NezT Labs: GraphRAG with Neo4j

NezT Labs (in-house R&D) · AI Workflow Software

An in-house build: a GraphRAG system that combines semantic vector search with a Neo4j knowledge graph for document question answering.

What it does

Semantic chunking of documents with entity and relation extraction into Neo4j.

Hybrid retrieval that blends graph traversal with vector similarity.

Retrieved knowledge stays inspectable as a graph rather than an opaque list of passages.

Tech stack

Python, LangChain, Google Gemini, Neo4j, Docker

Impact

Better answers where questions depend on relationships across sections, not just similar passages.