Chaininsight

C+ 74 completed
Api
containerized / python · small
126
Files
16,876
LOC
6
Frameworks
10
Languages

Pipeline State

completed
Run ID
#345631
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
80.00
Framework unique
Isolation
Last stage change
2026-05-10 03:35:28
Deduplication group #65371
Member of a group with 1 similar repo(s) — this repo is canonical view group →
Top concepts (2)
Project DescriptionWeb Frontend
Provenance: Repobility (https://repobility.com) — every score reproducible from /scan/

AI Prompt

Create an end-to-end supply chain inventory analytics platform called ChainInsight. I need this system to handle hierarchical forecasting, reinforcement learning for replenishment, and MLOps pipelines. The core functionality should involve ingesting data, running 6 forecasting models, reconciling predictions using 4-layer hierarchical forecasting (MinTrace), and optimizing inventory with curriculum-learning RL (PPO+SAC). The platform should be containerized, ideally using FastAPI for the API and have a React frontend. Please structure the project to include components for the Data Layer, Forecasting Layer, and RL Layer, ensuring the architecture is robust enough for a 200-SKU retail supply chain.
python fastapi react mlops supply-chain forecasting reinforcement-learning sqlalchemy vite containerization
Generated by gemma4:latest

Catalog Information

An API that delivers end‑to‑end supply‑chain inventory analytics, combining hierarchical forecasting, reinforcement‑learning replenishment, and MLOps pipelines.

Description

The system exposes a set of RESTful endpoints that accept historical sales and inventory data, process it through a hierarchical forecasting engine, and return multi‑level demand predictions. It then feeds these forecasts into a reinforcement‑learning agent that learns optimal reorder policies under constraints such as lead time and storage capacity. The platform integrates MLOps practices, enabling continuous training, versioning, and deployment of models via automated pipelines. Designed for logistics and operations teams, it helps reduce stockouts and excess inventory while improving service levels. The solution is built on a lightweight Python stack, making it easy to embed in existing data workflows.

الوصف

يقدم النظام مجموعة من نقاط النهاية RESTful التي تستقبل بيانات المبيعات والمخزون التاريخية، وتقوم بمعالجتها عبر محرك التنبؤ الهرمي لإرجاع توقعات الطلب على مستويات متعددة. ثم يتم تغذية هذه التوقعات إلى وكيل التعلم التعزيزي الذي يتعلم سياسات إعادة التزويد الأمثل مع مراعاة قيود مثل زمن التسليم وسعة التخزين. يدمج النظام ممارسات MLOps، مما يتيح التدريب المستمر، وإصدار النماذج، ونشرها عبر خطوط أنابيب آلية. صمم هذا الحل للفرق اللوجستية والعمليات، ويساعد على تقليل نقص المخزون والوفرة الزائدة مع تحسين مستويات الخدمة. يعتمد على بنية Python خفيفة الوزن، ما يسهل دمجه في سير العمل البياني الحالي. يتيح للمحللين إمكانية مراقبة الأداء وتحديث النماذج دون انقطاع. كما يوفر واجهة مرنة للتكامل مع أنظمة تخطيط موارد المؤسسات (ERP) لتسهيل تبني الحل على نطاق واسع.

Novelty

7/10

Tags

supply-chain-analytics inventory-forecasting hierarchical-forecasting reinforcement-learning mlops time-series demand-planning inventory-optimization

Technologies

fastapi matplotlib numpy pandas pytorch scikit-learn scipy sqlalchemy uvicorn

Claude Models

claude-opus-4.6

Quality Score

C+
74.4/100
Structure
73
Code Quality
74
Documentation
68
Testing
65
Practices
82
Security
92
Dependencies
60

Strengths

  • CI/CD pipeline configured (github_actions)
  • Code linting configured (ruff (possible))
  • Good security practices \u2014 no major issues detected
  • Containerized deployment (Docker)
  • Properly licensed project

Weaknesses

  • 1008 duplicate lines detected \u2014 consider DRY refactoring
  • 4 'god files' with >500 LOC need decomposition

Security & Health

7.3h
Tech Debt (B)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (1)
Repobility · code-quality intelligence platform · https://repobility.com
MIT
License
4.3%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
55.2%
json
22.5%
typescript
14.0%
markdown
6.1%
yaml
1.1%
toml
0.4%
javascript
0.4%
css
0.1%
text
0.1%
html
0.1%

Frameworks

FastAPI React pytest Tailwind CSS Vite SQLAlchemy

Concepts (2)

Generated by the Repobility scanner · https://repobility.com
CategoryNameDescriptionConfidence
Repobility · code-quality intelligence platform · https://repobility.com
auto_descriptionProject DescriptionNixtla-format time series forecasting with rigorous statistical evaluation, hierarchical reconciliation, and curriculum-learning RL for a 200-SKU retail supply chain80%
auto_categoryWeb Frontendweb-frontend70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/69698.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV