RESEARCH · RESEARCH · #1502
CourseChat: on‑premises multi-course RAG tutor for business education (arXiv:2610.02510v1)
The authors present CourseChat, an on-premises, multi-course retrieval-augmented generation (RAG) tutor deployed behind a campus web gateway and integrated for use with Moodle; it runs twin edge hosts with FastAPI, a local vector database, and an LLM served via Ollama across six isolated course CRNs. The paper reports two model bake-offs, a source-fidelity comparison, conversation and quiz audits, finds that larger models failed classroom speed constraints while 12B and 7B passed and a mixture-of-experts introduced new errors, and retains an 8B production model pending demonstrated overall improvement; the study does not evaluate learning gains or public-gateway acceptance.
KEY POINTS
- The authors present CourseChat, an on-premises, multi-course retrieval-augmented generation (RAG) tutor deployed behind a campus web gateway and integrated for use with Moodle; it runs twin edge hosts with FastAPI, a local vector database, and an LLM served via Ollama across six isolated course CRNs.
- The paper reports two model bake-offs, a source-fidelity comparison, conversation and quiz audits, finds that larger models failed classroom speed constraints while 12B and 7B passed and a mixture-of-experts introduced new errors, and retains an 8B production model pending demonstrated overall improvement; the study does not evaluate learning gains or public-gateway acceptance.
- This work demonstrates practical hardware–software trade-offs and on‑premises design choices for deploying RAG tutors in real campus environments, highlighting performance, fidelity, and product decisions that affect classroom applicability.
WHY IT MATTERS
This work demonstrates practical hardware–software trade-offs and on‑premises design choices for deploying RAG tutors in real campus environments, highlighting performance, fidelity, and product decisions that affect classroom applicability.