Skip to content

llm-graph-builder

Turn unstructured files into a Neo4j knowledge graph

Visit official site

What llm-graph-builder is

The app is described as a Neo4j application that uses large language models such as OpenAI and Gemini to extract nodes, relationships and properties from unstructured data. It builds a structured knowledge graph with the Langchain framework.

What you can do with it

  • Convert unstructured data into a structured knowledge graph
  • Use a custom schema or an existing one from settings
  • View graphs in Bloom by one source or several sources
  • Query Neo4j data conversationally and read source metadata

Application scenarios

  • Build a domain knowledge graph from academic paper concepts
  • Identify trends and influential figures in social media data
  • Set up an internal knowledge system from company documents

Getting started

  • Prepare Neo4j V5.15 or higher with APOC installed
  • Create and configure an .env file with API keys
  • Choose a source such as a local file, a YouTube video or a web page
  • Upload the file and pick an LLM to generate the graph

Pros & cons

✓ What we like

  • Conversational queries can return source metadata
  • Local deployment runs through docker-compose

! What to watch out for

  • The setup names Neo4j V5.15 or higher and APOC
  • An .env file with API keys is part of the documented setup

FAQ

What inputs are listed?

PDF, DOCS, TXT, YouTube videos and web pages are named as unstructured sources.

How is the graph deployed?

The material lists docker-compose locally and Google Cloud Platform for cloud deployment.

Last reviewed: 2026-11-15

More AI coding tools tools

View all →

How we review