Back to Homepage
Project Page XDU Freshmen Assistant

Entry for the 2026 XDU Spark Cup Agent Development Competition

XDU Freshmen Assistant

A campus QA project for first-year students at Xidian University

The project has completed local prototyping and launched an initial cloud release. Users now only need to open a single web page in the browser to access campus Q&A and document-based questioning. The current scope focuses on onboarding, study planning, competition entry, campus resources, and routine procedure guidance.

Target Users XDU freshmen
Release Status Initial cloud version online
Current Capability Text Q&A + document text Q&A

Project Background

Project Need

The project is designed for first-year students at Xidian University. For freshmen, the core issue is not a total lack of information, but the fact that campus information is scattered across department notices, chat groups, academic affairs pages, experience posts, and loose documents. Students often need to handle onboarding, study planning, competition entry, resource access, and routine procedures at the same time, so a single dialogue-based entry point is needed.

  • Information sources are scattered during onboarding, making it hard to decide what to read and do first
  • Training schemes, course plans, and study priorities are not easy to interpret at the beginning
  • Competition directions are numerous, yet freshmen still need clearer beginner-oriented guidance
  • Campus resources and routine procedures still require too much manual searching

Functional Overview

Core Functions

The current release is already online, and the frontend, backend, knowledge base, and baseline engineering path have all been connected.

Current module

Text-based Q&A

Users can type questions directly in the browser, with current coverage focused on onboarding, study planning, competitions, campus resources, and routine procedures

Current module

Conversation Interaction

The interface supports new chat reset, quick prompt cards, and a more natural streaming-style output to reduce context carryover and improve the basic dialogue experience

Current module

Markdown Rendering

The frontend correctly renders headings, lists, code blocks, and tables, making longer and more structured answers easier to read

Current module

Document Text Q&A

The system accepts common document formats such as PDF, DOCX, XLSX, PPTX, and TXT, extracts their text, and supports follow-up questions about the uploaded content

Current module

Knowledge-first Answering

The backend follows a local-knowledge-first strategy: it retrieves and summarizes local materials first, then uses Coze capability as a supplement

Current module

Source Type Hints

Answers retain user-facing source hints, such as public library guidance notes.

Technical Structure

Main Technical Path

The current system uses a hybrid architecture: static frontend page + cloud Python backend + local knowledge augmentation + Coze capability supplement. The online version has already been built into a complete browser-accessible QA flow.

01 Static Frontend Page

Handles the chat interface, input area, quick prompts, Markdown rendering, attachment upload, and chat reset.

02 Cloud Python Backend

Provides OpenAI-compatible endpoints for chat, attachment text extraction, and service health checks.

03 Local Knowledge Augmentation

Loads, retrieves, and summarizes locally curated campus materials before final response generation.

04 Coze Capability Supplement

Supplies the external generation layer after local knowledge has already provided the primary grounding.

Frontend Independent static web page

Used for chat UI, quick prompts, attachment upload, streaming output, and Markdown rendering.

Backend API Python backend service

Handles the main chat requests, document text extraction, and baseline service health checks for the frontend.

Knowledge Base raw / curated / templates layering

The knowledge base covers freshman Q&A, campus resources, procedures, study guidance, competitions, and public program information.

Deployment & Ops Cloud deployment and baseline operations

The online release runs on a cloud server, with Nginx, systemd, and HTTPS covering public access, process uptime, and basic security.

Engineering Smoke tests + GitHub Actions

Baseline checks already cover health, chat response shape, attachment extraction, and knowledge loading and retrieval.

Current Status

Current Delivery Status

Completed

Initial Cloud Release

The project has completed a cloud deployment, and users can directly access the frontend and use the core QA functions

Completed

End-to-end QA Flow

Frontend, backend, local knowledge support, and Coze capability supplement have been integrated into one usable path

Completed

Document Text Handling

The online version already supports document text extraction and follow-up questioning over the extracted content

Completed

Deployment and Security Baseline

Nginx, systemd, HTTPS, server-side environment variables, and localhost-only backend listening have all been set in place

Completed

Baseline Engineering Support

The repository already includes baseline tests and GitHub Actions CI, so the project is beyond a bare runnable prototype

Scope Boundary

Current Positioning

The project is stable enough for demonstration and online access, but it is not yet positioned as a long-term public commercial system; time-sensitive information should still follow the latest official notices from the university and departments.

Demo / Usage

Online Version Demonstration

Showcase Focus Demonstration of the current cloud release

The video corresponds to the current browser-accessible release path. It can be played directly on this page and viewed together with the proposal as supporting context.

Demo Video

Recorded usage flow corresponding to the current cloud release, playable directly on the page.

Future Work

Planned Improvements

  • Add stronger annual verification and refresh mechanisms for time-sensitive policy and scholarship information.
  • Continue structuring the knowledge base and strengthen retrieval, summarization, and citation stability.
  • Evaluate OCR, scanned-document support, and broader multimodal enhancement beyond the current text-only attachment path.
  • Improve long-term public deployment support with better monitoring, traffic control, and operational visibility.
  • Keep the current lightweight online path stable while gradually extending the fuller agent-oriented engineering branch.