# TheAiSingularity/graphrag-local-ollama

Local models support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction

Repository: https://github.com/TheAiSingularity/graphrag-local-ollama
Canonical: https://ross.abutalabs.com/products/graphrag-local-ollama
Language: Python
License: MIT
License Family: permissive
Last push: 2026-05-08T20:26:23+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 81, release rhythm 35, longevity 56
- inputs: {"age_days": 786, "days_push": 117, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1108, forks 162 (observed 2026-08-28T04:03:37.035082+00:00)

## What it is
A local adaptation of Microsoft's GraphRAG that runs LLM and embedding extraction entirely through Ollama models like llama3, mistral, gemma2, and phi3. It builds entity knowledge graphs from documents, generates community summaries, and offers a web UI with multiple query modes including Global, Local, DRIFT, Basic, and LazyGraphRAG.

## Use cases
- run graphrag on local models without openai api costs
- build a knowledge graph from my documents with ollama
- answer global questions over a private text corpus
- visualize a knowledge graph of my documents in a browser
- index large text corpora cheaply with lazygraphrag
- query documents with drift search iterative reasoning

## When to choose
- you want GraphRAG's knowledge-graph RAG without paying for OpenAI models
- you already run Ollama and want local LLM and embedding inference
- you need a web UI for indexing, querying, and graph visualization
- you want fast indexing via LazyGraphRAG or iterative DRIFT search

## When to avoid
- you need the official, fully supported Microsoft GraphRAG implementation
- you have no GPU or hardware to run local models comfortably
- you want a managed cloud RAG service rather than self-hosted tooling
- your corpus is tiny and a simple vector RAG setup would suffice

## Facets
- artifact type: application
- maturity: active
- function: rag, llm-inference, agent-framework, data-visualization, search-engine
- domain: large-language-models, artificial-intelligence, self-hosted
- platform: python, cli, self-hosted, cross-platform
- tags: graphrag, ollama, knowledge-graph, local-llm, community-summarization, drift-search, embeddings, retrieval-augmented-generation, natural-language-processing, web-server

## Member repositories
- TheAiSingularity/graphrag-local-ollama (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:37.035082+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 2026-08-30T06:43:44.458136+00:00, confidence not recorded.
  - readme: https://github.com/TheAiSingularity/graphrag-local-ollama (fetched 2026-08-28T04:03:37.035082+00:00, sha 622a9e5cff6a)
- Data as of 2026-08-30T08:39:29.467469+00:00.