Semih Salihoglu on harnessing LLMs – from queries to knowledge graphs and beyond.
Subscribe: Apple • Spotify • Overcast • Google • AntennaPod • Podcast Addict • Amazon • RSS.
Semih Salihoglu is an Associate Professor at University of Waterloo, and co-creator of Kuzu an open source embeddable property graph database management system. This episode explores the use of large language models (LLMs) for generating queries across different query languages like SQL and Cypher for graphs. It examines the potential and limitations of LLMs in handling complex query constructs like recursion, subqueries, and joins.
The episode also covers the integration of knowledge graphs with retrieval-augmented generation (RAG) systems for question answering, and the automated construction of knowledge graphs from text using LLMs. Additionally, it touches on broader observations around combining LLMs with logic-based reasoning, the need for rigorous benchmarking and evaluation, and the role of data modeling in LLM performance. Overall, the episode provides insights into the current state and future directions of leveraging LLMs and knowledge graphs for various data querying, retrieval, and reasoning tasks.
Semih Salihoglu’s blog posts:
- RAG using structured data: Overview & important questions
- RAG using unstructured data and the role of knowledge graphs
Interview highlights – key sections from the video version:
- Limitations of LLMs for Generating Complex Queries
- The Effect of Data Modeling on LLM Performance for Data Querying
- Metadata, Open Data, and Enhancing LLMs
- Knowledge Graphs for Enhanced Question Answering
- Automated Knowledge Graph Construction with LLMs
- The Future of Auto-Ranking and Knowledge Graphs
Related content:
- A video version of this conversation is available on our YouTube channel.
- Boosting RAG Systems with Knowledge Graphs: Early Insights
- What Every Competent GDBMS Should Do (aka The Goals & Vision of Kùzu)
- What is Graph Intelligence?
- Philipp Moritz and Goku Mohandas: Navigating the Nuances of Retrieval Augmented Generation
- Emil Eifrem: The Future of Graph Databases
- Sudhir Hasbe: Trends in Data Management: From Source to BI and Generative AI
- Juan Sequeda and Dean Allemang: Contextualizing Enterprise Data for More Accurate LLMs
- Brian Raymond: ETL for LLMs
- Jerry Liu: An Open Source Data Framework for LLMs
If you enjoyed this episode, please support our work by encouraging your friends and colleagues to subscribe to our newsletter: