feat(parser): add OpenDataLoader, PaddleOCR-VL engines, and parser improvements
Introduce opendataloader and PaddleOCR-VL parser engines with tenant-level settings UI, replace liteparse, and harden Excel/PPT/Markdown parsing. Optional odl-hybrid sidecar stays local-build only and is excluded from default dev-start and full profiles.
This commit is contained in:
@@ -3256,6 +3256,10 @@ func (s *knowledgeService) resolveDocReader(ctx context.Context, engine, fileTyp
|
||||
return docparser.NewMinerUReader(overrides)
|
||||
case "mineru_cloud":
|
||||
return docparser.NewMinerUCloudReader(overrides)
|
||||
case "paddleocr_vl":
|
||||
return docparser.NewPaddleOCRVLReader(overrides)
|
||||
case "paddleocr_vl_cloud":
|
||||
return docparser.NewPaddleOCRVLCloudReader(overrides)
|
||||
case "builtin":
|
||||
// 明确指定使用 builtin 引擎(docreader),不使用 simple format 兜底
|
||||
return s.documentReader
|
||||
|
||||
Reference in New Issue
Block a user