# Azure-Samples/graphrag-accelerator

One-click deploy of a Knowledge Graph powered RAG (GraphRAG) in Azure

Repository: https://github.com/Azure-Samples/graphrag-accelerator
Canonical: https://ross.abutalabs.com/products/graphrag-accelerator
Homepage: https://github.com/microsoft/graphrag
Language: Python
License: MIT
License Family: permissive
Archived: true
Last push: 2025-05-27T13:56:40+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 23, release rhythm 8, longevity 63
- inputs: {"age_days": 889, "days_push": 463, "days_rel": 712, "gap_med": null, "n_releases_24m": 1}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2409, forks 419 (observed 2026-08-28T04:06:44.266791+00:00)

## What it is
A one-click Azure deployment accelerator that hosts the GraphRAG knowledge-graph-powered RAG system as a scalable API service. It builds on the microsoft/graphrag Python package to expose indexing pipelines and graph-based query endpoints on Azure infrastructure.

## Use cases
- deploy graphrag as a hosted API on Azure
- run knowledge graph RAG over my documents
- query a knowledge graph with an LLM
- set up an auto-scaling GraphRAG service with user access control
- index large document collections into a graph for question answering

## When to choose
- you want a production-style, auto-scaling GraphRAG API hosted on Azure
- you need user access control and high-utilization serving of GraphRAG endpoints
- you prefer infrastructure-as-code (bicep) deployment of the full Azure stack

## When to avoid
- you want active development or new features - the repo is no longer maintained; use microsoft/graphrag instead
- you want a lightweight local or low-cost setup - the Azure stack and indexing can be expensive
- you need an officially supported Microsoft product - this is a demonstration accelerator

## Facets
- artifact type: application
- maturity: abandoned
- function: rag, llm-inference, search-engine, api-framework, etl
- domain: large-language-models, artificial-intelligence, cloud-computing
- platform: python, cloud, self-hosted
- tags: graphrag, knowledge-graph, azure, solution-accelerator, infrastructure-as-code, bicep, one-click-deploy, retrieval-augmented-generation, search, docker

## Member repositories
- Azure-Samples/graphrag-accelerator (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:44.266791+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 2026-08-30T02:34:00.796982+00:00, confidence not recorded.
  - readme: https://github.com/Azure-Samples/graphrag-accelerator (fetched 2026-08-28T04:06:44.266791+00:00, sha fede465519ea)
  - homepage: https://github.com/microsoft/graphrag (fetched 2026-08-29T10:14:07.186204+00:00, sha d79a65b9f110)
- Data as of 2026-08-30T08:39:29.467469+00:00.