Skip to content

MUJINN/score-dimension

Repository files navigation

Score Dimension Service

A service for generating structured scoring dimensions from problem statements, reference answers, total score, and subject metadata. It is designed as a reusable building block inside AI grading workflows.

What this project does

  • Accepts problem content, reference answers, total score, and subject information
  • Calls a workflow service to generate scoring rubrics
  • Returns structured score-dimension results for downstream grading systems
  • Filters oversized base64 image payloads before processing

Why it matters

AI grading systems become much more useful when they can produce structured scoring rubrics instead of only raw scores. This repository represents that middle-layer capability.

Main files

  • app/main.py: FastAPI application entry
  • app/api/routers/score_dimension.py: score-dimension endpoints
  • app/services/dify_service.py: workflow integration logic
  • app/core/config.py: runtime configuration

Quick start

pip install -r requirements.txt
uvicorn app.main:app --host 0.0.0.0 --port 8080

Key capabilities

  • Scoring rubric generation
  • FastAPI service structure
  • Workflow integration
  • Input sanitation for base64-heavy content

Notes

This public repository is a cleaned release version. Local environment files, logs, caches, and virtual environments were excluded.

About

Service for generating structured scoring dimensions from problems, answers, and score metadata.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages