# Azure/GPT-RAG

Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.

Repository: https://github.com/Azure/GPT-RAG
Canonical: https://ross.abutalabs.com/products/gpt-rag
Homepage: https://aka.ms/gpt-rag
Language: Python
License: MIT
License Family: permissive
Topics: azure, gpt-4, openai, azd-templates, agent-framework, agentic-rag, ai-agents, foundry-iq, microsoft-foundry, rag
Last push: 2026-09-02T16:12:14+00:00

## Health v2 (maintenance only)
Score: 90/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 100, release rhythm 82, longevity 83
- inputs: {"age_days": 1163, "days_push": 0, "days_rel": 43, "gap_med": 1, "n_releases_24m": 90}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1170, forks 319 (observed 2026-09-03T02:15:05.071696+00:00)

## What it is
GPT-RAG is an Azure solution accelerator providing architecture templates and deployment assets for enterprise-scale Retrieval-Augmented Generation using Azure OpenAI and Azure AI Search. It ships with Zero-Trust security, Responsible AI practices, observability, and AI agent capabilities such as NL2SQL query generation.

## Use cases
- deploy a secure enterprise RAG chatbot on Azure
- build a Q&A experience over company documents with Azure OpenAI
- set up ChatGPT-style chat grounded in enterprise data
- implement zero-trust network-isolated OpenAI deployments
- generate SQL from natural language with AI agents
- operationalize generative AI at enterprise scale

## When to choose
- you are all-in on Azure and want Azure OpenAI with Azure AI Search
- you need a production-ready, security-reviewed RAG reference architecture
- you want zero-trust, network-isolated deployment out of the box
- you need agent extensibility like NL2SQL on top of RAG

## When to avoid
- you want a cloud-agnostic or self-hosted open-model RAG stack
- you use AWS, GCP, or on-prem infrastructure instead of Azure
- you need a lightweight library to embed in an existing app rather than a full accelerator
- you want to avoid Azure-specific services like AI Search and AI Foundry

## Facets
- artifact type: framework
- maturity: active
- function: rag, llm-inference, agent-framework, search-engine, chatbot, infrastructure-as-code, monitoring, security
- domain: large-language-models, cloud-computing, self-hosted
- platform: cloud, python
- tags: azure-openai, azure-ai-search, solution-accelerator, zero-trust, enterprise-ai, bicep, azd-templates, responsible-ai, retrieval-augmented-generation, ai-agents, docker

## Member repositories
- Azure/GPT-RAG (main) score 90

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:05.071696+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:28:39.646623+00:00, confidence not recorded.
  - readme: https://github.com/Azure/GPT-RAG (fetched 2026-09-03T02:15:05.071696+00:00, sha e74fdaa35883)
- Data as of 2026-08-30T08:39:29.467469+00:00.