# varunshenoy/GraphGPT

Extrapolating knowledge graphs from unstructured text using GPT-3 🕵️‍♂️

Repository: https://github.com/varunshenoy/GraphGPT
Canonical: https://ross.abutalabs.com/products/graphgpt
Homepage: https://graphgpt.vercel.app
Language: JavaScript
License: MIT
License Family: permissive
Topics: gpt-3, knowledge-graph
Last push: 2024-05-10T10:01:21+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 93
- inputs: {"age_days": 1310, "days_push": 845, "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 4426, forks 397 (observed 2026-08-28T04:08:48.888726+00:00)

## What it is
GraphGPT is a web application that converts unstructured natural language text into a knowledge graph using GPT-3, visualizing entities and their relationships. Successive queries can update the existing graph state or create entirely new structures.

## Use cases
- extract a knowledge graph from a movie synopsis
- visualize entities and relationships from a wikipedia passage
- build a graph from a video transcript
- incrementally update a knowledge graph with new text
- explore how GPT-3 structures unstructured text

## When to choose
- you want a quick visual demo of LLM-based entity/relation extraction
- you need a lightweight tool to turn prose into an interactive graph
- you want to study few-shot prompt design for structured JSON output

## When to avoid
- you need production-grade knowledge graph extraction with low latency
- you want a maintained library to embed in your own project (the author recommends GPT Index/LlamaIndex instead)
- you cannot rely on the OpenAI API or don't have an API key

## Facets
- artifact type: application
- maturity: experimental
- function: nlp, llm-inference, data-visualization, rag
- domain: artificial-intelligence, large-language-models, data-visualization
- platform: -
- tags: knowledge-graph, gpt-3, openai, graph-visualization, toy-project, natural-language-processing, web, nodejs, javascript

## Member repositories
- varunshenoy/GraphGPT (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:48.888726+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 2026-08-29T18:20:57.477248+00:00, confidence not recorded.
  - readme: https://github.com/varunshenoy/GraphGPT (fetched 2026-08-28T04:08:48.888726+00:00, sha b6ee034a0dc6)
  - homepage: https://graphgpt.vercel.app (fetched 2026-08-29T09:08:40.420532+00:00, sha 64fc2a84db5b)
- Data as of 2026-08-30T08:39:29.467469+00:00.