Researchers have developed CourseChat, an on-premises RAG tutoring system designed for undergraduate business education. The system grounds answers in course materials and operates within institutional infrastructure, utilizing a FastAPI service, local vector database, and an Ollama-served LLM. Evaluations showed that while some larger models struggled with speed, a 12B model and a 7B alternative were viable, leading to the retention of an 8B production model for its overall performance. AI
IMPACT Provides insights into practical deployment challenges and model selection for on-premises RAG systems in educational settings.
RANK_REASON The cluster describes a research paper detailing the development and evaluation of a specific AI application (a campus tutor) and its hardware-software trade-offs.
Read on arXiv cs.IR (Information Retrieval) →
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →