Secure, enterprise-ready landing zone for deploying AI agent applications on Microsoft Foundry.
GPT-RAG is now Agent Landing Zone. It is the former GPT-RAG Solution Accelerator, renamed and matured.
Note
Version 4.0.0 supports new deployments only. Existing GPT-RAG deployments are not upgraded in place; to move to Agent Landing Zone, redeploy into a new environment. Existing GPT-RAG environments can keep running on their GPT-RAG release, whose tags stay available.
Choose one of two options:
| Option | Commands | What you get |
|---|---|---|
| Full stack | azd up |
Infrastructure plus the UI, orchestrator, and ingestion applications. |
| Infrastructure only | azd provision, then azd deploy later |
The landing zone infrastructure now; deploy applications when you are ready. |
To deploy your own application instead of the default components, describe it in app-definition.json. See samples/custom-app for an example.
Prerequisites, network-isolated deployment, and configuration are covered in the central documentation.
Component versions for this release are pinned in manifest.json.
| Component | Repository | Version |
|---|---|---|
| UI | Azure/agent-app-ui | see manifest.json |
| Orchestrator | Azure/agent-app-orchestrator | see manifest.json |
| Ingestion | Azure/agent-app-ingestion | see manifest.json |
The full documentation lives in the Agent Landing Zone section of the AI Landing Zones documentation site.
See CONTRIBUTING.md, SECURITY.md, and SUPPORT.md. Release history is in CHANGELOG.md.
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos is subject to those third-party's policies.