System scope
- Uses a RAG chatbot so users can retrieve distributed internal enterprise documents and knowledge in natural language.
- Integrates vector retrieval, semantic indexing, and knowledge graphs to improve recall for related knowledge and multi-step queries.
Contributions and outcomes
- Designed and compared GraphRAG, LightRAG, Semantic Indexing, and different semantic query methods.
- Built retrieval experiments and an evaluation workflow, analyzed how architecture choices affect retrieval efficiency and answer quality, and organized the results into an enterprise knowledge question-answering system proposal.
- Collaborated with Delta Electronics and the NTNU Speech and Machine Intelligence Laboratory; Advisor: Prof. Berlin Chen.
Additional note: This is an internal enterprise research project; only the publicly shareable research scope is presented here.