From Ancient Epic to Modern Marvel: Demystifying the Mahabharata Chatbot with GraphRAG
summary
A working web chatbot maps the Mahabharata into Neo4j and uses GraphRAG plus the Gemini API to translate natural language into Cypher and return graph-aware answers. Initial manual graph stores 191 main character nodes and 579 relationships; automated LLM Graph Builder ingest of 18 PDFs produces ~50,000 nodes and ~500,000 relationships. The system retrieves shortest paths, contextualizes alliances and causal links, and serves answers via a demo web app — a usable version one with room for multilingual and VR extensions.
AI-written summary · about
chapters (11)
- 0:00Introduction to the talk
- 1:12What is the Mahabharata
- 3:19Relationships in the Mahabharata
- 5:06Why graph databases for this epic
- 5:48Graphing the Mahabharata step-by-step
- 8:17Making the graph accessible
- 10:46Introducing GraphRAG
- 12:10Using LLM Graph Builder tool
- 13:57Results and next steps
- 14:59Future possibilities for the chatbot
- 16:01Resources and conclusion
related talks
32mDemystifying the Mahabharata with GraphRAG
30mAgentic RAG with Knowledge Graphs Explained
33mSmarter Industrial Fault Diagnosis with Knowledge Graphs and Large Language Models
01h 17mGraph Database and Retrieval Augmented Generation
27mWhen Vectors Aren’t Enough: Unlocking AI’s Hidden Connections with Graphs
26mPractical GraphRAG Making LLMs smarter with Knowledge Graphs
29mKnowledge graph based chatbots
30mThe GraphRAG System That Asks Back: Intelligent Probing with Better Contextual Answers