In this blog post by Tomaz Bratanic on the Neo4j Developer Blog, he discusses the use of Large Language Models (LLMs) in conjunction with knowledge graphs to enable multi-hop question answering. This approach is particularly useful when a single question requires information from multiple documents or requires multiple sub-questions to be answered. The blog post also discusses the retrieval-augmented approach to LLM applications and how vector similarity search is used to identify relevant data to enhance the LLMs ability to generate accurate and relevant answers. The post is part of Neo4js NaLLM project, which aims to explore practical uses of LLMs in conjunction with Neo4j and provide an open space for the community to observe, learn, and contribute.
