Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
GraphRAG: Text to Q&A
This talk demonstrates extracting entities and relationships from text using LLMs, building knowledge graphs, and combining vector and database search for improved Q&A with explainability.
Usually you only see text + embeddings with LLMs but many advanced RAG patterns need more structure. In a knowledge graph you can represent that structure and use it to provide better context for Q&A. But how to get there from text documents? You can use the language skills of LLMs to extract entities and relationships from texts and store them in the graph connected to the original documents and chunks.
The application and code I’ll show will demonstrate how to get from text to graph to GraphRAG and I will highlight the good and the difficult aspects of this approach.
This Neo4j graph builder uses OpenAI GPT-4.1 to generate graph schemas.
Neo4j LLM Builder extracts unstructured text into knowledge graphs via LLMs.