Building Agentic AI Assistants with Graphs Retrieval Augmented Generation

Discover how the latest GraphRAG technology combines conversational LLMs, knowledge graphs, document retrieval, and source evidence to create more connected, transparent, and explainable AI applications. Unlike traditional chat systems that retrieve isolated text passages, GraphRAG connects entities and relationships, retrieves relevant local or global context, and generates responses that can be inspected and traced back to supporting evidence. This approach is especially valuable for questions involving connected concepts, multi-step reasoning, and broad understanding of large document collections. The presentation will explain the GraphRAG architecture and demonstrate a healthcare and life-sciences use case developed with Python, OpenAI, LangGraph, SQLite, and structured JSON. The example knowledge graph connects concepts such as symptoms, diagnoses, procedures, body sites, genes, proteins, drugs, diseases, experiments, and evidence sources.The demonstration uses a synthetic clinical knowledge graph. A user asks:

“What procedure is supported for a patient with cough and shortness of breath when suspected pneumonia is documented and a chest radiograph with two views is ordered?”

The system identifies explicit clinical facts, traverses the knowledge graph, retrieves the relevant relationship path, asks an OpenAI agent to use only retrieved candidates, and returns an evidence-bearing response. Demo code identifiers are used instead of production CPT records. For more information look at the series of biotech papers at “Artificial Intelligence Applications in Biostatistics, Bioinformatics and Computational Biology by Ernest Bonat, Ph.D.”

What you will learn?

• The difference between traditional RAG and GraphRAG
• How entities, relationships, and evidence are represented in a knowledge graph
• How local, global, and relationship-based retrieval work
• How LangGraph orchestrates retrieval, reasoning, and validation
• How structured JSON supports transparent AI responses
• How GraphRAG can be applied responsibly in healthcare and biotechnology
• Why synthetic data, auditability, validation, and human review are important in clinical AI

This session is intended for AI and machine-learning engineers, data scientists, bioinformaticians, computational biologists, healthcare professionals, biotech researchers, students, educators, and anyone interested in practical applications of Generative AI and GraphRAG**.**

Who should attend:
This presentation is designed for AI/ML engineers, data scientists, software developers, bioinformatics professionals, healthcare technology professionals, researchers, medical informaticists, and anyone interested in practical applications of Agentic AI in healthcare and life sciences. No advanced knowledge of Agentic AI is required. The presentation will introduce the architecture step by step and conclude with a practical multi-agent clinical coding demonstration.

Agenda:
· 5:30 – 6:00 pm: Networking and refreshments
· 6:00 – 6:10 pm: Welcome!
· 6:10 – 7:30 pm: Presentation and open discussion
· 7:30 – 8:00 pm: Networking

Location: Entrepreneur Collaborative Center, 2101 East Palm Avenue, Tampa, FL 33605

Parking: Free parking is available in the lot directly north of the ECC building. Please do not park immediately adjacent to the facility.

RSVP: Seating is limited — please RSVP early. If you're bringing a guest, have them RSVP separately so we can plan accordingly.

Speakers:
Ernest Bonat, Ph.D. — Senior GenAI Engineer specializing in Machine Learning systems and AI assistants for Biostatistics , Bioinformatics, Computational Biology, and Healthcare.