Ross ROSS = Recommend OSS · open-source software intelligence for agents

rahulnyk/knowledge_graph

Convert any text to a graph of knowledge. This can be used for Graph Augmented Generation or Knowledge Graph based QnA observed · 2026-08-28

github.com/rahulnyk/knowledge_graph · Jupyter Notebook · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

71/100

  • Activity 97
  • Release rhythm 35
  • Longevity 74

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 1046
  • days_rel: n/a
  • days_push: 18
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

3713 stars · 591 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A Python/Jupyter Notebook project that converts any text corpus into a knowledge graph by extracting concepts with an LLM and linking co-occurring concepts. It supports Graph Augmented Generation (GRAG) for QnA and includes graph visualization.

Use cases

  • build a knowledge graph from a pdf document
  • chat with my documents using graph rag
  • extract concepts and relationships from text
  • visualize a text corpus as a network graph
  • run graph algorithms to find important concepts in a document
  • create a knowledge graph without using openai api

When to avoid

  • you need production-grade entity extraction with NER models
  • you need a scalable graph database solution for enterprise data
  • you need a polished application rather than notebook-based code

Facets

library · maturity active

nlp rag llm-inference data-visualization parser artificial-intelligence data-visualization developer-tools python cross-platform knowledge-graph graph-rag concept-extraction graph-visualization jupyter-notebook local-llm natural-language-processing retrieval-augmented-generation

1 source

Member repositories

RepositoryRoleHealth v2
rahulnyk/knowledge_graphmain71

For agents

markdown · JSON · MCP: product_card(name="rahulnyk/knowledge_graph")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem