Tutorials#

This section contains a collection of flow samples and step-by-step tutorials.

Area	Sample	Description
SDK	Getting started with prompt flow	A step by step guidance to invoke your first flow run.
CLI	Chat with PDF	An end-to-end tutorial on how to build a high quality chat application with prompt flow, including flow development and evaluation with metrics.
SDK	Chat with PDF - test, evaluation and experimentation	We will walk you through how to use prompt flow Python SDK to test, evaluate and experiment with the “Chat with PDF” flow.
SDK	Connection management	Manage various types of connections using sdk
CLI	Working with connection	Manage various types of connections using cli
SDK	Run prompt flow in Azure AI	A quick start tutorial to run a flow in Azure AI and evaluate it.
SDK	Flow run management in Azure AI	Flow run management in azure AI

Samples#

Area	Sample	Description
Standard Flow	basic	a basic flow with prompt and python tool.
Standard Flow	basic-with-connection	a basic flow using custom connection with prompt and python tool
Standard Flow	basic-with-builtin-llm	a basic flow using builtin llm tool
Standard Flow	customer-intent-extraction	a flow created from existing langchain python code
Standard Flow	web-classification	a flow demonstrating multi-class classification with LLM. Given an url, it will classify the url into one web category with just a few shots, simple summarization and classification prompts.
Standard Flow	autonomous-agent	a flow showcasing how to construct a AutoGPT flow to autonomously figures out how to apply the given functions to solve the goal, which is film trivia that provides accurate and up-to-date information about movies, directors, actors, and more.
Chat Flow	chat-with-wikipedia	a flow demonstrating Q&A with GPT3.5 using information from Wikipedia to make the answer more grounded.
Chat Flow	chat-with-pdf	a flow that allow you to ask questions about the content of a PDF file and get answers.
Evaluation Flow	eval-classification-accuracy	a flow illustrating how to evaluate the performance of a classification system.