Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/GingerlyData247/SOTeam4-P2/llms.txt

Use this file to discover all available pages before exploring further.

Trustworthy Model Registry

Deploy ML models with confidence. Automated trust scoring, lineage tracking, and compliance validation for enterprise environments.

Get StartedAPI Reference
Reproducibility: 1.0
License: Compatible
Reviewedness: 0.75
Net Score: 0.89

What is Trustworthy Model Registry?

The Trustworthy Model Registry (TMR) goes beyond traditional package managers by embedding trust, compliance, and governance directly into the ML artifact lifecycle. Instead of relying on popularity or manual review, engineering teams gain automated, repeatable assurances about the models they deploy.

Automated Trust Scoring

Compute 13+ trust metrics including reproducibility, license compatibility, reviewedness, and code quality automatically.

HuggingFace Integration

Ingest and evaluate public HuggingFace models automatically with full metadata extraction and lineage tracking.

AWS-Native Deployment

Deploy to AWS Lambda with S3 artifact storage, CloudWatch logging, and API Gateway integration out of the box.

Quick Start

Get up and running with the Trustworthy Model Registry in minutes.

1

Set up your environment

Install Python 3.12+ and configure your AWS credentials.
export AWS_REGION=us-east-2
export STORAGE_BUCKET=your-s3-bucket
export AUTH_TOKEN=your-admin-token
2

Start the API server locally

Clone the repository and start the FastAPI server.
git clone https://github.com/GingerlyData247/SOTeam4-P2.git
cd SOTeam4-P2
pip install -r requirements.txt
uvicorn src.run:app --reload
The API will be available at http://localhost:8000 with interactive docs at /docs.
3

Ingest your first model

Use the API to ingest a HuggingFace model and compute trust metrics.
curl -X POST "http://localhost:8000/api/artifact/ingest" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://huggingface.co/gpt2"}'

{
  "id": "1",
  "name": "gpt2",
  "category": "MODEL",
  "net_score": 0.85,
  "reproducibility": 1.0,
  "license": "mit",
  "reviewedness": 0.75
}
4

Query trust metrics

Retrieve detailed trust metrics for any artifact.
curl "http://localhost:8000/api/artifact/MODEL/1/rate"

Explore the Documentation

Dive deeper into the features and capabilities of the Trustworthy Model Registry.

Core Concepts

Learn about trust metrics, artifact lifecycle, and lineage tracking.

API Reference

Explore the complete REST API documentation with examples.

AWS Deployment

Deploy the registry to AWS Lambda with S3 and API Gateway.

CLI Tool

Use the command-line interface for batch model evaluation.

Ready to get started?

Start deploying ML models with automated trust verification and compliance validation.

Get Started Now