← Browse tools

Data & context

Microsoft GraphRAG

Knowledge-graph extraction and collection-level context for retrieval beyond individual text chunks.

Overview

Research summary

Microsoft GraphRAG uses language models to extract structured relationships from unstructured text and builds graph-based context for question answering. Its indexing and query pipeline targets questions that benefit from relationships and summaries across a document collection. The MIT-licensed repository is research software, not a supported Microsoft product. Its maintainers currently accept maintenance work such as bug fixes and security dependency updates, but state that new features and external pull requests are not planned. Indexing can incur substantial model costs and requires corpus-specific configuration.

Repository summary

Stars
Unavailable
Open issues
Unavailable
Last push
Unavailable
Commits, 90 days
Unavailable
Repository activity
Not scored
Version
Unavailable

Recorded catalogue figures. View repository data and provenance →

Classification

Pricing & services

Paid services unknown

Whether the provider offers paid products or services has not been established.

Licence scope

Implementation

Recorded implementation details and interfaces for Microsoft GraphRAG.

Implementation details

Python indexing and graph-based retrieval pipeline

Languages
Python
Repository type
source

Recorded interfaces and capabilities

Licence scope

Repository

Repository snapshots, release information and recorded maintenance signals.

Repository snapshot

microsoft/graphrag ↗

Stars
Unavailable
Open issues
Unavailable
Last push
Unavailable
Commits, 90 days
Unavailable
Repository activity
Not scored
Archived
Not recorded

Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).

Maintenance and provenance

Catalogue snapshot
2026-10-06

Documentation

Recorded references and research provenance for this entry.

Recorded sources 3

Research metadata

Research date
2026-10-01
Catalogue snapshot
2026-10-06

Community & social 1 channels

Communities