cybermaggedon 286f762369 The id field in pipeline Metadata was being overwritten at each processing (#686) ... The id field in pipeline Metadata was being overwritten at each processing stage (document → page → chunk), causing knowledge storage to create separate cores per chunk instead of grouping by document. Add a root field that: - Is set by librarian to the original document ID - Is copied unchanged through PDF decoder, chunkers, and extractors - Is used by knowledge storage for document_id grouping (with fallback to id) Changes: - Add root field to Metadata schema with empty string default - Set root=document.id in librarian when initiating document processing - Copy root through PDF decoder, recursive chunker, and all extractors - Update knowledge storage to use root (or id as fallback) for grouping - Add root handling to translators and gateway serialization - Update test mock Metadata class to include root parameter		2026-03-11 12:16:39 +00:00
..
__init__.py	Librarian (#304)	2025-02-11 16:01:03 +00:00
__main__.py	Librarian (#304)	2025-02-11 16:01:03 +00:00
blob_store.py	Document API updates (#660)	2026-03-05 15:20:45 +00:00
collection_manager.py	Fix collection existence test logic (#597)	2026-01-05 16:31:26 +00:00
librarian.py	Filter answers from document lists (#683)	2026-03-10 17:22:19 +00:00
service.py	The id field in pipeline Metadata was being overwritten at each processing (#686)	2026-03-11 12:16:39 +00:00