Commit graph

8 commits

Author SHA1 Message Date
kempersc
ad74d8379e feat(scripts): improve types-vocab extraction to derive all vocabulary from schema
- Remove hardcoded type mappings, derive dynamically from LinkML
- Extract keywords from annotations, structured_aliases, and comments
- Add rename_plural_slot.py utility for schema slot renaming
2026-01-10 15:37:52 +01:00
kempersc
13938c92ca chore(schemas): sync LinkML schemas to frontend apps
Copies authoritative schemas from schemas/20251121/ to:
- frontend/public/schemas/20251121/
- apps/archief-assistent/public/schemas/20251121/

This ensures slot definitions with corrected ontology property
references (commit 2808dad6cd) are available to frontend apps.
2026-01-10 15:02:25 +01:00
kempersc
e5a08a353d enrich person profiles 2026-01-10 14:14:04 +01:00
kempersc
f2bc2d54cb feat(archief-assistent): integrate ontology-driven vocabulary into semantic cache
Implements Rule 46: Ontology-Driven Cache Segmentation

Semantic Cache Enhancements:
- Add institutionSubtype, recordSetType, wikidataEntity to ExtractedEntities
- Add extractionMethod field to track vocabulary vs regex extraction
- Implement async extractEntitiesWithVocabulary() using term log
- Maintain sync regex fallback for cache key generation (<5ms)

Build Pipeline:
- Add prebuild hook to regenerate types-vocab.json from LinkML schemas
- Extract vocabulary from *Type.yaml and *Types.yaml schema files
- Generate GLAMORCUBESFIXPHDNT code mappings automatically

New Script:
- scripts/extract-types-vocab.ts - Extracts vocabulary from LinkML schemas
- Supports --skip-embeddings flag for faster builds
- Outputs to apps/archief-assistent/public/types-vocab.json

This enables richer cache segmentation using ontology-derived subtypes
(e.g., 'MUNICIPAL_ARCHIVE', 'ART_MUSEUM') instead of just top-level
GLAMORCUBESFIXPHDNT codes.
2026-01-10 13:30:30 +01:00
kempersc
01b9d77566 feat(archief-assistent): add ontology-driven types vocabulary for cache segmentation
Add LinkML-derived vocabulary for semantic cache entity extraction (Rule 46):

- types-vocab.json: 10,142 lines of institution type vocabulary from LinkML
  - 19 GLAMORCUBESFIXPHDNT type codes with Dutch/English/German/French labels
  - Includes subtypes (kunstmuseum, rijksmuseum, streekarchief, etc.)
  - Extracted from CustodianType.yaml and CustodianTypes.yaml

- types-vocabulary.ts: TypeScript module for entity extraction
  - Exports INSTITUTION_TYPES with regex patterns per type code
  - Replaces hardcoded patterns with schema-derived vocabulary
  - Supports multilingual matching

- Rule 46 documentation (.opencode/rules/)
  - Specifies vocabulary extraction workflow
  - Defines cache key generation algorithm
  - Migration path from hardcoded patterns
2026-01-10 12:57:03 +01:00
kempersc
4f0cafe98a enrich HC profiles 2026-01-02 02:11:04 +01:00
kempersc
d64f857aa9 add sparql validator and RAG injector 2025-12-30 03:43:31 +01:00
kempersc
aca68ea47f remove a,bihguous web-claims 2025-12-21 00:01:54 +01:00