The Data Exchange with Ben Lorica Why ‘Structure’ Is All You Need: A Deep Dive into Next-Gen AI Retrieval
67 snips
Feb 13, 2025 
Tom Smoker, co-founder of WhyHow.ai, shares insights on transforming unstructured data into structured knowledge. He discusses how knowledge graphs enhance AI retrieval, citing successful applications at LinkedIn and Pinterest. The conversation delves into the complexities of building these graphs and the balance between automation and intentional design. They also tackle the hallucination problem in AI, emphasizing the role of data clarity. Smoker argues for leveraging operational data to improve AI systems, showcasing the potential of graph-based methodologies.
AI Snips
Chapters
Transcript
Episode notes
Using Structure in RAG
- Leverage structure like SQL databases or metadata even without a full knowledge graph.
- Infuse RAG queries with queries from structured data sources for improved retrieval.
Knowledge Graph Basics
- A knowledge graph can be defined as a knowledge base with axioms (rules and reasoning).
- Even a simple .txt file with triples (word connections) offers valuable structured data for retrieval.
Veterinary Radiology Use Case
- In a veterinary radiology case, Graph RAG helped specify context for bulldog conditions.
- Standard LLMs struggled to focus on bulldogs, recommending treatments for Labradors instead.