Skip to main content

​
Introduction

Vishwas provides APIs to measure and monitor fairness in AI systems, generate human-readable explanations, and create compliance-ready audit reports.

Analyze Fairness

Measure bias across protected attributes

Explain Predictions

Generate interpretable explanations

Generate Reports

Create audit-ready compliance reports

​
Key Features

​
Fairness Metrics

Vishwas supports 15+ industry-standard fairness metrics:
CategoryMetrics
Group FairnessDemographic Parity, Equalized Odds, Equal Opportunity
CalibrationCalibration, Sufficiency, Balance
IndividualIndividual Fairness, Counterfactual Fairness
CausalCausal Discrimination, Path-Specific Effects

​
Explanation Methods

MethodBest For
SHAPFeature importance with game-theoretic foundation
LIMELocal interpretable explanations
AnchorsRule-based explanations
Counterfactuals”What-if” scenarios
PrototypesSimilar examples from training data

​
Indian Context

Vishwas includes India-specific enhancements:
  • Protected attributes: Caste, religion, regional origin
  • Language support: Explanations in 12 Indian languages
  • Regulatory mapping: RBI, SEBI, IRDAI guidelines

​
Quick Example

from rotavision import Rotavision

client = Rotavision()

# Analyze fairness
analysis = client.vishwas.analyze(
    model_id="loan-approval-v2",
    dataset={
        "features": features,
        "predictions": predictions,
        "actuals": actuals,
        "protected_attributes": ["gender", "region"]
    },
    metrics=["demographic_parity", "equalized_odds"]
)

print(f"Overall Score: {analysis.overall_score}")
print(f"Bias Detected: {analysis.bias_detected}")

# Explain a prediction
explanation = client.vishwas.explain(
    model_id="loan-approval-v2",
    input_data=applicant_features,
    prediction=0.73,
    method="shap"
)

print(f"Top factors: {explanation.top_features}")

​
Endpoints

MethodEndpointDescription
POST/vishwas/analyzeRun fairness analysis
GET/vishwas/analyses/{id}Get analysis results
GET/vishwas/analysesList analyses
POST/vishwas/explainExplain a prediction
POST/vishwas/reportsGenerate compliance report
GET/vishwas/reports/{id}Get report status/download