GraphRAG
Extract graph context from unstructured text for LLM question answering.
Overview
What you provide
- A text corpus, indexing configuration and model access
What you get
- Graph indexes and context-supported query answers
Software or published weights are available under MIT. Model inference, external services and your own compute are separate; hosted plan prices were not reviewed.
Official pricing ↗Pricing checked:
Setup & workflow
- Follow the official command-line quickstart and configure indexing before querying.
- Prepare the input: A text corpus, indexing configuration and model access.
- Run a small, reversible example and inspect the output: Graph indexes and context-supported query answers.
- Start with a small corpus and inspect extracted entities, source links and indexing costs.
Requirements & installation
- Configure the documented runtime and authorized service access before attempting this workflow.
Plans & billing details
Cost planning
- Review scope is licensing and documented free-use boundaries, not numeric prices or current hosted-plan allowances.
Published prices are a snapshot. Confirm billing cycle, taxes and current allowances with the provider.
Limits & review
- This research demonstration is in maintenance mode and is not a supported Microsoft service.
- Evidence review only: the product was not installed or tested in this crawl.
Your part
- Start with a small corpus and inspect extracted entities, source links and indexing costs.
When to consider another product
Unreviewed production decisions, unrestricted account access or guaranteed factual results.
Frequently asked questions
What is GraphRAG?
GraphRAG is a retrieval framework for deriving graph context from unstructured material for language-model answers.
What can GraphRAG do?
Documented outputs include graph indexes and context-supported query answers.
Who is GraphRAG for?
It is intended for people who need to extract graph context from unstructured text for LLM question answering.
How much does GraphRAG cost?
Software or published weights are available under MIT. Model inference, external services and your own compute are separate; hosted plan prices were not reviewed.
What should I check before using GraphRAG?
Configure the documented runtime and authorized service access before attempting this workflow. Keep this limitation in mind: This research demonstration is in maintenance mode and is not a supported Microsoft service.
When should I look at something else?
It is not intended for unreviewed production decisions, unrestricted account access or guaranteed factual results.
Website traffic
microsoft.github.io
2026-09
Previous month visits: 906,784
Snapshot captured:
All available locations and languages
Estimated monthly paid search traffic: 0
Snapshot captured:
Search traffic is estimated from keyword rankings, search volume and click-through rates. It excludes direct and referral visits and is not total website traffic.
13-month change: −85%
Monthly values
| Month | Estimated visits |
|---|---|
| 2025-10 | 513,087 |
| 2025-11 | 487,174 |
| 2025-12 | 501,169 |
| 2026-01 | 546,700 |
| 2026-02 | 551,367 |
| 2026-03 | 523,839 |
| 2026-04 | 495,613 |
| 2026-05 | 489,511 |
| 2026-06 | 435,471 |
| 2026-07 | 390,150 |
| 2026-08 | 346,746 |
| 2026-09 | 293,655 |
| 2026-10 | 74,554 |
Months without an estimate are left blank, not counted as zero.
Domain-wide estimate; includes other products and pages on this domain. This is not verified usage, revenue or product quality.
Sources & verification3
This profile is based on official sources, not a hands-on product test.
Vendor descriptions and demos document advertised features. Editorial guidance is based on these sources.
Discovered via OpenFree.Tools.
- GraphRAG — official READMEraw.githubusercontent.com
The maintainer README supports this scope: Extract graph context from unstructured text for LLM question answering.
- GraphRAG — product entry pointmicrosoft.github.io
The public product entry point was retrieved. Functional scope and setup in this record are grounded in the linked maintainer README.
- GraphRAG — license termsraw.githubusercontent.com
The retrieved license materials support this boundary: MIT. Review the complete terms for your use case.
Product details
- Product type
- Developer framework
- Getting started
- Requires setup
- Category
- AI Models & Developer Tools
- Evidence
- Official-source review