Avoid duplicate use llm flag

.github/workflows/scripts.yml

@@ -24,4 +24,8 @@ jobs:
       - name: Test convert script
         run: poetry run marker benchmark_data/pdfs --max_files 1 --workers 1 --page_range 0
       - name: Text convert script multiple workers
-        run: poetry run marker benchmark_data/pdfs --max_files 2 --workers 2 --page_range 0-5
+        run: poetry run marker benchmark_data/pdfs --max_files 2 --workers 2 --page_range 0-5
+      - name: Test llm option
+        run: |
+          poetry run marker_single benchmark_data/pdfs/switch_trans.pdf --page_range 0 --use_llm > output.txt || true
+          grep -qv "UserWarning" output.txt

marker/config/parser.py

@@ -70,6 +70,12 @@ class ConfigParser:
         )(fn)
 
         # we put common options here
+        fn = click.option(
+            "--use_llm",
+            is_flag=True,
+            default=False,
+            help="Use LLM for higher accuracy.",
+        )(fn)
         fn = click.option(
             "--converter_cls",
             type=str,

marker/config/printer.py

@@ -6,6 +6,8 @@ from marker.config.crawler import crawler
 
 
 class CustomClickPrinter(click.Command):
+    force_flags = ["use_llm"]
+
     def parse_args(self, ctx, args):
         display_help = "config" in args and "--help" in args
         if display_help:
@@ -47,6 +49,9 @@ class CustomClickPrinter(click.Command):
         # Add shared attribute options first
         for attr, info in shared_attrs.items():
             if info["type"] in attr_types:
+                if attr in self.force_flags:
+                    continue
+
                 ctx.command.params.append(
                     click.Option(
                         ["--" + attr],

poetry.lock

@@ -850,14 +850,14 @@ files = [
 
 [[package]]
 name = "click"
-version = "8.1.8"
+version = "8.2.0"
 description = "Composable command line interface toolkit"
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.10"
 groups = ["main", "dev"]
 files = [
-    {file = "click-8.1.8-py3-none-any.whl", hash = "sha256:63c132bbbed01578a06712a2d1f497bb62d9c1c0d329b7903a866228027263b2"},
-    {file = "click-8.1.8.tar.gz", hash = "sha256:ed53c9d8990d83c2a27deae68e4ee337473f6330c040a31d4225c9574d16096a"},
+    {file = "click-8.2.0-py3-none-any.whl", hash = "sha256:6b303f0b2aa85f1cb4e5303078fadcbcd4e476f114fab9b5007005711839325c"},
+    {file = "click-8.2.0.tar.gz", hash = "sha256:f5452aeddd9988eefa20f90f05ab66f17fce1ee2a36907fd30b05bbb5953814d"},
 ]
 
 [package.dependencies]
@@ -6467,4 +6467,4 @@ full = ["ebooklib", "mammoth", "openpyxl", "python-pptx", "weasyprint"]
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.10"
-content-hash = "9ad983393fbfbb4ade6ce2e8a1ec239afde9e648ce56d7d34dd21eb50cd5d0ca"
+content-hash = "1f5c00e7588f89650cbe93b1ae34fa7b265d472b0b954e4a81a7b4912c2f3c01"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "marker-pdf"
-version = "1.7.0"
+version = "1.7.1"
 description = "Convert documents to markdown with high speed and accuracy."
 authors = ["Vik Paruchuri <github@vikas.sh>"]
 readme = "README.md"
@@ -30,7 +30,7 @@ surya-ocr = "^0.14.1"
 regex = "^2024.4.28"
 pdftext = "~0.6.2"
 markdownify = "^0.13.1"
-click = "^8.1.7"
+click = "^8.2.0"
 markdown2 = "^2.5.2"
 filetype = "^1.2.0"
 scikit-learn = "^1.6.1"