Commit graph

10 commits

Author SHA1 Message Date
kempersc
b30711fcfb update slots 2026-01-14 09:05:54 +01:00
kempersc
99430c2a70 add new entries and semantic routing 2025-12-17 10:11:56 +01:00
kempersc
e0dd847491 extend ontology 2025-12-16 20:27:39 +01:00
kempersc
cb56aa7e40 enrich all custodian timespan 2025-12-15 22:31:41 +01:00
kempersc
68c5aa2724 feat(api): Add heritage person classification and RAG retry logic
- Add GLAMORCUBESFIXPHDNT heritage type detection for person profiles
- Two-stage classification: blocklist non-heritage orgs, then match keywords
- Special handling for Digital (D) type: requires heritage org context
- Add career_history heritage_relevant and heritage_type fields
- Add exponential backoff retry for Anthropic API overload errors
- Fix DSPy 3.x async context with dspy.context() wrapper
2025-12-15 01:31:54 +01:00
kempersc
c50c35fd3a enrich person custodian 2025-12-14 17:09:55 +01:00
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a new script `test_pico_arabic_waqf.py` to test the GLM annotator's ability to extract person observations from Arabic historical documents.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
kempersc
1b1cfbfca0 enrich custodians 2025-12-11 22:32:09 +01:00
kempersc
d4906abae4 update postgis data 2025-12-10 23:51:51 +01:00
kempersc
41959f0766 correct HCID! 2025-12-10 13:01:13 +01:00