Part of the GPT-RAG solution.
This repo provides a user interface built with Chainlit to interact with GPT-powered retrieval-augmented generation systems. It is designed to work seamlessly with the Orchestrator backend and supports customization and theming.
For comprehensive information about GPT-RAG, including architecture details, configuration guides, best practices, troubleshooting resources, deployment guidance, customization options, and advanced usage scenarios, please refer to the official project documentation.
Provision the infrastructure first by following the GPT-RAG repository instructions GPT-RAG. This ensures all required Azure resources (e.g., Container App, Storage, AI Search) are in place before deploying the web application.
Click to view software prerequisites
The machine used to customize and or deploy the service should have:
- Azure CLI: Install Azure CLI
- Azure Developer CLI (optional, if using azd): Install azd
- Git: Download Git
- Python 3.12: Download Python 3.12
- Docker CLI: Install Docker
- VS Code (recommended): Download VS Code
Make sure you're logged in to Azure before anything else:
az loginInitialize the template:
azd init -t azure/gpt-rag-ui Important
Use the same environment name with azd init as in the infrastructure deployment to keep components consistent.
Update env variables then deploy:
azd env refresh
azd deploy Important
Run azd env refresh with the same subscription and resource group used in the infrastructure deployment.
To deploy using a script, first clone the repository, set the App Configuration endpoint, and then run the deployment script.
git clone https://github.com/Azure/gpt-rag-ui.git
$env:APP_CONFIG_ENDPOINT = "https://<your-app-config-name>.azconfig.io"
cd gpt-rag-ui
.\scripts\deploy.ps1git clone https://github.com/Azure/gpt-rag-ui.git
export APP_CONFIG_ENDPOINT="https://<your-app-config-name>.azconfig.io"
cd gpt-rag-ui
./scripts/deploy.sh- Modify theme in
public/theme.json - Customize layout with
public/custom.css - Adjust app behavior in
.chainlit/config.toml
The UI can show release versions in a subtle footer at the bottom of the page.
SHOW_RELEASE_FOOTER(boolean, defaulttrue): enables or disables footer display.RELEASE(string): GPT-RAG release value from App Configuration.VERSIONfile: GPT-RAG UI release value (local file in this repository).
Display format:
gpt-rag vX.Y.Z | gpt-rag-ui vA.B.C
Behavior:
- If a value does not start with
v, the prefix is added automatically. - If one value is missing, the footer shows an English fallback message for that side.
- The frontend fetches release data from
/version-footer.
Encountered an error or bug? Help us improve the quality of this accelerator by reporting issues or suggesting enhancements on our GitHub Issues page. Your feedback helps make GPT-RAG better for everyone!
Note
For earlier versions, use the corresponding release in the GitHub repository (e.g., v1.0.0 for the initial version).
We appreciate contributions! See CONTRIBUTING for guidelines on submitting pull requests.
This project may contain trademarks or logos. Authorized use of Microsoft trademarks or logos must follow Microsoft’s Trademark & Brand Guidelines. Modified versions must not imply sponsorship or cause confusion. Third-party trademarks are subject to their own policies.