping to production—with a mature CLI and integration points. Install it if you are building or managing LLM-based applications and want structured tooling for testing, evaluation, and deployment.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.9, 3.10, or 3.11; Python 3.8 support was dropped in v1.17.0 for security reasons.
- Low friction installation as a pure Python wheel.
- Actively maintained with recent releases; last commit 2026-08-05.
License · maintenance · safety
MIT License (permissive) — MIT License permits commercial and private use with minimal restrictions, making it suitable for both open-source and proprietary LLM applications.
last release 2026-05-01 (105 days) · last repo commit 2026-08-05 · 11,218 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 82,848 downloads/mo, #14,127 on PyPI
Alternatives
Verify before relying
pip install promptflow
pf flow init --flow ./my_chatbot --type chat
pf connection create --file ./my_chatbot/openai.yaml --set api_key=<key> --name open_ai_connection
pf flow test --flow ./my_chatbot --interactive- Whether the three runtime dependencies (promptflow-tracing, promptflow-core, promptflow-devkit) are installable independently or only as part of this package.
- Performance characteristics when working with large datasets or complex multi-node flows.
- Compatibility with specific LLM providers beyond OpenAI and Azure OpenAI mentioned in the quick start.
What it is and what it does
Prompt flow is Microsoft's end-to-end development toolkit for LLM applications. It provides a structured way to create flows that combine language models, Python code, and external tools, then test, evaluate, and deploy them. The package includes CLI tools for initializing flows from templates (like chat), managing API connections, and running interactive tests. It emphasizes production-quality development with built-in tracing to debug LLM interactions, evaluation capabilities for assessing flow quality on larger datasets, and integration with CI/CD pipelines.
The package depends on three internal subpackages: promptflow-tracing for instrumentation, promptflow-core for runtime execution, and promptflow-devkit for local development and testing. It supports Python 3.9 through 3.11 and is actively maintained by Microsoft, with recent security fixes and improvements documented in the release history.
Use it for
- Build and iterate on chatbot flows using the CLI template system and interactive testing mode.
- Evaluate LLM application quality by running flows against test datasets and integrating results into CI/CD.
- Debug LLM interactions with built-in tracing to understand how prompts and model outputs flow through your application.
- Deploy flows to production or integrate them into existing applications with connection management for API keys.
- Collaborate on LLM projects using the optional Azure AI cloud version for team-based development.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
Prompt flow is actively maintained, has no known vulnerabilities, installs with low friction, and is MIT-licensed. It directly addresses the full development lifecycle for LLM applications—from prototyping to production—with a mature CLI and integration points. Install it if you are building or managing LLM-based applications and want structured tooling for testing, evaluation, and deployment.
Install
promptflow on PyPI
Before you install
Low friction installation as a pure Python wheel. Actively maintained with recent releases; last commit 2026-08-05. Depends on three internal subpackages (promptflow-tracing, promptflow-core, promptflow-devkit) that ship together.
Requires Python 3.9, 3.10, or 3.11; Python 3.8 support was dropped in v1.17.0 for security reasons.
License in practice
MIT License permits commercial and private use with minimal restrictions, making it suitable for both open-source and proprietary LLM applications.
Quickstart
pip install promptflow
pf flow init --flow ./my_chatbot --type chat
pf connection create --file ./my_chatbot/openai.yaml --set api_key=<key> --name open_ai_connection
pf flow test --flow ./my_chatbot --interactiveVerify before relying
- Whether the three runtime dependencies (promptflow-tracing, promptflow-core, promptflow-devkit) are installable independently or only as part of this package.
- Performance characteristics when working with large datasets or complex multi-node flows.
- Compatibility with specific LLM providers beyond OpenAI and Azure OpenAI mentioned in the quick start.
Package facts
| License | MIT License permissive |
| Python support | Supports the current Python release <4.0,>=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 3 packagespromptflow-tracingpromptflow-corepromptflow-devkit |
| Maintenance | Actively maintained 105 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 82,848 / month, #14,127 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: MIT LicenseOperating System :: OS IndependentProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.9 |
Evidence: promptflow-1.18.5-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “prompt engineering workflow tool”
- promptflowPrompt flow is a development suite for building, testing, and…
- pomlPOML is a markup language and Python SDK for structuring, templating,…
- inspect-aiInspect is a framework for evaluating large language models,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also promptflow-core · promptflow-devkit · prompty · vellum-ai · promptflow-tracing · promptlayer · lfx · poml · mlflow · pdd-cli