This sample shows an agentic Autogen application using Mistral and FastAPI, deployed with Defang. For demonstration purposes, it will require a Mistral AI API key (see Configuration for more details). However, you are free to modify it to use a different LLM, say the Defang OpenAI Access Gateway service, as an alternative. Note that the Vite React frontend is served through the FastAPI backend so that they can be treated as one service in production.
- Download Defang CLI
- (Optional) If you are using Defang BYOC authenticate with your cloud provider account
- (Optional for local development) Docker CLI
To run the application locally, you can use the following command:
docker compose up --buildFor this sample, you will need to provide the following configuration:
Note that if you are using the 1-click deploy option, you can set these values as secrets in your GitHub repository and the action will automatically deploy them for you.
An API key to access the Mistral AI API.
defang config set MISTRAL_API_KEYNote
Download Defang CLI
Deploy your application to the Defang Playground by opening up your terminal and typing:
defang compose upIf you want to deploy to your own cloud account, you can use Defang BYOC.
Title: Agentic Autogen
Short Description: An Autogen agent application using Mistral and FastAPI, deployed with Defang.
Tags: Agent, Autogen, Mistral, FastAPI, Vite, React, Python, JavaScript, AI
Languages: Python, JavaScript