GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph

Join Tomaz Bratanic as he delves into the innovative use of retrieval-augmented generation (RAG) for developing LLM-based chatbots in the life sciences. Learn about the limitations of current language models, such as outdated information and hallucinations, and how RAG helps overcome these issues by incorporating up-to-date, context-specific data at query time. Discover the potential of integrating structured data from biomedical knowledge graphs to improve the accuracy and reliability of chatbot responses. Watch this video to explore practical implementations, including using predefined Cypher templates and tools for a more robust and deterministic approach.

Tomaz Bratanic
Graph ML and GenAI Expert – Neo4j