fix: use new pdf_backend (#96)

* change default

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

* adopt new docling-parse

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

* fix and improve test

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

---------

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

Author: dolfim-ibm

docling_jobkit/convert/manager.py

@@ -13,8 +13,6 @@
 from pydantic import BaseModel, Field
 
 from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
-from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
-from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
 from docling.backend.pdf_backend import PdfDocumentBackend
 from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
 from docling.datamodel import vlm_model_specs
@@ -32,6 +30,7 @@
     TableStructureOptions,
     VlmConvertOptions,
     VlmPipelineOptions,
+    normalize_pdf_backend,
 )
 from docling.datamodel.pipeline_options_vlm_model import ApiVlmOptions, InlineVlmOptions
 from docling.datamodel.vlm_engine_options import (
@@ -1012,13 +1011,10 @@ def _parse_standard_pdf_opts(
     def _parse_backend(
         self, request: ConvertDocumentsOptions
     ) -> type[PdfDocumentBackend]:
-        if request.pdf_backend == PdfBackend.DLPARSE_V1:
+        pdf_backend = normalize_pdf_backend(request.pdf_backend)
+        if pdf_backend == PdfBackend.DOCLING_PARSE:
             backend: type[PdfDocumentBackend] = DoclingParseDocumentBackend
-        elif request.pdf_backend == PdfBackend.DLPARSE_V2:
-            backend = DoclingParseV2DocumentBackend
-        elif request.pdf_backend == PdfBackend.DLPARSE_V4:
-            backend = DoclingParseV4DocumentBackend
-        elif request.pdf_backend == PdfBackend.PYPDFIUM2:
+        elif pdf_backend == PdfBackend.PYPDFIUM2:
             backend = PyPdfiumDocumentBackend
         else:
             raise RuntimeError(f"Unexpected PDF backend type {request.pdf_backend}")

docling_jobkit/datamodel/convert.py

@@ -344,11 +344,11 @@ class ConvertDocumentsOptions(BaseModel):
             description=(
                 "The PDF backend to use. String. "
                 f"Allowed values: {', '.join([v.value for v in PdfBackend])}. "
-                f"Optional, defaults to {PdfBackend.DLPARSE_V4.value}."
+                f"Optional, defaults to {PdfBackend.DOCLING_PARSE.value}."
             ),
-            examples=[PdfBackend.DLPARSE_V4],
+            examples=[PdfBackend.DOCLING_PARSE],
         ),
-    ] = PdfBackend.DLPARSE_V4
+    ] = PdfBackend.DOCLING_PARSE
 
     table_mode: Annotated[
         TableFormerMode,

tests/test_options.py

@@ -3,8 +3,6 @@
 import pytest
 
 from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
-from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
-from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
 from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
 from docling.datamodel import vlm_model_specs
 from docling.datamodel.base_models import InputFormat
@@ -56,7 +54,7 @@ def test_options_validator():
     pipeline_opts = m.get_pdf_pipeline_opts(opts)
     assert pipeline_opts.pipeline_options is not None
     assert isinstance(pipeline_opts.pipeline_options, PdfPipelineOptions)
-    assert pipeline_opts.backend == DoclingParseV4DocumentBackend
+    assert pipeline_opts.backend == DoclingParseDocumentBackend
     assert pipeline_opts.pipeline_options.generate_page_images is True
 
     opts = ConvertDocumentsOptions(
@@ -70,15 +68,16 @@ def test_options_validator():
     assert pipeline_opts.pipeline_options.generate_page_images is True
     assert pipeline_opts.pipeline_options.generate_picture_images is True
 
-    opts = ConvertDocumentsOptions(pdf_backend=PdfBackend.DLPARSE_V2)
-    pipeline_opts = m.get_pdf_pipeline_opts(opts)
-    assert pipeline_opts.pipeline_options is not None
-    assert pipeline_opts.backend == DoclingParseV2DocumentBackend
-
-    opts = ConvertDocumentsOptions(pdf_backend=PdfBackend.DLPARSE_V1)
-    pipeline_opts = m.get_pdf_pipeline_opts(opts)
-    assert pipeline_opts.pipeline_options is not None
-    assert pipeline_opts.backend == DoclingParseDocumentBackend
+    for pdf_backend in (
+        PdfBackend.DLPARSE_V4,
+        PdfBackend.DLPARSE_V2,
+        PdfBackend.DLPARSE_V1,
+        PdfBackend.DOCLING_PARSE,
+    ):
+        opts = ConvertDocumentsOptions(pdf_backend=pdf_backend)
+        pipeline_opts = m.get_pdf_pipeline_opts(opts)
+        assert pipeline_opts.pipeline_options is not None
+        assert pipeline_opts.backend == DoclingParseDocumentBackend
 
     opts = ConvertDocumentsOptions(
         pipeline=ProcessingPipeline.VLM,