haiku.rag/haiku_rag_slim/haiku/rag/store/models
Yiorgis Gozadinos afc5b02285
Update schema to store docling_document as compressed bytes
- Change DocumentRecord.docling_document_json (str) to docling_document (bytes)
- Use large_binary Arrow type (64-bit offsets) to avoid 2GB column limit
- Decompress in Document.get_docling_document() using gzip
- Update DocumentRepository field mappings
2026-01-10 15:17:27 +02:00
..
__init__.py Incorporate additional docling meta in search(), expand_context() and relevant qa/research agents 2025-12-08 15:54:56 +02:00
chunk.py Remove unused bounding box calculations 2025-12-08 15:56:21 +02:00
document.py Update schema to store docling_document as compressed bytes 2026-01-10 15:17:27 +02:00