This application utilizes the following Azure resources:
- Azure Spring Apps to host the application
- Azure OpenAI for ChatGPT
- Azure Redis to save the conversation history for each user.
Here's a high level architecture diagram that illustrates these components. Notice that these are all contained within a single resource group, that will be created for you when you create the resources.
You can run this sample app using the Azure CLI by following these steps.
- JDK 17
- Maven
- Azure CLI
- An Azure subscription with access granted to Azure OpenAI (see more here)
- Run
git clone https://github.com/rohanmukesh/spring-ai-azure-movee.git
- Run
cd spring-ai-azure-movee
. - Build with
./mvnw clean package -PProduction
.
Before running the web app, you need to preprocess the movies and load them into the vector store:
source env.sh
java -jar spring-ai-azure-movee/target/spring-ai-azure-movee-0.0.1-SNAPSHOT.jar --from=/<path>/<to>/<your>/<documents>
Or dowload the pre-built vector store of the public documents of the Azure Spring Apps.
To run the demo in the local machine, please follow these steps:
-
Launch the web app
./mvnw clean package source env.sh java -jar spring-ai-azure-movee/target/spring-ai-azure-movee-0.0.1-SNAPSHOT.jar
-
Open
http://localhost:8080
in your browser.