AI Powered Knowledge Graph Generator for Video Learning Using RAG

educational-video-knowledge-fragmentation: Rapid growth of educational video content creates fragmented knowledge for learners.

poor-learning-retention: Video-based learning faces poor learner retention.

inefficient-content-retrieval: Learners face inefficient retrieval of information from educational videos.

lack-of-persistent-interconnected-learning: Existing video summarizers and note-taking systems do not provide a persistent and interconnected learning experience.

ai-knowledge-graph-video-learning-system: The paper proposes an AI-powered system that converts educational video content into an active, queryable knowledge base with knowledge graphs.

llm-transcript-multidimensional-analysis: The system extracts YouTube transcripts and uses large language models to generate structured learning artifacts such as summaries, quizzes, flashcards, and key insights.

semantic-embedding-vector-retrieval: The system encodes video content into high-dimensional semantic embeddings stored in a vector database for efficient retrieval.

rag-natural-language-querying: A Retrieval-Augmented Generation framework lets users query stored video knowledge in natural language and receive context-aware, source-grounded responses.

automated-cross-video-knowledge-graph: An automated knowledge graph captures relationships between concepts across multiple videos for visual exploration of interconnected knowledge.

improved-retention-and-retrieval-efficiency:

scalable-intelligent-video-learning-solution: