fix: make enum serializable with human-readable value (#555)

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

docling/cli/main.py

@@ -27,8 +27,10 @@ from docling.datamodel.base_models import (
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
+    OcrEngine,
     OcrMacOptions,
     OcrOptions,
+    PdfBackend,
     PdfPipelineOptions,
     RapidOcrOptions,
     TableFormerMode,
@@ -68,22 +70,6 @@ def version_callback(value: bool):
         raise typer.Exit()
 
 
-# Define an enum for the backend options
-class PdfBackend(str, Enum):
-    PYPDFIUM2 = "pypdfium2"
-    DLPARSE_V1 = "dlparse_v1"
-    DLPARSE_V2 = "dlparse_v2"
-
-
-# Define an enum for the ocr engines
-class OcrEngine(str, Enum):
-    EASYOCR = "easyocr"
-    TESSERACT_CLI = "tesseract_cli"
-    TESSERACT = "tesseract"
-    OCRMAC = "ocrmac"
-    RAPIDOCR = "rapidocr"
-
-
 def export_documents(
     conv_results: Iterable[ConversionResult],
     output_dir: Path,

docling/datamodel/base_models.py

@@ -19,12 +19,12 @@ if TYPE_CHECKING:
 
 
 class ConversionStatus(str, Enum):
-    PENDING = auto()
-    STARTED = auto()
-    FAILURE = auto()
-    SUCCESS = auto()
-    PARTIAL_SUCCESS = auto()
-    SKIPPED = auto()
+    PENDING = "pending"
+    STARTED = "started"
+    FAILURE = "failure"
+    SUCCESS = "success"
+    PARTIAL_SUCCESS = "partial_success"
+    SKIPPED = "skipped"
 
 
 class InputFormat(str, Enum):
@@ -89,15 +89,15 @@ MimeTypeToFormat = {
 
 
 class DocInputType(str, Enum):
-    PATH = auto()
-    STREAM = auto()
+    PATH = "path"
+    STREAM = "stream"
 
 
 class DoclingComponentType(str, Enum):
-    DOCUMENT_BACKEND = auto()
-    MODEL = auto()
-    DOC_ASSEMBLER = auto()
-    USER_INPUT = auto()
+    DOCUMENT_BACKEND = "document_backend"
+    MODEL = "model"
+    DOC_ASSEMBLER = "doc_assembler"
+    USER_INPUT = "user_input"
 
 
 class ErrorItem(BaseModel):

docling/datamodel/pipeline_options.py

@@ -126,6 +126,26 @@ class OcrMacOptions(OcrOptions):
     )
 
 
+# Define an enum for the backend options
+class PdfBackend(str, Enum):
+    """Enum of valid PDF backends."""
+
+    PYPDFIUM2 = "pypdfium2"
+    DLPARSE_V1 = "dlparse_v1"
+    DLPARSE_V2 = "dlparse_v2"
+
+
+# Define an enum for the ocr engines
+class OcrEngine(str, Enum):
+    """Enum of valid OCR engines."""
+
+    EASYOCR = "easyocr"
+    TESSERACT_CLI = "tesseract_cli"
+    TESSERACT = "tesseract"
+    OCRMAC = "ocrmac"
+    RAPIDOCR = "rapidocr"
+
+
 class PipelineOptions(BaseModel):
     """Base pipeline options."""