neo4j-labs/llm-graph-builder

Neo4j graph construction from unstructured data using LLMs

What it solves

This project simplifies the process of converting unstructured data—such as PDFs, text files, web pages, and YouTube videos—into structured Knowledge Graphs. By using Large Language Models (LLMs), it automates the extraction of nodes and relationships, allowing users to store and query their data in a Neo4j database.

How it works

The application provides a web interface where you upload files or provide web sources. It uses LLMs to parse the content, extract entities and relationships based on a defined schema, and store them in Neo4j. Once built, you can visualize these graphs using Neo4j Bloom or interact with your data through a built-in chat interface that supports various retrieval modes, including graph-based and vector-based search.

Who it’s for

It is designed for developers and data engineers who want to build and query Knowledge Graphs from diverse data sources without manually defining every relationship. It is particularly useful for those already working within the Neo4j ecosystem who want to leverage LLMs for automated data structuring.

Highlights

  • Supports a wide range of input sources including local files, AWS S3, Google Cloud Storage, Wikipedia, and YouTube.
  • Compatible with many LLM providers, including OpenAI, Anthropic, Gemini, Groq, and local models via Ollama.
  • Includes built-in token usage tracking to monitor and manage LLM costs.
  • Offers flexible deployment options, including local Docker-based setups and cloud deployment on Google Cloud Run.
  • Enables conversational Q&A over your graph data with metadata-backed responses.

Related

  • Project
    robert-mcdermott/ai-knowledge-graph

    An AI-powered system that extracts Subject-Predicate-Object triplets from unstructured text to create interactive, queryable knowledge graphs.

  • Project
    MazzaWill/neo4j-python-pandas-py2neo-v3

    A toolkit for converting Excel data into Neo4j knowledge graphs, featuring both legacy educational examples and modern GraphRAG and vector-search implementations.

  • Project
    neo4j/neo4j-graphrag-python

    A Python library from Neo4j that lets you build Graph Retrieval‑Augmented Generation (GraphRAG) apps. It provides pipelines to turn text/PDFs into a Neo4j knowledge graph, utilities for vector indexing, hybrid retrievers that blend vector search with graph traversal, and a simple RAG API that plugs any supported LLM (OpenAI, Anthropic, Ollama, etc.). Install via `pip install neo4j-graphrag` (optional extras for your LLM), create a KG, index embeddings, then query with natural language.

  • Project
    MiracleTanC/Neo4j-KGBuilder

    A lightweight knowledge graph construction and visualization tool based on Neo4j and Spring Boot, featuring visual editing, ER modeling, and external data source integration.

  • Project
    yifanfeng97/Hyper-Extract

    A smart knowledge extraction CLI that transforms unstructured documents into structured knowledge bases, graphs, and lists using LLMs and domain-specific templates.