Exam Classifier Poc

F 49 completed
Other
web_app / javascript · tiny
15
Files
1,394
LOC
2
Frameworks
6
Languages

Pipeline State

completed
Run ID
#396340
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
46.38
Framework unique
Isolation
Last stage change
2026-05-10 03:35:10
Deduplication group #60485
Member of a group with 1 similar repo(s) — this repo is canonical view group →
Top concepts (2)
Project DescriptionWeb Backend
Repobility · code-quality intelligence platform · https://repobility.com

AI Prompt

Create a web application that can automatically process an English exam PDF. The system needs to split the PDF into individual questions and then classify each question against a predefined taxonomy using the Gemini 2.0 Flash API. The frontend should allow a user to upload a PDF, and upon processing, display reviewable question cards. These cards must show confidence tags (green for $\ge 85\%$, orange for $70-84\%$, and red for $<70\%$) and allow hovering to see the full taxonomy breakdown across five dimensions (Subject, Unit, Section, Learning Point, Type). The backend should be built with FastAPI, and the frontend with React.
javascript react fastapi python gemini pdf-processing web-app classification
Generated by gemma4:latest

Catalog Information

Auto-splits an English exam PDF into individual questions and classifies each one against a taxonomy using Gemini 2.0 Flash.

Description

Auto-splits an English exam PDF into individual questions and classifies each one against a taxonomy using Gemini 2.0 Flash.

Novelty

3/10

Tags

javascript react fastapi python gemini pdf-processing web-app classification

Claude Models

claude-opus-4-6

Quality Score

F
49.2/100
Structure
39
Code Quality
52
Documentation
42
Testing
0
Practices
81
Security
100
Dependencies
60

Strengths

  • Good security practices \u2014 no major issues detected

Weaknesses

  • No LICENSE file \u2014 legal ambiguity for contributors
  • No tests found \u2014 high risk of regressions
  • No CI/CD configuration \u2014 manual testing and deployment
  • 124 duplicate lines detected \u2014 consider DRY refactoring
  • 2 'god files' with >500 LOC need decomposition

Recommendations

  • Add a test suite \u2014 start with critical path integration tests
  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
  • Add a linter configuration to enforce code style consistency
  • Add a LICENSE file (MIT recommended for open source)

Security & Health

5.1h
Tech Debt (D)
A
OWASP (100%)
FAIL
Quality Gate
B
Risk (21)
Powered by Repobility — scan your code at https://repobility.com
Unknown
License
0.8%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

javascript
50.3%
python
40.0%
markdown
5.9%
json
1.7%
html
1.3%
text
0.8%

Frameworks

FastAPI React

Concepts (2)

Analysis by Repobility (https://repobility.com) · MCP-ready
CategoryNameDescriptionConfidence
Citation: Repobility (2026). State of AI-Generated Code. https://repobility.com/research/
auto_descriptionProject DescriptionAuto-splits an English exam PDF into individual questions and classifies each one against a taxonomy using Gemini 2.0 Flash.80%
auto_categoryWeb Backendweb-backend70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/120701.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV