Spaces:
Running
Running
""" | |
GAIA Solver Test Suite | |
This package contains all test scripts and utilities for the GAIA benchmark solver. | |
Test Scripts: | |
- test_specific_question.py: Test individual questions by ID | |
- test_routing_integration.py: Test multi-agent routing system | |
- test_classification_only.py: Test question classification only | |
- test_loader.py: Test question loading functionality | |
- test_web_loader.py: Test web-based question loading | |
- validate_answers.py: Validate answers against GAIA metadata | |
- validate_all_questions.py: Comprehensive validation suite | |
- validate_rd5_consensus.py: Chess analysis validation | |
Utilities: | |
- test_logging_utils.py: Shared logging utilities for all tests | |
Usage: | |
cd /path/to/GAIA_Solver | |
source venv/bin/activate | |
python tests/test_specific_question.py <question_id> | |
python tests/test_routing_integration.py | |
""" |