recon/scripts
Matt 6be1e4cfa6 feat(wiki-index): add wave 2 pipeline for wikidata-only places
Processes places with wikidata but no wikipedia tag:
- Batch resolve Q-IDs via Wikidata API (50/request)
- Validate resolved titles against local ZIM
- Generate summaries with Gemini API (3-4 sentences)
- Circuit breaker: 50 consecutive 429s triggers 5min pause
- Revalidate any remaining unvalidated entries

Filters for US+CA places, skips existing wave 1 entries.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-04-29 19:50:43 +00:00
..
__init__.py Initial commit: RECON codebase baseline 2026-04-14 14:57:23 +00:00
aa_download.py Initial commit: RECON codebase baseline 2026-04-14 14:57:23 +00:00
aa_download_pass2.py Initial commit: RECON codebase baseline 2026-04-14 14:57:23 +00:00
backup.sh Initial commit: RECON codebase baseline 2026-04-14 14:57:23 +00:00
cleanup_outliers.py Initial commit: RECON codebase baseline 2026-04-14 14:57:23 +00:00
domain_reenrich.py Initial commit: RECON codebase baseline 2026-04-14 14:57:23 +00:00
domain_remap.py Initial commit: RECON codebase baseline 2026-04-14 14:57:23 +00:00
migrate_domains.py Initial commit: RECON codebase baseline 2026-04-14 14:57:23 +00:00
migrate_skill_level.py Initial commit: RECON codebase baseline 2026-04-14 14:57:23 +00:00
rebuild_qdrant.py Initial commit: RECON codebase baseline 2026-04-14 14:57:23 +00:00
reenrich_reference.py Initial commit: RECON codebase baseline 2026-04-14 14:57:23 +00:00
repair_corrupted.py Initial commit: RECON codebase baseline 2026-04-14 14:57:23 +00:00
validate.py Initial commit: RECON codebase baseline 2026-04-14 14:57:23 +00:00
wiki_index_wave2.py feat(wiki-index): add wave 2 pipeline for wikidata-only places 2026-04-29 19:50:43 +00:00