|
| 1 | +# Guide to local development |
| 2 | + |
| 3 | +## Requirements: |
| 4 | + |
| 5 | +- Python 3.10 or higher + PIP |
| 6 | +- Azure CLI, and an Azure Subscription |
| 7 | +- Visual Studio Code IDE |
| 8 | + |
| 9 | +# Local setup |
| 10 | + |
| 11 | +> **Note for macOS Developers**: If you are using macOS on Apple Silicon (ARM64) the DevContainer will **not** work. This is due to a limitation with the Azure Functions Core Tools (see [here](https://github.com/Azure/azure-functions-core-tools/issues/3112)). We recommend using the [Non DevContainer Setup](./NON_DEVCONTAINER_SETUP.md) instructions to run the accelerator locally. |
| 12 | +
|
| 13 | +The easiest way to run this accelerator is in a VS Code Dev Containers, which will open the project in your local VS Code using the [Dev Containers extension](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers): |
| 14 | + |
| 15 | +1. Start Docker Desktop (install it if not already installed) |
| 16 | +1. Open the project: |
| 17 | + [](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator) |
| 18 | + |
| 19 | +1. In the VS Code window that opens, once the project files show up (this may take several minutes), open a terminal window |
| 20 | + |
| 21 | +## Detailed Development Container setup instructions |
| 22 | + |
| 23 | +The solution contains a [development container](https://code.visualstudio.com/docs/remote/containers) with all the required tooling to develop and deploy the accelerator. To deploy the Multi Agent Solution accelerator using the provided development container you will also need: |
| 24 | + |
| 25 | +* [Visual Studio Code](https://code.visualstudio.com) |
| 26 | +* [Remote containers extension for Visual Studio Code](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers) |
| 27 | + |
| 28 | +If you are running this on Windows, we recommend you clone this repository in [WSL](https://code.visualstudio.com/docs/remote/wsl) |
| 29 | + |
| 30 | +```cmd |
| 31 | +git clone https://github.com/microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator |
| 32 | +``` |
| 33 | + |
| 34 | +Open the cloned repository in Visual Studio Code and connect to the development container. |
| 35 | + |
| 36 | +```cmd |
| 37 | +code . |
| 38 | +``` |
| 39 | + |
| 40 | +!!! tip |
| 41 | + Visual Studio Code should recognize the available development container and ask you to open the folder using it. For additional details on connecting to remote containers, please see the [Open an existing folder in a container](https://code.visualstudio.com/docs/remote/containers#_quick-start-open-an-existing-folder-in-a-container) quickstart. |
| 42 | + |
| 43 | +When you start the development container for the first time, the container will be built. This usually takes a few minutes. **Please use the development container for all further steps.** |
| 44 | + |
| 45 | +The files for the dev container are located in `/.devcontainer/` folder. |
| 46 | + |
| 47 | +## Local deployment and debugging: |
| 48 | + |
| 49 | +1. **Clone the repository.** |
| 50 | + |
| 51 | +2. **Log into the Azure CLI:** |
| 52 | + |
| 53 | + - Check your login status using: |
| 54 | + ```bash |
| 55 | + az account show |
| 56 | + ``` |
| 57 | + - If not logged in, use: |
| 58 | + ```bash |
| 59 | + az login |
| 60 | + ``` |
| 61 | + - To specify a tenant, use: |
| 62 | + ```bash |
| 63 | + az login --tenant <tenant_id> |
| 64 | + ``` |
| 65 | + |
| 66 | +3. **Create a Resource Group:** |
| 67 | + |
| 68 | + - You can create it either through the Azure Portal or the Azure CLI: |
| 69 | + ```bash |
| 70 | + az group create --name <resource-group-name> --location EastUS2 |
| 71 | + ``` |
| 72 | + |
| 73 | +4. **Deploy the Bicep template:** |
| 74 | + |
| 75 | + - You can use the Bicep extension for VSCode (Right-click the `.bicep` file, then select "Show deployment plane") or use the Azure CLI: |
| 76 | + ```bash |
| 77 | + az deployment group create -g <resource-group-name> -f infra/main.bicep --query 'properties.outputs' |
| 78 | + ``` |
| 79 | + - **Note**: You will be prompted for a `principalId`, which is the ObjectID of your user in Entra ID. To find it, use the Azure Portal or run: |
| 80 | + ```bash |
| 81 | + az ad signed-in-user show --query id -o tsv |
| 82 | + ``` |
| 83 | + You will also be prompted for locations for Cosmos and OpenAI services. This is to allow separate regions where there may be service quota restrictions. |
| 84 | +
|
| 85 | + - **Additional Notes**: |
| 86 | +
|
| 87 | + **Role Assignments in Bicep Deployment:** |
| 88 | + |
| 89 | + The **macae-dev.bicep** deployment includes the assignment of the appropriate roles to AOAI and Cosmos services. If you want to modify an existing implementation—for example, to use resources deployed as part of the simple deployment for local debugging—you will need to add your own credentials to access the Cosmos and AOAI services. You can add these permissions using the following commands: |
| 90 | + ```bash |
| 91 | + az cosmosdb sql role assignment create --resource-group <solution-accelerator-rg> --account-name <cosmos-db-account-name> --role-definition-name "Cosmos DB Built-in Data Contributor" --principal-id <aad-user-object-id> --scope /subscriptions/<subscription-id>/resourceGroups/<solution-accelerator-rg>/providers/Microsoft.DocumentDB/databaseAccounts/<cosmos-db-account-name> |
| 92 | + ``` |
| 93 | +
|
| 94 | + ```bash |
| 95 | + az role assignment create --assignee <aad-user-upn> --role "Azure AI User" --scope /subscriptions/<subscription-id>/resourceGroups/<solution-accelerator-rg>/providers/Microsoft.CognitiveServices/accounts/<azure-ai-foundry-name> |
| 96 | + ``` |
| 97 | + **Using a Different Database in Cosmos:** |
| 98 | +
|
| 99 | + You can set the solution up to use a different database in Cosmos. For example, you can name it something like autogen-dev. To do this: |
| 100 | + 1. Change the environment variable **COSMOSDB_DATABASE** to the new database name. |
| 101 | + 2. You will need to create the database in the Cosmos DB account. You can do this from the Data Explorer pane in the portal, click on the drop down labeled “_+ New Container_” and provide all the necessary details. |
| 102 | +
|
| 103 | +6. **Create a `.env` file:** |
| 104 | +
|
| 105 | + - Navigate to the `src\backend` folder and create a `.env` file based on the provided `.env.sample` file. |
| 106 | + - Update the `.env` file with the required values from your Azure resource group in Azure Portal App Service environment variables. |
| 107 | + - Alternatively, if resources were |
| 108 | + provisioned using `azd provision` or `azd up`, a `.env` file is automatically generated in the `.azure/<env-name>/.env` |
| 109 | + file. To get your `<env-name>` run `azd env list` to see which env is default. |
| 110 | +
|
| 111 | +7. **Fill in the `.env` file:** |
| 112 | +
|
| 113 | + - Use the output from the deployment or check the Azure Portal under "Deployments" in the resource group. |
| 114 | + - Make sure to set APP_ENV to "**dev**" in `.env` file. |
| 115 | +
|
| 116 | +8. **(Optional) Set up a virtual environment:** |
| 117 | +
|
| 118 | + - If you are using `venv`, create and activate your virtual environment for both the frontend and backend folders. |
| 119 | +
|
| 120 | +9. **Install requirements - frontend:** |
| 121 | +
|
| 122 | + - In each of the frontend and backend folders - |
| 123 | + Open a terminal in the `src` folder and run: |
| 124 | + ```bash |
| 125 | + pip install -r requirements.txt |
| 126 | + ``` |
| 127 | + |
| 128 | +9. **Build the frontend (important):** |
| 129 | +
|
| 130 | + - Before running the frontend server, you must build the frontend to generate the necessary `build/assets` directory. |
| 131 | +
|
| 132 | + From the `src/frontend` directory, run: |
| 133 | +
|
| 134 | + ```bash |
| 135 | + npm install |
| 136 | + npm run build |
| 137 | + ``` |
| 138 | +
|
| 139 | +11. **Run the application:** |
| 140 | + - From the src/backend directory: |
| 141 | + ```bash |
| 142 | + python app_kernel.py |
| 143 | + ``` |
| 144 | + - In a new terminal from the src/frontend directory |
| 145 | + ```bash |
| 146 | + python frontend_server.py |
| 147 | + ``` |
| 148 | +
|
| 149 | +10. Open a browser and navigate to `http://localhost:3000` |
| 150 | +11. To see swagger API documentation, you can navigate to `http://localhost:8000/docs` |
| 151 | +
|
| 152 | +## Debugging the solution locally |
| 153 | +
|
| 154 | +You can debug the API backend running locally with VSCode using the following launch.json entry: |
| 155 | +
|
| 156 | +``` |
| 157 | + { |
| 158 | + "name": "Python Debugger: Backend", |
| 159 | + "type": "debugpy", |
| 160 | + "request": "launch", |
| 161 | + "cwd": "${workspaceFolder}/src/backend", |
| 162 | + "module": "uvicorn", |
| 163 | + "args": ["app:app", "--reload"], |
| 164 | + "jinja": true |
| 165 | + } |
| 166 | +``` |
| 167 | +To debug the python server in the frontend directory (frontend_server.py) and related, add the following launch.json entry: |
| 168 | +
|
| 169 | +``` |
| 170 | + { |
| 171 | + "name": "Python Debugger: Frontend", |
| 172 | + "type": "debugpy", |
| 173 | + "request": "launch", |
| 174 | + "cwd": "${workspaceFolder}/src/frontend", |
| 175 | + "module": "uvicorn", |
| 176 | + "args": ["frontend_server:app", "--port", "3000", "--reload"], |
| 177 | + "jinja": true |
| 178 | + } |
| 179 | +``` |
| 180 | +
|
0 commit comments