On-premise OER-based AI knowledge-base assistant system for computer science education

Design · All designs
Evidence · 2 claims (2 for) · 1 study (1 design), q2 · 0 of 1 report an effect size · 2 claims rest on one study

Description

A three-subsystem architecture comprising an LMS Layer, a Knowledge Base Layer with structured extraction and a FAISS vector index, and an AI Inference Layer with curriculum alignment and model optimization modules. The article states that "all components operate entirely on-premise on a consumer-grade GPU (RTX 3060, 12 GB VRAM), with no external API calls". It ingests 82 open-licensed Markdown documents (~347,000 tokens) from MIT OpenCourseWare, OpenStax, CS50 and WikiCS, and serves student queries via retrieval-augmented generation with quantized Qwen-7B or DeepSeek-MoE models.

Design Implications

Context

Requirements

• Openly licensed OER documents (Creative Commons or OSI-compatible) as the knowledge corpus
• A consumer-grade GPU with at least 12 GB VRAM for deployment

Constraints

• The article characterizes it as a knowledge-base assistant rather than a validated intelligent tutor; no controlled learner study was conducted
• Evaluation dataset drawn from English-medium OER platforms; multilingual extension is future work

Target Learners

• introductory undergraduate computer science students

Learning Goals

• factual recall, concept explanation, and multi-hop reasoning about introductory computer science topics

Claims

• Deepseek Moe Ours Strongest Accuracy Balance [+M]
• Nf4 Quantization Vram Reduction [+M]

Related Designs

Examples

-

Key Sources

• Shen X, Feng L, Hua S, Liu D, Xie Z and Liu B (2026) Towards sustainable AI knowledge-base assistants in computer science education: on-premise deployment and optimization with open educational resources. Front. Psychol. 17:1843444. https://doi.org/10.3389/fpsyg.2026.1843444

Page metadata

Field	Value
type	design
id	on-premise-oer-knowledge-base-assistant-system
title	On-premise OER-based AI knowledge-base assistant system for computer science education
description	A three-subsystem architecture comprising an LMS Layer, a Knowledge Base Layer with structured extraction and a FAISS vector index, and an AI Inference Layer with curriculum alignment and model optimization modules.
status	review
generated	by process:settle-candidates on 2026-10-11
trust	unverified — no one has confirmed this page's content
sources	1 — shen-x-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.