fix param

app.py

@@ -157,14 +157,15 @@ def _file_to_b64_image_only(path_or_url: str) -> Tuple[str, int]:
     return base64.b64encode(content).decode("utf-8"), 1  # 1 = image 类型
 
 def _call_api(api_url: str, path_or_url: str, use_layout_detection: bool,
-              prompt_label: Optional[str], use_chart_recognition: bool = False) -> Dict[str, Any]:
+              prompt_label: Optional[str], use_chart_recognition: bool = False,
+              use_doc_unwarping: bool = True, use_doc_orientation_classify: bool = True) -> Dict[str, Any]:
     b64, file_type = _file_to_b64_image_only(path_or_url)
     payload = {
         "file": b64,
         "useLayoutDetection": bool(use_layout_detection),
         "fileType": file_type,
-        "useDocUnwarping":False,
-        "useDocOrientationClassify":False
+        "useDocUnwarping": use_doc_unwarping,
+        "useDocOrientationClassify": use_doc_orientation_classify
     }
     if not use_layout_detection:
         if not prompt_label:
@@ -227,11 +228,12 @@ def _process_api_response_page(result: Dict[str, Any]) -> Tuple[str, str, str]:
     md_text = _escape_inequalities_in_math(md_text)
     return md_text or "(Empty result)", output_html, md_text
 
-def handle_complex_doc(path_or_url: str, use_chart_recognition: bool) -> Tuple[str, str, str]:
+def handle_complex_doc(path_or_url: str, use_chart_recognition: bool, use_doc_unwarping: bool, use_doc_orientation_classify: bool) -> Tuple[str, str, str]:
     if not path_or_url:
         raise gr.Error("Please upload an image first.")
     data = _call_api(DEFAULT_API_URL, path_or_url, use_layout_detection=True,
-                     prompt_label=None, use_chart_recognition=use_chart_recognition)
+                     prompt_label=None, use_chart_recognition=use_chart_recognition,
+                     use_doc_unwarping=use_doc_unwarping, use_doc_orientation_classify=use_doc_orientation_classify)
     result = data.get("result", {})
     return _process_api_response_page(result)
 
@@ -245,7 +247,7 @@ def handle_targeted_recognition(path_or_url: str, prompt_choice: str) -> Tuple[s
         "Chart Recognition": "chart",
     }
     label = mapping.get(prompt_choice, "ocr")
-    data = _call_api(DEFAULT_API_URL, path_or_url, use_layout_detection=False, prompt_label=label)
+    data = _call_api(DEFAULT_API_URL, path_or_url, use_layout_detection=False, prompt_label=label, use_doc_unwarping=False, use_doc_orientation_classify=False)
     result = data.get("result", {})
     md_preview, _, md_raw = _process_api_response_page(result)
     return md_preview, md_raw
@@ -273,6 +275,7 @@ body, .gradio-container { font-family: "Noto Sans SC", "Microsoft YaHei", "PingF
 .notice strong { font-weight: 700; }
 .notice a { color: #3b82f6; text-decoration: none; }
 .notice a:hover { text-decoration: underline; }
+.checkbox-row .gradio-checkbox { flex-grow: 1; text-align: center; }
 """
 
 with gr.Blocks(head=GOOGLE_FONTS_URL, css=custom_css, theme=gr.themes.Soft()) as demo:
@@ -280,7 +283,7 @@ with gr.Blocks(head=GOOGLE_FONTS_URL, css=custom_css, theme=gr.themes.Soft()) as
     gr.HTML(f"""<div class="app-header"><img src="{logo_data_url}" alt="App Logo" style="max-height:10%; width: auto; margin: 10px auto; display: block;"></div>""")
     gr.HTML("""<div class="notice"><strong>Heads up:</strong> The Hugging Face demo can be slow at times. For a faster experience, please try <a href="https://aistudio.baidu.com/application/detail/98365" target="_blank" rel="noopener noreferrer">Baidu AI Studio</a> or <a href="https://modelscope.cn/studios/PaddlePaddle/PaddleOCR-VL_Online_Demo/summary" target="_blank" rel="noopener noreferrer">ModelScope</a>.</div>""")
     gr.HTML("""<div class="quick-links"><a href="https://github.com/PaddlePaddle/PaddleOCR" target="_blank">GitHub</a> | <a href="https://ernie.baidu.com/blog/publication/PaddleOCR-VL_Technical_Report.pdf" target="_blank">Technical Report</a> | <a href="https://huggingface.co/PaddlePaddle/PaddleOCR-VL" target="_blank">Model</a></div>""")
-    
+
     with gr.Tabs():
         # ===================== Document Parsing =====================
         with gr.Tab("Document Parsing"):
@@ -294,8 +297,13 @@ with gr.Blocks(head=GOOGLE_FONTS_URL, css=custom_css, theme=gr.themes.Soft()) as
                     example_url_doc = gr.State(value=None)
 
                     with gr.Row(variant="panel"):
-                        chart_parsing_switch = gr.Checkbox(label="Enable chart parsing", value=False, scale=1)
-                        btn_parse = gr.Button("Parse Document", variant="primary", scale=2)
+                        with gr.Column(scale=2):
+                            btn_parse = gr.Button("Parse Document", variant="primary")
+                        with gr.Column(scale=3):
+                            with gr.Row(elem_classes=["checkbox-row"]):
+                                chart_parsing_switch = gr.Checkbox(label="Enable chart parsing", value=False, min_width=10)
+                                doc_unwarping_switch = gr.Checkbox(label="Enable document unwarping", value=True, min_width=10)
+                                doc_orientation_switch = gr.Checkbox(label="Enable orientation classification", value=True, min_width=10)
 
                     if complex_document_examples:
                         complex_paths = [e[0] for e in complex_document_examples]  # 这里是 List[str]
@@ -343,13 +351,13 @@ with gr.Blocks(head=GOOGLE_FONTS_URL, css=custom_css, theme=gr.themes.Soft()) as
 
             file_doc.change(fn=on_file_doc_change, inputs=[file_doc], outputs=[example_url_doc, preview_doc_html])
 
-            def parse_doc_router(fp, example_url, use_chart):
+            def parse_doc_router(fp, example_url, use_chart, use_unwarping, use_orientation):
                 src = fp if fp else example_url
                 if not src:
                     raise gr.Error("Please upload an image or pick an example first.")
-                return handle_complex_doc(src, use_chart)
+                return handle_complex_doc(src, use_chart, use_unwarping, use_orientation)
 
-            btn_parse.click(fn=parse_doc_router, inputs=[file_doc, example_url_doc, chart_parsing_switch],
+            btn_parse.click(fn=parse_doc_router, inputs=[file_doc, example_url_doc, chart_parsing_switch, doc_unwarping_switch, doc_orientation_switch],
                             outputs=[md_preview_doc, vis_image_doc, md_raw_doc])
 
         # ===================== Element-level Recognition =====================