Update docs

Signed-off-by: Christoph Auer <[email protected]>

README.md

@@ -110,6 +110,8 @@ This can improve output quality if you find that multiple columns in extracted t
 
 
 ```python
+from docling.datamodel.pipeline_options import PipelineOptions
+
 pipeline_options = PipelineOptions(do_table_structure=True)
 pipeline_options.table_structure_options.do_cell_matching = False  # uses text cells predicted from table structure model
 
@@ -119,6 +121,20 @@ doc_converter = DocumentConverter(
 )
 ```
 
+Since docling 1.14.0: You can control which TableFormer mode you want to use. Choose between `TableFormerMode.FAST` (default) and `TableFormerMode.ACCURATE` (better, but slower) to receive better quality with difficult table structures.
+
+```python
+from docling.datamodel.pipeline_options import PipelineOptions, TableFormerMode
+
+pipeline_options = PipelineOptions(do_table_structure=True)
+pipeline_options.table_structure_options.mode = TableFormerMode.ACCURATE  # use more accurate TableFormer model
+
+doc_converter = DocumentConverter(
+    artifacts_path=artifacts_path,
+    pipeline_options=pipeline_options,
+)
+```
+
 ### Impose limits on the document size
 
 You can limit the file size and number of pages which should be allowed to process per document:

examples/custom_convert.py

@@ -83,9 +83,9 @@ def main():
     # PyPdfium with OCR
     # -----------------
     # pipeline_options = PipelineOptions()
-    # pipeline_options.do_ocr=False
+    # pipeline_options.do_ocr=True
     # pipeline_options.do_table_structure=True
-    # pipeline_options.table_structure_options.do_cell_matching = True
+    # pipeline_options.table_structure_options.do_cell_matching = False
 
     # doc_converter = DocumentConverter(
     #     pipeline_options=pipeline_options,