feat(infra): integrate PaddleOCR's PP-StructureV3 as a document parser backend (#714)

2025-08-13 16:37:42 +08:00
parent 708a6ed0c0
commit 6b60c07c22
30 changed files with 657 additions and 174 deletions
--- a/backend/infra/impl/document/parser/builtin/parse_xlsx.go
+++ b/backend/infra/impl/document/parser/builtin/parse_xlsx.go
@@ -27,7 +27,7 @@ import (
 	contract "github.com/coze-dev/coze-studio/backend/infra/contract/document/parser"
 )

-func parseXLSX(config *contract.Config) parseFn {
+func ParseXLSX(config *contract.Config) ParseFn {
 	return func(ctx context.Context, reader io.Reader, opts ...parser.Option) (docs []*schema.Document, err error) {
 		f, err := excelize.OpenReader(reader)
 		if err != nil {