arXiv：cs.AI· Sidney Shapiro, Joshua Lindemann·· 5 小时前AI 评分32
CourseChat：面向商科教育的本地化多课程 RAG 辅导系统及其软硬件权衡
On-Premises Multi-Course RAG Tutoring for Business Education: Hardware-Software Trade-offs in a Campus AI Tutor
AI 导读
研究团队推出 CourseChat，一个部署在校园网关后、面向本科商科教育的本地化多课程 RAG 辅导系统，计划嵌入 Moodle 使用。六个按课程编号（CRN）隔离的课程共享双边缘 AI 主机，运行 FastAPI 服务、本地向量数据库和由 Ollama 提供的本地 LLM。
正文
Abstract:Campus AI tutors based on retrieval-augmented generation (RAG) must ground answers in assigned course materials while keeping textbooks and student dialogue on institutional infrastructure. We present CourseChat, an on-premises, multi-course RAG tutor for undergraduate business education, deployed behind a campus web gateway and intended for use embedded in Moodle. Six isolated course offerings, each keyed by its own course reference number (CRN), share twin-edge AI hosts running a FastAPI service, a local vector database, and a local large language model (LLM) served by Ollama. We report two generation-model bake-off rounds, a separate fixed-evidence source-fidelity comparison, and conversation and quiz audits. Several larger models failed the classroom speed gate, but a 12B model and a 7B alternative passed. A separate mixture-of-experts candidate improved some corrections while introducing new factual and continuity errors. We therefore retain the 8B production model pending a demonstrated overall improvement, rather than claiming that 8B is universally optimal. Software changes improved follow-up topic resolution while preserving course scope; 435 prebuilt questions across 65 modules decouple practice from live generation. The results support treating model choice, evidence selection, serving compatibility, and product design as a joint engineering decision. They do not establish learning gains: faculty ratings, peak-load capacity, and complete public-gateway acceptance remain separate evaluation needs.
| Comments: | 23 pages, 3 figures, 4 tables |
| Subjects: | Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.02510 [cs.AI] |
| (or arXiv:2610.02510v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02510 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sidney Shapiro [view email]
[v1]
Thu, 1 Oct 2026 21:33:46 UTC (30 KB)
来源：arXiv：cs.AI · arxiv.org