WeKnora/internal/infrastructure
wizardchen 74c845a1f4 fix(docparser): normalize PaddleOCR-VL HTML tables (#1725)
PaddleOCR-VL renders tables as HTML with per-cell text-align styles.
These waste tokens on layout markup and bypass the chunker's
table-protection logic (which only recognizes Markdown pipe tables),
causing large tables to be split mid-row.

Convert inline HTML <table> blocks to GFM Markdown tables when possible,
and strip presentational attributes (style/class/align/...) for tables
using rowspan/colspan that Markdown cannot express.

Refs: https://github.com/Tencent/WeKnora/issues/1725
2026-06-22 17:31:26 +08:00
..
chunker fix(chunker): carry deep sub-heading context into large-section chunks 2026-06-16 16:56:57 +08:00
docparser fix(docparser): normalize PaddleOCR-VL HTML tables (#1725) 2026-06-22 17:31:26 +08:00
web_fetch fix(web_fetch): use ValidateURLForSSRF instead of removed IsSSRFSafeURL 2026-03-31 22:26:16 +08:00
web_search feat(retriever): add OpenSearch driver skeleton + interface stubs (PR 2a of 3) 2026-05-26 20:54:58 +08:00