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

This commit is contained in:
Lin Manhui
2025-08-13 16:37:42 +08:00
committed by GitHub
parent 708a6ed0c0
commit 6b60c07c22
30 changed files with 657 additions and 174 deletions

View File

@@ -24,12 +24,12 @@ import (
"github.com/cloudwego/eino/schema"
)
type p struct {
parseFn
type Parser struct {
ParseFn
}
func (p p) Parse(ctx context.Context, reader io.Reader, opts ...parser.Option) ([]*schema.Document, error) {
return p.parseFn(ctx, reader, opts...)
func (p Parser) Parse(ctx context.Context, reader io.Reader, opts ...parser.Option) ([]*schema.Document, error) {
return p.ParseFn(ctx, reader, opts...)
}
type parseFn func(ctx context.Context, reader io.Reader, opts ...parser.Option) (docs []*schema.Document, err error)
type ParseFn func(ctx context.Context, reader io.Reader, opts ...parser.Option) (docs []*schema.Document, err error)