https://github.com/azure/gpt-rag

Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.
https://github.com/azure/gpt-rag

azd-templates azure gpt-3 gpt-4 openai

Last synced: 7 days ago
JSON representation

Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.

• Host: GitHub
• URL: https://github.com/azure/gpt-rag
• Owner: Azure
• License: mit
• Created: 2023-06-27T13:23:44.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2026-03-25T11:54:26.000Z (about 1 month ago)
• Last Synced: 2026-03-25T20:19:02.800Z (about 1 month ago)
• Topics: azd-templates, azure, gpt-3, gpt-4, openai
• Language: Python
• Homepage: https://aka.ms/gpt-rag
• Size: 68.6 MB
• Stars: 1,143
• Watchers: 18
• Forks: 295
• Open Issues: 9
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md
  • Security: SECURITY.md
  • Support: SUPPORT.md
  • Agents: AGENTS.md

Awesome Lists containing this project

• awesome-ChatGPT-repositories - GPT-RAG - Sharing the learning along the way we been gathering to enable Azure OpenAI at scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. (NLP)

README

          



# GPT-RAG Solution Accelerator

This solution accelerator provides architecture templates and deployment assets to help organizations build secure, scalable, and enterprise-ready **Retrieval-Augmented Generation (RAG)** solutions powered by **AI Agents**. It applies proven Azure design patterns and incorporates **Zero-Trust security**, **Responsible AI**, and **end-to-end observability**, enabling teams to operationalize Generative AI with confidence.

For full documentation, visit the **[GPT-RAG documentation site](https://azure.github.io/GPT-RAG/)**.

GPT-RAG is built on a Zero-Trust architecture to ensure that all components operate within a controlled, isolated environment. Network access is tightly governed, and communication between services follows least-privilege principles.

## Architecture

![Zero Trust Architecture](media/architecture_zero_trust.png)

*Zero-Trust Architecture*

## AI Agent Capabilities

The accelerator supports a broad range of enterprise scenarios—from customer support to decision automation—by enabling systems to process complex queries across large data collections. It is designed for seamless integration into existing environments and can be adapted to both straightforward and advanced operational patterns.

A key capability of GPT-RAG is its support for **AI Agents**, enabling scenarios such as **NL2SQL query generation** and other context-aware interactions. This extensibility allows organizations to build intelligent workflows that retrieve, interpret, and act on data with contextual precision.

![Zero Trust UI](media/gpt-rag-homepage.png)

*GPT-RAG UI*

## Contributing

We welcome contributions! See the [contribution guidelines](https://azure.github.io/GPT-RAG/contributing/) for details on how to contribute.

## Trademarks

This project may contain trademarks or logos. Authorized use of Microsoft trademarks or logos must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks/usage/general). Modified versions must not imply sponsorship or cause confusion. Third-party trademarks are subject to their own policies.