We're developing a GraphRAG system using Diffbot's APIs to construct reliable knowledge graphs, which are then stored in a Neo4j graph database for efficient querying and information retrieval.

0:00 intro
0:22 brief overview of graph rag and knowledge graphs
0:50 potential pitfalls of vectorbased rag
1:29 graph rag research by microsoft
2:09 potential pitfalls of llms constructing knowledge graphs
2:20 brief intro of entity resolution
3:03 entity resolution problem with gpt4
3:41 entity resolution handled by Diffbot
3:51 Graph RAG demo + article importer
4:37 web scraping without worrying about hallucinated sources
5:24 KG construction from news article
5:37 enrich the knowledge graph with Enhance API
5:57 final network graph
6:09 question answering (vector vs. vector+kg)
7:26 more examples (vector vs. vector+kg)
7:35 skip the outro and have fun with the repo!
7:52 attribution to Tomaž Bratanic and Anej Gorkič

Get your free Diffbot token to start building graph rag at:
app.diffbot.com/getstarted

Github repo for this Graph RAG project:
https://github.com/tomasonjo/diffbot...

#graphrag #knowledgegraphs #llms