ben/coze-studio
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

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

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files

4
backend/infra/impl/document/parser/builtin/parse_json.go
View File

@@ -28,7 +28,7 @@ import (
contract "github.com/coze-dev/coze-studio/backend/infra/contract/document/parser"
)
func parseJSON(config *contract.Config) parseFn {
func ParseJSON(config *contract.Config) ParseFn {
return func(ctx context.Context, reader io.Reader, opts ...parser.Option) (docs []*schema.Document, err error) {
b, err := io.ReadAll(reader)
if err != nil {
@@ -41,7 +41,7 @@ func parseJSON(config *contract.Config) parseFn {
}
if len(rawSlices) == 0 {
return nil, fmt.Errorf("[parseJSON] json data is empty")
return nil, fmt.Errorf("[ParseJSON] json data is empty")
}
var header []string