← Back to project catalogue
GP-CS-117QU6GComputer ScienceReady

Multilingual campus service assistant

A multilingual information retrieval system that answers campus-service questions from approved university documents in English and Hindi, with citations to the original source.

Multilingual campus service assistant project visual
GP-CS-117QU6G · Computer Science
  • Nuxt
  • Vue
  • FastAPI
  • PostgreSQL
  • pgvector
  • Python
  • Docker

Project definition

Problem statement

University service information is often spread across circulars, PDF notices, department pages, handbooks, and frequently changing announcements. Students may know the question they need to ask without knowing which office or document contains the answer.

A general chatbot can produce a fluent response without reliable evidence. This project instead limits answers to approved campus material, shows the supporting source, and avoids answering when the available evidence is insufficient.

Project objectives

  • Answer routine campus-service questions using only approved institutional documents.
  • Accept questions in English and Hindi while preserving the meaning of the original source.
  • Attach document citations to answers so students can verify important information.
  • Give authorised staff a controlled way to add, replace, archive, and re-index documents.
  • Measure retrieval quality, citation correctness, response usefulness, and refusal behaviour.

Project structure

Project components

01

Document preprocessing

Extracts text from approved PDF and text documents, divides it into traceable passages, and records source metadata.

02

Language processing

Detects the query language, normalises the input, and supports English and Hindi retrieval through a replaceable multilingual pipeline.

03

Semantic retrieval

Creates vector representations, finds relevant passages, ranks results, and retains document and page references.

04

Answer composer

Selects supporting sentences from retrieved passages, attaches citations, and rejects unsupported questions.

05

Document control

Allows authorised staff to add, replace, archive, re-index, and classify university documents.

06

Evaluation subsystem

Runs prepared questions and records retrieval, citation, refusal, and latency metrics.

Methodology

Project workflow

  1. 01
    Input approved documents

    A staff user uploads a notice, handbook, form, or service document with its language, category, owner, and effective date.

  2. 02
    Build the retrieval index

    The system extracts and segments the content, creates vector representations, and retains references to the original pages.

  3. 03
    Process the question

    The system detects and normalises a question submitted in English or Hindi.

  4. 04
    Retrieve evidence and compose an answer

    Relevant passages are ranked and the best supported sentences are returned with the documents and pages used.

  5. 05
    Evaluate the result

    Prepared answerable and refusal questions are used to calculate and review system performance.

Demonstration scenario

A student asks in Hindi about an active scholarship notice. The assistant returns a concise answer with the relevant document and page citation. An administrator can replace the notice through the protected API and verify that the next query uses the updated source.

Engineering

Tools and method

Web application
Nuxt and Vue for the student question experience, with accessible responsive layouts.
Application API
FastAPI for protected document workflows, query handling, access control, and health checks.
Data layer
PostgreSQL for documents and metadata, with pgvector storage and an HNSW index.
Language pipeline
Python-based document processing, language detection, Hindi term aliases, and deterministic character-vector retrieval.
Answer strategy
Extractive answers with page citations, confidence thresholds, and unsupported-answer refusal.
Delivery
Docker-based local setup and deployment documentation with application secrets kept outside source control.

Testing

Evaluation

Evaluation measures

  • Relevant-passage retrieval rate across the prepared question set
  • Citation correctness and source-page traceability
  • Groundedness and unsupported-answer refusal rate
  • English and Hindi meaning consistency on paired questions
  • Response latency under the defined demonstration workload

Project boundaries

  • The assistant does not make admissions, fee, scholarship, disciplinary, or academic decisions.
  • It does not search the unrestricted public web or treat unapproved material as university policy.
  • It does not expose private student records or require personal information for routine questions.
  • Low-confidence or unsupported questions are redirected to the responsible campus office.

Included

  1. 01Student query interface and protected document administration API
  2. 02Approved-document ingestion, indexing, retrieval, and citation pipeline
  3. 03English and Hindi question support with an adapter for additional languages
  4. 04Prepared evaluation dataset, test results, and demonstration scenarios
  5. 05Complete source code in a private GitHub repository
  6. 06Complete project documentation in PDF and editable Word formats with synopsis, abstract, methodology, architecture diagrams, test results, screenshots, and conclusion

Project record

No information is collected on this page.

Permanent project ID
GP-CS-117QU6G
Catalogued
21 Aug 2026
Completed
23 Aug 2026
Verified
23 Aug 2026
Demonstration
Included in repository

Handover

After purchase

  1. 01
    Payment is confirmed

    The project is marked unavailable and cannot be purchased again.

  2. 02
    Repository access is granted

    The buyer's submitted GitHub account receives access to the private repository.

  3. 03
    The purchase record is delivered

    The certification sheet is prepared from the reviewed buyer details and sent privately by email.