# robert-mcdermott/ai-knowledge-graph

AI Powered Knowledge Graph Generator

Repository: https://github.com/robert-mcdermott/ai-knowledge-graph
Canonical: https://ross.abutalabs.com/products/ai-knowledge-graph
Homepage: https://robert-mcdermott.medium.com/from-unstructured-text-to-interactive-knowledge-graphs-using-llms-dd02a1f71cd6
Language: Python
License: Apache-2.0
License Family: permissive
Topics: artificial-intelligence, knowledge-distillation, knowledge-graph, llm, networkx, pyvis, visualization
Last push: 2025-12-28T00:22:06+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 59, release rhythm 63, longevity 37
- inputs: {"age_days": 528, "days_push": 249, "days_rel": 249, "gap_med": 0, "n_releases_24m": 16}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2865, forks 390 (observed 2026-08-28T04:07:26.523998+00:00)

## What it is
A Python CLI tool that uses an LLM to extract Subject-Predicate-Object triplets from unstructured text documents and renders them as an interactive knowledge graph HTML visualization. It works with any OpenAI-compatible API endpoint including Ollama, LM Studio, OpenAI, and vLLM.

## Use cases
- extract a knowledge graph from unstructured text documents
- visualize entity relationships from text as an interactive graph
- use a local LLM like Ollama to build knowledge graphs
- convert free-form text into structured SPO triplets
- map connections between concepts in a large document
- build an entity-relationship graph without hand-coded extraction rules

## When to choose
- you want an automated LLM-powered pipeline from raw text to an interactive knowledge graph
- you need to work with local models via Ollama or any OpenAI-compatible endpoint
- you want entity standardization and relationship inference built in
- you prefer a simple CLI workflow with configurable chunking and LLM settings

## When to avoid
- you need a production-grade graph database or RDF/SPARQL support
- you want deterministic, non-LLM extraction with hand-coded rules
- you need real-time or streaming graph updates
- you lack access to any LLM endpoint, since extraction depends entirely on one

## Facets
- artifact type: cli-tool
- maturity: active
- function: llm-inference, nlp, data-visualization, rag, cli
- domain: artificial-intelligence, large-language-models, data-visualization, developer-tools
- platform: python, cli, cross-platform
- tags: knowledge-graph, llm, networkx, pyvis, entity-extraction, spo-triplets, ollama, openai-compatible, natural-language-processing

## Member repositories
- robert-mcdermott/ai-knowledge-graph (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:26.523998+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 2026-08-30T07:36:14.367381+00:00, confidence not recorded.
  - readme: https://github.com/robert-mcdermott/ai-knowledge-graph (fetched 2026-08-28T04:07:26.523998+00:00, sha c85cd1583cee)
  - homepage: https://robert-mcdermott.medium.com/from-unstructured-text-to-interactive-knowledge-graphs-using-llms-dd02a1f71cd6 (fetched 2026-08-29T09:51:52.835789+00:00, sha 2e31ebdf2018)
- Data as of 2026-08-30T08:39:29.467469+00:00.