Context expansion is now automatic and structure-aware. For structured
documents, expands within the section containing the match. For sections
that exceed the budget or are too small, expands item-by-item outward
skipping noise labels. Unstructured documents use budget-based outward
expansion. Results sorted by relevance score.
- 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
