Boosting LLM accuracy with Entity Resolution-based RAG

Enterprises are increasingly looking to run Large Language Models (LLMs) on private, internal data that LLMs have never seen and which must remain confidential. Retrieval Augmented Generation (RAG) enhances LLMs with data from specific, controlled sources. Typically, RAG uses vector databases, which excel at retrieving information from unstructured data. However, for structured data like customer records, a different RAG approach may be better. In this talk, we introduce Entity RAG, which uses real-time entity resolution to provide LLMs with accurate, unified data about real-world entities such as customers, companies, and products. We will showcase a use case integrated with Langchain, demonstrating the benefits of using entity resolution technology alongside vector databases. You will learn how to quickly set up an entity resolution system to deliver fast, accurate entity data to your LLM.

Steven Renwick

Tilores

Steven is co-founder and CEO of Tilores, the API for unifying scattered customer data in real-time. Originally from Scotland, Steven started in the biological sciences and has a PhD in Genetics from UCL and an MBA from Oxford University. Before founding Tilores he was the CPO at a German consumer credit bureau, Regis24, where Tilores' entity resolution technology was originally conceived. Previously, he founded the UK fintech company, Satago.