# neo4j-labs/llm-graph-builder

Neo4j graph construction from unstructured data using LLMs

Repository: https://github.com/neo4j-labs/llm-graph-builder
Canonical: https://ross.abutalabs.com/products/llm-graph-builder
Homepage: https://llm-graph-builder.neo4jlabs.com/
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: data-import, genai, graph, graph-rag, graph-search, graphdb, graphrag, knowledge-graph, langchain, neo4j, rag, unstructured-data, vectordb
Last push: 2026-08-10T16:11:54+00:00

## Health v2 (maintenance only)
Score: 90/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 94, longevity 68
- inputs: {"age_days": 965, "days_push": 23, "days_rel": 41, "gap_med": 30, "n_releases_24m": 14}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5197, forks 878 (observed 2026-08-28T04:09:12.080907+00:00)

## What it is
A web application that transforms unstructured data (PDFs, DOCs, TXTs, YouTube videos, web pages) into a knowledge graph stored in Neo4j using LLMs and LangChain. It includes a FastAPI backend and React frontend with graph visualization and a chat-with-data interface.

## Use cases
- build a knowledge graph from pdfs
- extract entities and relationships from documents into neo4j
- chat with my documents using a graph rag pipeline
- convert youtube videos and web pages into a structured graph
- visualize llm-extracted graphs in neo4j bloom
- ingest files from s3 or gcs into a knowledge graph

## When to choose
- you want LLM-powered graph construction into Neo4j from mixed unstructured sources
- you need a ready-made GraphRAG app with chat and visualization
- you want support for multiple LLM providers including OpenAI, Gemini, Anthropic, and Ollama

## When to avoid
- you don't use Neo4j or don't want a graph database
- you need a lightweight library to embed in your own pipeline rather than a full application
- you can't run Neo4j 5.23+ with APOC

## Facets
- artifact type: application
- maturity: active
- function: rag, llm-inference, etl, search-engine, chatbot, data-visualization
- domain: large-language-models, databases, artificial-intelligence
- platform: python, self-hosted, cross-platform
- tags: knowledge-graph, neo4j, graphrag, langchain, unstructured-data, fastapi, react, graph-construction, retrieval-augmented-generation, natural-language-processing, data-engineering, web-server, docker

## Member repositories
- neo4j-labs/llm-graph-builder (main) score 90

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:12.080907+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 2026-08-29T18:01:42.875311+00:00, confidence not recorded.
  - readme: https://github.com/neo4j-labs/llm-graph-builder (fetched 2026-08-28T04:09:12.080907+00:00, sha 361ff699fc89)
  - homepage: https://llm-graph-builder.neo4jlabs.com/ (fetched 2026-08-29T08:55:26.619454+00:00, sha d65a10577a32)
- Data as of 2026-08-30T08:39:29.467469+00:00.