Skip to content

Latest commit

 

History

History
352 lines (234 loc) · 17 KB

README.md

File metadata and controls

352 lines (234 loc) · 17 KB
Raw
page_type languages products urlFragment name description
sample
azdeveloper
python
js
typescript
bash
bicep
azure
azure-openai
azure-bing-web
azure-cognitive-search
contoso-creative-writer
Creative Writing Assistant - Working with Agents using Prompty (Python Implementation)
Using Azure OpenAI agent with Python, integrating Bing Search API and Azure AI Search, to create articles based on user topics and instruction.

Creative Writing Assistant: Working with Agents using Prompty (Python Implementation)

Open in GitHub Codespaces Open in Dev Containers

Table of Contents

App preview

Agent workflow preview

Contoso Creative Writer is an app that will help you write well researched, product specific articles. Enter the required information and then click "Start Work". To watch the steps in the agent workflow select the debug button in the bottom right corner of the screen. The result will begin writing once the agents complete the tasks to write the article.

This sample demonstrates how to create and work with AI agents driven by Azure OpenAI. It includes a FastAPI app that takes a topic and instruction from a user and then calls a research agent that uses the Bing Search API to research the topic, a product agent that uses Azure AI Search to do a semantic similarity search for related products from a vector store, a writer agent to combine the research and product information into a helpful article, and an editor agent to refine the article that's finally presented to the user.

Features

This project template provides the following features:

Architecture Digram

Azure account requirements

IMPORTANT: In order to deploy and run this example, you'll need:

Getting Started

You have a few options for setting up this project. The easiest way to get started is GitHub Codespaces, since it will setup all the tools for you, but you can also set it up locally.

GitHub Codespaces

  1. You can run this template virtually by using GitHub Codespaces. The button will open a web-based VS Code instance in your browser:

    Open in GitHub Codespaces

  2. Open a terminal window.

  3. Sign in to your Azure account. You'll need to login to both the Azure Developer CLI and Azure CLI:

    i. First with Azure Developer CLI

    azd auth login

    ii. Then sign in with Azure CLI

    az login --use-device-code

  4. Provision the resources and deploy the code:

    azd up

    You will be prompted to select some details about your deployed resources, including location. As a reminder we recommend Canada East as the region for this project. Once the deployment is complete you should be able to scroll up in your terminal and see the url that the app has been deployed to. It should look similar to this Ingress Updated. Access your app at https://env-name.codespacesname.eastus2.azurecontainerapps.io/. Navigate to the link to try out the app straight away!

  5. Once the above steps are completed you can test the sample.

VS Code Dev Containers

A related option is VS Code Dev Containers, which will open the project in your local VS Code using the Dev Containers extension:

  1. Start Docker Desktop (install it if not already installed)

  2. Open the project:

    Open in Dev Containers

  3. In the VS Code window that opens, once the project files show up (this may take several minutes), open a terminal window.

  4. Install required packages:

    cd src/api
pip install -r requirements.txt

    Once you've completed these steps jump to deployment.

Local environment

Prerequisites

Note for Windows users: If you are not using a container to run this sample, our hooks are currently all shell scripts. To provision this sample correctly while we work on updates we recommend using git bash.

Initializing the project

  1. Create a new folder and switch to it in the terminal, then run this command to download the project code:

    azd init -t agent-openai-python-prompty

    Note that this command will initialize a git repository, so you do not need to clone this repository.

  2. Install required packages:

    cd src/api
pip install -r requirements.txt

Deployment

Once you've opened the project in Codespaces, Dev Containers, or locally, you can deploy it to Azure.

  1. Sign in to your Azure account. You'll need to login to both the Azure Developer CLI and Azure CLI:

    i. First with Azure Developer CLI

    azd auth login

    ii. Then sign in with Azure CLI

    az login --use-device-code

    If you have any issues with that command, you may also want to try azd auth login --use-device-code.

    This will create a folder under .azure/ in your project to store the configuration for this deployment. You may have multiple azd environments if desired.

  2. Provision the resources and deploy the code:

    azd up

    This project uses gpt-35-turbo-0613,gpt-4-1106-Preview and gpt-4o-2024-05-13 which may not be available in all Azure regions. Check for up-to-date region availability and select a region during deployment accordingly. We recommend using Canada East for this project.

    After running azd up, you may be asked the following question during Github Setup:

    Do you want to configure a GitHub action to automatically deploy this repo to Azure when you push code changes?
(Y/n) Y

    You should respond with N, as this is not a necessary step, and takes some time to set up.

Testing the sample

This sample repository contains an agents folder that includes subfolders for each agent. Each agent folder contains a prompty file where the agent's prompty is defined and a python file with the code used to run it. Exploring these files will help you understand what each agent is doing. The agent's folder also contains an orchestrator.py file that can be used to run the entire flow and to create an article. When you ran azd up a catalogue of products was uploaded to the Azure AI Search vector store and index name contoso-products was created.

To test the sample:

  1. Run the example web app locally using a FastAPI server.

    First navigate to the src/api folder

    cd ./src/api

    Run the FastAPI webserver

    fastapi dev main.py

    Important Note: If you are running in Codespaces, you will need to change the visibility of the API's 8000 and 5173 ports to public in your VS Code terminal's PORTS tab. The ports tab should look like this:

    Screenshot showing setting port-visibility

    If you open the server link in a browser, you will see a URL not found error, this is because we haven't created a home url route in FastAPI. We have instead created a /get_article route which is used to pass context and instructions directly to the get_article.py file which runs the agent workflow.

    (Optional) We have created a web interface which we will run next, but you can test the API is working as expected by running this in the browser:

    http://127.0.0.1:8080/get_article?context=Write an article about camping in alaska&instructions=find specifics about what type of gear they would need and explain in detail

  2. Once the FastAPI server is running you can now run the web app. To do this open a new terminal window and navigate to the web folder using this command:

    cd ./src/web

    First install node packages:

    npm install

    Then run the web app with a local dev web server:

    npm run dev

    This will launch the app, where you can use example context and instructions to get started. On the 'Creative Team' page you can examine the output of each agent by clicking on it. The app should look like this:

    Change the instructions and context to create an article of your choice.

  3. For debugging purposes you may want to test in Python using the orchestrator Logic

    To run the sample using just the orchestrator logic use the following command:

    cd ./src/api
python -m orchestrator

Tracing

To activate the Prompty tracing server:

export LOCAL_TRACING=true

Then start the orchestrator:

cd ./src/api
python -m orchestrator

Once you can see the article has been generated, a .runs folder should appear in the ./src/api . Select this folder and click the .tracy file in it. This shows you all the Python functions that were called in order to generate the article. Explore each section and see what helpful information you can find.

Evaluating results

Contoso Creative Writer uses evaluators to assess application response quality. The 4 metrics the evaluators in this project assess are Coherence, Fluency, Relevance and Groundedness. A custom evaluate.py script has been written to run all evaulations for you.

  1. To run the script run the following commands:
cd ./src/api
python -m evaluate.evaluate
  • Check: You see scores for Coherence, Fluency, Relevance and Groundedness.
  • Check: The scores are between 1 and 5
  1. To understand what is being evaluated open the src/api/evaluate/eval_inputs.jsonl file.
    • Observe that 3 examples of research, product and assignment context are stored in this file. This data will be sent to the orchestrator so that each example will have:
    • each example will have the evaluations run and will incoperate all of the context, research, products, and final article when grading the response.

Setting up CI/CD with GitHub actions

This template is set up to run CI/CD when you push changes to your repo. When CI/CD is configured, evaluations will in GitHub actions and then automatically deploy your app on push to main.

To set up CI/CD with GitHub actions on your repository, run the following command:

azd pipeline config

Guidance

Region Availability

This template uses gpt-35-turbo-0613,gpt-4-1106-Preview and gpt-4o-2024-05-13 which may not be available in all Azure regions. Check for up-to-date region availability and select a region during deployment accordingly

  • We recommend using Canada East

Costs

You can estimate the cost of this project's architecture with Azure's pricing calculator

Security

Note

When implementing this template please specify whether the template uses Managed Identity or Key Vault

This template has either Managed Identity or Key Vault built in to eliminate the need for developers to manage these credentials. Applications can use managed identities to obtain Microsoft Entra tokens without having to manage any credentials. Additionally, we have added a GitHub Action tool that scans the infrastructure-as-code files and generates a report containing any detected issues. To ensure best practices in your repo we recommend anyone creating solutions based on our templates ensure that the Github secret scanning setting is enabled in your repos.

Resources

Code of Conduct

This project has adopted the Microsoft Open Source Code of Conduct.

Resources:

For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Responsible AI Guidelines

This project follows below responsible AI guidelines and best practices, please review them before using this project: