fix: updated the render_as_doctags with the new arguments from doclin…

…g-core (#93) * updated the render_as_doctags with the new arguments from docling-core Signed-off-by: Peter Staar <taa@zurich.ibm.com> * ensuring that docling-core is >1.5.0 to accomodate with the latest export-to-doctags parameters Signed-off-by: Peter Staar <taa@zurich.ibm.com> * added the doctags tests Signed-off-by: Peter Staar <taa@zurich.ibm.com> * updated the README Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fix poetry lock Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * Fix formatting problems Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * fixed the doctag export in docling/utils/export.py Signed-off-by: Peter Staar <taa@zurich.ibm.com> * propagate xsize and ysize Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
DS4SD · Sep 23, 2024 · 4794ce4 · 4794ce4
1 parent dce9934
commit 4794ce4
Show file tree

Hide file tree

Showing 18 changed files with 3,091 additions and 20 deletions.
diff --git a/README.md b/README.md
@@ -70,7 +70,9 @@ from docling.document_converter import DocumentConverter
 source = "https://arxiv.org/pdf/2408.09869"  # PDF path or URL
 converter = DocumentConverter()
 result = converter.convert_single(source)
+
 print(result.render_as_markdown())  # output: "## Docling Technical Report[...]"
+print(result.render_as_doctags())  # output: "<document><title><page_1><loc_20>..."
 ```
 
 ### Convert a batch of documents

diff --git a/docling/datamodel/document.py b/docling/datamodel/document.py
@@ -368,20 +368,30 @@ def render_as_doctags(
             "table",
             "figure",
         ],
-        page_tagging: bool = True,
-        location_tagging: bool = True,
-        location_dimensions: Tuple[int, int] = (100, 100),
-        add_new_line: bool = True,
+        xsize: int = 100,
+        ysize: int = 100,
+        add_location: bool = True,
+        add_content: bool = True,
+        add_page_index: bool = True,
+        # table specific flags
+        add_table_cell_location: bool = False,
+        add_table_cell_label: bool = True,
+        add_table_cell_text: bool = True,
     ) -> str:
         return self.output.export_to_document_tokens(
             delim=delim,
             main_text_start=main_text_start,
             main_text_stop=main_text_stop,
             main_text_labels=main_text_labels,
-            page_tagging=page_tagging,
-            location_tagging=location_tagging,
-            location_dimensions=location_dimensions,
-            add_new_line=add_new_line,
+            xsize=xsize,
+            ysize=ysize,
+            add_location=add_location,
+            add_content=add_content,
+            add_page_index=add_page_index,
+            # table specific flags
+            add_table_cell_location=add_table_cell_location,
+            add_table_cell_label=add_table_cell_label,
+            add_table_cell_text=add_table_cell_text,
         )
 
     def render_element_images(

diff --git a/docling/utils/export.py b/docling/utils/export.py
@@ -111,7 +111,7 @@ def _process_page():
         )
         # No page-tagging since we only do 1 page at the time
         content_dt = doc.export_to_document_tokens(
-            main_text_start=start_ix, main_text_stop=end_ix, page_tagging=False
+            main_text_start=start_ix, main_text_stop=end_ix, add_page_index=False
         )
 
         return content_text, content_md, content_dt, page_cells, page_segments, page

diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -23,7 +23,7 @@ packages = [{include = "docling"}]
 [tool.poetry.dependencies]
 python = "^3.10"
 pydantic = "^2.0.0"
-docling-core = "^1.4.0"
+docling-core = "^1.5.0"
 docling-ibm-models = "^1.2.0"
 deepsearch-glm = "^0.21.1"
 filetype = "^1.2.0"

diff --git a/tests/data/2203.01017v2.doctags.txt b/tests/data/2203.01017v2.doctags.txt
diff --git a/tests/data/2203.01017v2.json b/tests/data/2203.01017v2.json
diff --git a/tests/data/2206.01062.doctags.txt b/tests/data/2206.01062.doctags.txt
diff --git a/tests/data/2206.01062.json b/tests/data/2206.01062.json
diff --git a/tests/data/2305.03393v1-pg9.doctags.txt b/tests/data/2305.03393v1-pg9.doctags.txt
@@ -0,0 +1,20 @@
+<document>
+<paragraph><location><page_1><loc_22><loc_81><loc_79><loc_85></location>order to compute the TED score. Inference timing results for all experiments were obtained from the same machine on a single core with AMD EPYC 7763 CPU @2.45 GHz.</paragraph>
+<subtitle-level-1><location><page_1><loc_22><loc_77><loc_52><loc_79></location>5.1 Hyper Parameter Optimization</subtitle-level-1>
+<paragraph><location><page_1><loc_22><loc_68><loc_79><loc_77></location>We have chosen the PubTabNet data set to perform HPO, since it includes a highly diverse set of tables. Also we report TED scores separately for simple and complex tables (tables with cell spans). Results are presented in Table. 1. It is evident that with OTSL, our model achieves the same TED score and slightly better mAP scores in comparison to HTML. However OTSL yields a 2x speed up in the inference runtime over HTML.</paragraph>
+<caption><location><page_1><loc_22><loc_59><loc_79><loc_66></location>Table 1. HPO performed in OTSL and HTML representation on the same transformer-based TableFormer [9] architecture, trained only on PubTabNet [22]. Effects of reducing the # of layers in encoder and decoder stages of the model show that smaller models trained on OTSL perform better, especially in recognizing complex table structures, and maintain a much higher mAP score than the HTML counterpart.</caption>
+<table>
+<location><page_1><loc_23><loc_41><loc_78><loc_57></location>
+<caption>Table 1. HPO performed in OTSL and HTML representation on the same transformer-based TableFormer [9] architecture, trained only on PubTabNet [22]. Effects of reducing the # of layers in encoder and decoder stages of the model show that smaller models trained on OTSL perform better, especially in recognizing complex table structures, and maintain a much higher mAP score than the HTML counterpart.</caption>
+<row_0><col_0><col_header>#</col_0><col_1><col_header>#</col_1><col_2><col_header>Language</col_2><col_3><col_header>TEDs</col_3><col_4><col_header>TEDs</col_4><col_5><col_header>TEDs</col_5><col_6><col_header>mAP</col_6><col_7><col_header>Inference</col_7></row_0>
+<row_1><col_0><col_header>enc-layers</col_0><col_1><col_header>dec-layers</col_1><col_2><col_header>Language</col_2><col_3><col_header>simple</col_3><col_4><col_header>complex</col_4><col_5><col_header>all</col_5><col_6><col_header>(0.75)</col_6><col_7><col_header>time (secs)</col_7></row_1>
+<row_2><col_0><body>6</col_0><col_1><body>6</col_1><col_2><body>OTSL HTML</col_2><col_3><body>0.965 0.969</col_3><col_4><body>0.934 0.927</col_4><col_5><body>0.955 0.955</col_5><col_6><body>0.88 0.857</col_6><col_7><body>2.73 5.39</col_7></row_2>
+<row_3><col_0><body>4</col_0><col_1><body>4</col_1><col_2><body>OTSL HTML</col_2><col_3><body>0.938 0.952</col_3><col_4><body>0.904</col_4><col_5><body>0.927</col_5><col_6><body>0.853</col_6><col_7><body>1.97</col_7></row_3>
+<row_4><col_0><body></col_0><col_1><body></col_1><col_2><body>OTSL HTML</col_2><col_3><body>0.923</col_3><col_4><body>0.909 0.897 0.901</col_4><col_5><body>0.938 0.915</col_5><col_6><body>0.843</col_6><col_7><body>3.77</col_7></row_4>
+<row_5><col_0><body>2</col_0><col_1><body>4</col_1><col_2><body></col_2><col_3><body>0.945</col_3><col_4><body></col_4><col_5><body>0.931</col_5><col_6><body>0.859 0.834</col_6><col_7><body>1.91 3.81</col_7></row_5>
+<row_6><col_0><body>4</col_0><col_1><body>2</col_1><col_2><body>OTSL HTML</col_2><col_3><body>0.952 0.944</col_3><col_4><body>0.92 0.903</col_4><col_5><body>0.942 0.931</col_5><col_6><body>0.857 0.824</col_6><col_7><body>1.22 2</col_7></row_6>
+</table>
+<subtitle-level-1><location><page_1><loc_22><loc_35><loc_43><loc_36></location>5.2 Quantitative Results</subtitle-level-1>
+<paragraph><location><page_1><loc_22><loc_22><loc_79><loc_34></location>We picked the model parameter configuration that produced the best prediction quality (enc=6, dec=6, heads=8) with PubTabNet alone, then independently trained and evaluated it on three publicly available data sets: PubTabNet (395k samples), FinTabNet (113k samples) and PubTables-1M (about 1M samples). Performance results are presented in Table. 2. It is clearly evident that the model trained on OTSL outperforms HTML across the board, keeping high TEDs and mAP scores even on difficult financial tables (FinTabNet) that contain sparse and large tables.</paragraph>
+<paragraph><location><page_1><loc_22><loc_16><loc_79><loc_22></location>Additionally, the results show that OTSL has an advantage over HTML when applied on a bigger data set like PubTables-1M and achieves significantly improved scores. Finally, OTSL achieves faster inference due to fewer decoding steps which is a result of the reduced sequence representation.</paragraph>
+</document>
diff --git a/tests/data/2305.03393v1-pg9.json b/tests/data/2305.03393v1-pg9.json