This research introduces a retrieval-augmented generation framework that integrates knowledge graphs with large language models to address hallucination problems in medical applications.

• Leverages Deepseek-R1 model with Weaviate vector database for accurate biomedical information retrieval
• Creates comprehensive knowledge graphs by extracting causal relationships and named entities from medical literature
• Significantly improves reliability for critical healthcare applications by grounding responses in verified medical knowledge
• Specifically targets accurate information delivery for age-related macular degeneration (AMD)

This innovation matters because it addresses a critical limitation in medical AI applications where factual accuracy can directly impact patient outcomes and healthcare decisions.

Knowledge Graph-Driven Retrieval-Augmented Generation: Integrating Deepseek-R1 with Weaviate for Advanced Chatbot Applications