Skip to content

GraphRAG-Ollama-UI

Run Microsoft GraphRAG locally with Ollama and a Gradio UI

Visit official site

What GraphRAG-Ollama-UI is

The tool is described as a local model adaptation of Microsoft GraphRAG that uses Ollama for local language and embedding models, with a Gradio interface for managing data, running queries and visualising results.

What you can do with it

  • Run language and embedding models locally with Ollama
  • Manage data, run queries and visualise results from an interactive UI
  • Visualise a knowledge graph in 3D with Plotly
  • Upload, view, edit and delete input files and manage GraphRAG settings

Application scenarios

  • Developers build and query local knowledge graphs
  • Data scientists run complex data queries and analysis
  • Educators demonstrate knowledge graph construction in teaching

Getting started

  • Create and activate a new conda environment
  • Install Ollama following its website instructions
  • Install the required packages with pip install -r requirements.txt
  • Launch the interactive UI with gradio app.py or python app.py

Pros & cons

✓ What we like

  • Removes the dependency on costly OpenAI models
  • An interactive UI covers data, queries, visualisation, output exploration and logging

! What to watch out for

  • Local use requires an Ollama installation
  • Setup needs a conda environment and package installation

FAQ

Which models run locally?

The material states Ollama provides local language and embedding models.

How is the knowledge graph visualised?

The material states Plotly is used for real-time 3D visualisation.

Last reviewed: 2026-11-15

More LLM API platform tools

View all →

How we review