Spaces:
Runtime error
Runtime error
Evaluation Suite
This directory contains a modular evaluation framework for the Fraud Model Explainability Assistant, built using the Strands Evaluation SDK while maintaining Langfuse + OpenTelemetry integration.
Structure
evals/
βββ __init__.py # Package initialization
βββ config.py # Shared evaluator configurations
βββ task_functions.py # Agent wrapper functions
βββ langfuse_reporter.py # Langfuse integration
βββ dataset_loader.py # JSON to Case conversion
βββ generate_experiment.py # SDK Experiment Generator
βββ run_helpfulness.py # Helpfulness evaluation
βββ run_trajectory.py # Trajectory evaluation
βββ run_full_suite.py # Full evaluation suite
Usage
Run Individual Evaluations
# Helpfulness only
python -m evals.run_helpfulness
# Trajectory only
python -m evals.run_trajectory
Run Full Suite
# All evaluators (Helpfulness, Faithfulness, Trajectory, Goal Success)
python -m evals.run_full_suite
Generate Synthetic Data
# Generate new test cases using SDK ExperimentGenerator
python -m evals.generate_experiment
Features
- SDK-Aligned: Uses
Experiment.run_evaluations()framework - Modular: Each evaluation type in separate file
- Langfuse Integration: Automatic score logging with trace correlation
- OpenTelemetry: Full observability stack integration
- Extensible: Easy to add new evaluators or metrics
Evaluators
- Helpfulness (
OutputEvaluator): Rates answer quality (accuracy, completeness, clarity) - Faithfulness (
OutputEvaluator): Verifies answer is grounded in retrieved context - Trajectory (
TrajectoryEvaluator): Checks tool usage sequence - Goal Success (Heuristic): Matches expected key points in answer
Comparison with evaluate.py
The modular suite provides the same functionality as the monolithic evaluate.py but with:
- β Better code organization
- β SDK-standard patterns
- β Easier to extend with new evaluators
- β
Built-in reporting (
report.run_display(),get_summary()) - β Maintains Langfuse + OTel integration