Major architectural changes based on Formica et al. (2023) research:
- Add TemplateClassifier for deterministic SPARQL template matching
- Add SlotExtractor with synonym resolution for slot values
- Add TemplateInstantiator using Jinja2 for query rendering
- Refactor dspy_heritage_rag.py to use template system
- Update main.py with streamlined pipeline
- Fix semantic_router.py ordering issues
- Add comprehensive metrics tracking
Template-based approach achieves 65% precision vs 10% LLM-only
per Formica et al. research on SPARQL generation.
Clean up old generated RDF/OWL files that have been superseded by
the clean schema deployed to Oxigraph (commit f8421a2903).
Only the current deployed schema should be regenerated as needed.
- Remove deprecated CustodianTypeCodeEnum from class_metadata_slots.yaml
- Update custodian_types slot to use uriorcurie range (references CustodianType subclasses)
- Update custodian_types_primary slot similarly
- Add migration note for legacy string format ['A'] vs new URI format
Per Rule 9: Enum-to-Class Promotion - Single Source of Truth
- Updated documentation to clarify integration points with existing components in the RAG pipeline and DSPy framework.
- Added detailed mapping of SPARQL templates to context templates for improved specificity filtering.
- Implemented wrapper patterns around existing classifiers to extend functionality without duplication.
- Introduced new tests for the SpecificityAwareClassifier and SPARQLToContextMapper to ensure proper integration and functionality.
- Enhanced the CustodianRDFConverter to include ISO country and subregion codes from GHCID for better geospatial data handling.
- Fixed bug where closing triple-quotes (""") would incorrectly re-trigger
multi-line string detection, causing subsequent class definitions to be skipped
- Added lineToProcess variable to track which portion of line to process after
closing a multi-line string, preventing re-detection of opening quotes
- Moved UML large diagram confirmation logic from OntologyViewerPage to
UMLVisualization component for better encapsulation
- PiCo ontology now correctly shows all 8 classes instead of 2
Deployed and verified on https://bronhouder.nl/ontology?ontology=PiCo
- Created deliverables_slot for expected or achieved deliverable outputs.
- Introduced event_id_slot for persistent unique event identifiers.
- Added follow_up_date_slot for scheduled follow-up action dates.
- Implemented object_ref_slot for references to heritage objects.
- Established price_slot for price information across entities.
- Added price_currency_slot for currency codes in price information.
- Created protocol_slot for API protocol specifications.
- Introduced provenance_text_slot for full provenance entry text.
- Added record_type_slot for classification of record types.
- Implemented response_formats_slot for supported API response formats.
- Established status_slot for current status of entities or activities.
- Added FactualCountDisplay component for displaying count query results.
- Introduced ReplyTypeIndicator component for visualizing reply types.
- Created approval_date_slot for formal approval dates.
- Added authentication_required_slot for API authentication status.
- Implemented capacity_items_slot for maximum storage capacity.
- Established conservation_lab_slot for conservation laboratory information.
- Added cost_usd_slot for API operation costs in USD.
Implements a state machine to filter streaming tokens:
- Only stream tokens from the 'answer' field to the frontend
- Skip tokens from 'reasoning', 'citations', 'confidence', 'follow_up' fields
- Remove DSPy field markers like '[[ ## answer ## ]]' from streamed content
This fixes the issue where raw DSPy signature field markers were being
displayed in the chat interface instead of clean answer text.
