Fix click bug

README.md

@@ -43,7 +43,7 @@ As you can see, the use_llm mode offers higher accuracy than marker or gemini al
 
 I want marker to be as widely accessible as possible, while still funding my development/training costs.  Research and personal usage is always okay, but there are some restrictions on commercial usage.
 
-The weights for the models are licensed `cc-by-nc-sa-4.0`, but I will waive that for any organization under \$5M USD in gross revenue in the most recent 12-month period AND under $5M in lifetime VC/angel funding raised. You also must not be competitive with the [Datalab API](https://www.datalab.to/).  If you want to remove the GPL license requirements (dual-license) and/or use the weights commercially over the revenue limit, check out the options [here](https://www.datalab.to).
+The weights for the models are licensed `cc-by-nc-sa-4.0`, but I will waive that for any organization under \$2M USD in gross revenue in the most recent 12-month period AND under \$2M in lifetime VC/angel funding raised. You also must not be competitive with the [Datalab API](https://www.datalab.to/).  If you want to remove the GPL license requirements (dual-license) and/or use the weights commercially over the revenue limit, check out the options [here](https://www.datalab.to).
 
 # Hosted API
 

marker/config/parser.py

@@ -12,7 +12,6 @@ from marker.renderers.json import JSONRenderer
 from marker.renderers.markdown import MarkdownRenderer
 from marker.settings import settings
 from marker.util import classes_to_strings, parse_range_str, strings_to_classes
-from marker.schema import BlockTypes
 
 logger = get_logger()
 
@@ -71,11 +70,6 @@ class ConfigParser:
         )(fn)
 
         # we put common options here
-        fn = click.option(
-            "--use_llm",
-            default=False,
-            help="Enable higher quality processing with LLMs.",
-        )(fn)
         fn = click.option(
             "--converter_cls",
             type=str,
@@ -88,13 +82,6 @@ class ConfigParser:
             default=None,
             help="LLM service to use - should be full import path, like marker.services.gemini.GoogleGeminiService",
         )(fn)
-
-        # enum options
-        fn = click.option(
-            "--force_layout_block",
-            type=click.Choice(choices=[t.name for t in BlockTypes]),
-            default=None,
-        )(fn)
         return fn
 
     def generate_config_dict(self) -> Dict[str, any]:

marker/config/printer.py

@@ -7,11 +7,11 @@ from marker.config.crawler import crawler
 
 class CustomClickPrinter(click.Command):
     def parse_args(self, ctx, args):
-
-        display_help = 'config' in args and '--help' in args
+        display_help = "config" in args and "--help" in args
         if display_help:
             click.echo(
-                "Here is a list of all the Builders, Processors, Converters, Providers and Renderers in Marker along with their attributes:")
+                "Here is a list of all the Builders, Processors, Converters, Providers and Renderers in Marker along with their attributes:"
+            )
 
         # Keep track of shared attributes and their types
         shared_attrs = {}
@@ -19,30 +19,42 @@ class CustomClickPrinter(click.Command):
         # First pass: identify shared attributes and verify compatibility
         for base_type, base_type_dict in crawler.class_config_map.items():
             for class_name, class_map in base_type_dict.items():
-                for attr, (attr_type, formatted_type, default, metadata) in class_map['config'].items():
+                for attr, (attr_type, formatted_type, default, metadata) in class_map[
+                    "config"
+                ].items():
                     if attr not in shared_attrs:
                         shared_attrs[attr] = {
-                            'classes': [],
-                            'type': attr_type,
-                            'is_flag': attr_type in [bool, Optional[bool]] and not default,
-                            'metadata': metadata,
-                            'default': default
+                            "classes": [],
+                            "type": attr_type,
+                            "is_flag": attr_type in [bool, Optional[bool]]
+                            and not default,
+                            "metadata": metadata,
+                            "default": default,
                         }
-                    shared_attrs[attr]['classes'].append(class_name)
+                    shared_attrs[attr]["classes"].append(class_name)
 
         # These are the types of attrs that can be set from the command line
-        attr_types = [str, int, float, bool, Optional[int], Optional[float], Optional[str]]
+        attr_types = [
+            str,
+            int,
+            float,
+            bool,
+            Optional[int],
+            Optional[float],
+            Optional[str],
+        ]
 
         # Add shared attribute options first
         for attr, info in shared_attrs.items():
-            if info['type'] in attr_types:
+            if info["type"] in attr_types:
                 ctx.command.params.append(
                     click.Option(
                         ["--" + attr],
-                        type=info['type'],
-                        help=" ".join(info['metadata']) + f" (Applies to: {', '.join(info['classes'])})",
-                        default=None, # This is important, or it sets all the default keys again in config
-                        is_flag=info['is_flag'],
+                        type=info["type"],
+                        help=" ".join(info["metadata"])
+                        + f" (Applies to: {', '.join(info['classes'])})",
+                        default=None,  # This is important, or it sets all the default keys again in config
+                        is_flag=info["is_flag"],
                     )
                 )
 
@@ -51,15 +63,21 @@ class CustomClickPrinter(click.Command):
             if display_help:
                 click.echo(f"{base_type}s:")
             for class_name, class_map in base_type_dict.items():
-                if display_help and class_map['config']:
-                    click.echo(f"\n  {class_name}: {class_map['class_type'].__doc__ or ''}")
+                if display_help and class_map["config"]:
+                    click.echo(
+                        f"\n  {class_name}: {class_map['class_type'].__doc__ or ''}"
+                    )
                     click.echo(" " * 4 + "Attributes:")
-                for attr, (attr_type, formatted_type, default, metadata) in class_map['config'].items():
+                for attr, (attr_type, formatted_type, default, metadata) in class_map[
+                    "config"
+                ].items():
                     class_name_attr = class_name + "_" + attr
 
                     if display_help:
                         click.echo(" " * 8 + f"{attr} ({formatted_type}):")
-                        click.echo("\n".join([f'{" " * 12}' + desc for desc in metadata]))
+                        click.echo(
+                            "\n".join([f"{' ' * 12}" + desc for desc in metadata])
+                        )
 
                     if attr_type in attr_types:
                         is_flag = attr_type in [bool, Optional[bool]] and not default
@@ -71,7 +89,7 @@ class CustomClickPrinter(click.Command):
                                 type=attr_type,
                                 help=" ".join(metadata),
                                 is_flag=is_flag,
-                                default=None # This is important, or it sets all the default keys again in config
+                                default=None,  # This is important, or it sets all the default keys again in config
                             )
                         )
 

marker/logger.py

@@ -18,7 +18,6 @@ def configure_logging():
 
     # Ignore future warnings
     warnings.simplefilter(action="ignore", category=FutureWarning)
-    warnings.simplefilter(action="ignore", category=UserWarning)
 
     # Set component loglevels
     logging.getLogger("PIL").setLevel(logging.ERROR)

marker/output.py

@@ -62,7 +62,7 @@ def text_from_rendered(rendered: BaseModel):
     elif isinstance(rendered, OCRJSONOutput):
         return rendered.model_dump_json(exclude=["metadata"], indent=2), "json", {}
     elif isinstance(rendered, ExtractionOutput):
-        return rendered.json, "json", {}
+        return rendered.document_json, "json", {}
     else:
         raise ValueError("Invalid output type")
 

marker/renderers/extraction.py

@@ -42,7 +42,7 @@ def merge_keys(
 
 class ExtractionOutput(BaseModel):
     pages: Dict[int, ExtractionResult]
-    json: dict
+    document_json: dict
 
 
 class ExtractionRenderer(BaseRenderer):
@@ -61,4 +61,4 @@ class ExtractionRenderer(BaseRenderer):
             )
             merge_keys(merged_result, outputs[pnum].extracted_data, merge_data)
 
-        return ExtractionOutput(pages=outputs, json=merged_result)
+        return ExtractionOutput(pages=outputs, document_json=merged_result)

tests/converters/test_extraction_converter.py

@@ -62,5 +62,5 @@ def test_extraction_converter_multiple_pages(extraction_converter, temp_doc):
     result = extraction_converter(temp_doc.name)
 
     assert result is not None
-    assert result.json is not None
-    assert result.json == {"test_key": "test_value"}
+    assert result.document_json is not None
+    assert result.document_json == {"test_key": "test_value"}