get started with Prompt flow

Author: ks6088ts

README.md

@@ -40,6 +40,7 @@ Here are the preferred tools for development.
 | [8_streamlit_azure_openai_batch](./apps/8_streamlit_azure_openai_batch/README.md)                   | Call Azure OpenAI Batch API with Streamlit              | ![8_streamlit_azure_openai_batch](./docs/images/8_streamlit_azure_openai_batch.main.png)                   |
 | [9_streamlit_azure_document_intelligence](./apps/9_streamlit_azure_document_intelligence/README.md) | Call Azure AI Document Intelligence API with Streamlit  | ![9_streamlit_azure_document_intelligence](./docs/images/9_streamlit_azure_document_intelligence.main.png) |
 | [10_streamlit_batch_transcription](./apps/10_streamlit_batch_transcription/README.md)               | Call Batch Transcription API with Streamlit             | ![10_streamlit_batch_transcription](./docs/images/10_streamlit_batch_transcription.main.png)               |
+| [11_promptflow](./apps/11_promptflow/README.md)                                                     | Get started with Prompt flow                            | No Image                                                                                                   |
 | [99_streamlit_examples](./apps/99_streamlit_examples/README.md)                                     | Code samples for Streamlit                              | ![99_streamlit_examples](./docs/images/99_streamlit_examples.explaindata.png)                              |
 
 ## How to run

apps/11_promptflow/.gitignore

@@ -0,0 +1 @@
+**/.promptflow/*

apps/11_promptflow/README.md

@@ -0,0 +1,72 @@
+# Getting Started with Prompt flow
+
+This application explains how to get started with [Prompt flow](https://github.com/microsoft/promptflow), a Python library that provides a simple and easy way to build conversational AI applications.
+
+## Prerequisites
+
+- Python 3.10 or later
+- Azure OpenAI Service
+
+## Overview
+
+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.
+
+## Usage
+
+1. Get the API key for Azure OpenAI Service
+1. Copy [.env.template](../../.env.template) to `.env` in the same directory
+1. Set credentials in `.env`
+1. Run scripts in the [apps/11_promptflow](./) directory
+
+Set up the environment and install dependencies:
+
+```shell
+# Create a virtual environment
+$ python -m venv .venv
+
+# Activate the virtual environment
+$ source .venv/bin/activate
+
+# Install dependencies
+$ pip install -r requirements.txt
+```
+
+## Examples
+
+[Prompt flow > Quick start](https://microsoft.github.io/promptflow/how-to-guides/quick-start.html) provides a quick start guide to Prompt flow.
+
+### [chat_minimal](https://github.com/microsoft/promptflow/tree/main/examples/flex-flows/chat-minimal)
+
+**Run as normal Python script**
+
+```shell
+$ python apps/11_promptflow/chat_minimal/main.py
+```
+
+**Run from CLI**
+
+```shell
+$ cd apps/11_promptflow/chat_minimal
+
+# Test flow
+$ pf flow test \
+    --flow main:chat \
+    --inputs question="What's the capital of France?"
+
+# Test flow: multi turn, access to http://localhost:{EPHEMERAL_PORT}
+$ pf flow test \
+    --flow main:chat \
+    --ui
+
+# Create run with multiple lines data
+$ pf run create \
+    --flow main:chat \
+    --data ./data.jsonl \
+    --column-mapping question='${data.question}' \
+    --stream
+```
+
+## References
+
+- [Prompt flow > repos](https://github.com/microsoft/promptflow)
+- [Prompt flow > documents](https://microsoft.github.io/promptflow/)

apps/11_promptflow/chat_minimal/chat.prompty

@@ -0,0 +1,22 @@
+---
+name: Minimal Chat
+model:
+  api: chat
+  configuration:
+    type: azure_openai
+    azure_deployment: gpt-4o
+  parameters:
+    temperature: 0.2
+    max_tokens: 1024
+inputs:
+  question:
+    type: string
+sample:
+  question: "What is Prompt flow?"
+---
+
+system:
+You are a helpful assistant.
+
+user:
+{{question}}

apps/11_promptflow/chat_minimal/data.jsonl

@@ -0,0 +1,2 @@
+{"question": "What is Prompt flow?"}
+{"question": "What is ChatGPT? Please explain with consise statement"}

apps/11_promptflow/chat_minimal/main.py

@@ -0,0 +1,21 @@
+from pathlib import Path
+
+from dotenv import load_dotenv
+from promptflow.core import Prompty
+from promptflow.tracing import start_trace, trace
+
+BASE_DIR = Path(__file__).absolute().parent
+
+
+@trace
+def chat(question: str) -> str:
+    load_dotenv()
+    prompty = Prompty.load(source=f"{BASE_DIR}/chat.prompty")
+    return prompty(question=question)
+
+
+if __name__ == "__main__":
+    start_trace()
+
+    result = chat("What's the capital of France?")
+    print(result)