glam/backend/rag
kempersc 505c12601a Add test script for PiCo extraction from Arabic waqf documents
- Implemented a new script `test_pico_arabic_waqf.py` to test the GLM annotator's ability to extract person observations from Arabic historical documents.
- The script includes environment variable handling for API token, structured prompts for the GLM API, and validation of extraction results.
- Added comprehensive logging for API responses, extraction results, and validation errors.
- Included a sample Arabic waqf text for testing purposes, following the PiCo ontology pattern.
2025-12-12 17:50:17 +01:00
..
optimized_models enrich custodians 2025-12-11 22:32:09 +01:00
__init__.py enrich custodians 2025-12-11 22:32:09 +01:00
atomic_decomposer.py enrich custodians 2025-12-11 22:32:09 +01:00
cache_config.py enrich custodians 2025-12-11 22:32:09 +01:00
dspy_heritage_rag.py enrich person profiles 2025-12-12 12:51:10 +01:00
gepa_training_extended.py enrich custodians 2025-12-11 22:32:09 +01:00
main.py Add test script for PiCo extraction from Arabic waqf documents 2025-12-12 17:50:17 +01:00
optimization_log.txt enrich custodians 2025-12-11 22:32:09 +01:00
requirements.txt enrich custodians 2025-12-11 22:32:09 +01:00
run_bootstrap_optimization.py enrich custodians 2025-12-11 22:32:09 +01:00
run_gepa_optimization.py enrich custodians 2025-12-11 22:32:09 +01:00
schema_loader.py enrich person profiles 2025-12-12 12:51:10 +01:00
semantic_cache.py enrich person profiles 2025-12-12 12:51:10 +01:00
test_dspy_rag.py enrich custodians 2025-12-11 22:32:09 +01:00
test_live_rag.py enrich person profiles 2025-12-12 12:51:10 +01:00