Update app.py

app.py

@@ -8,8 +8,8 @@ from pathlib import Path
 import re
 
 os.system('pip install -r requirements.txt')
-os.system('pip install -U magic_pdf-0.8.0a1-py3-none-any.whl')
-# os.system('python -m pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/')
+os.system('pip install -U magic_pdf-0.8.0a2-py3-none-any.whl')
+os.system('python -m pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/')
 
 from huggingface_hub import snapshot_download
 model_dir = snapshot_download('opendatalab/PDF-Extract-Kit')
@@ -17,7 +17,7 @@ model_dir = snapshot_download('opendatalab/PDF-Extract-Kit')
 os.system('wget https://github.com/opendatalab/MinerU/raw/master/magic-pdf.template.json')
 os.system('cp magic-pdf.template.json ~/magic-pdf.json')
 os.system(f"sed -i 's|/tmp/models|{model_dir}/models|g' /home/user/magic-pdf.json")
-# os.system("sed -i 's|cpu|cuda|g' /home/user/magic-pdf.json")
+os.system("sed -i 's|cpu|cuda|g' /home/user/magic-pdf.json")
 
 os.system("pip install gradio-pdf")
 from gradio_pdf import PDF
@@ -35,7 +35,7 @@ def read_fn(path):
     disk_rw = DiskReaderWriter(os.path.dirname(path))
     return disk_rw.read(os.path.basename(path), AbsReaderWriter.MODE_BIN)
 
-
+@spaces.GPU(duration=120)
 def parse_pdf(doc_path, output_dir, end_page_id):
     os.makedirs(output_dir, exist_ok=True)
 
@@ -119,7 +119,8 @@ def to_markdown(file_path, end_pages):
     # 返回转换后的PDF路径
     new_pdf_path = os.path.join(local_md_dir, file_name + "_layout.pdf")
 
-    return md_content, txt_content, archive_zip_path, show_pdf(new_pdf_path)
+    # return md_content, txt_content, archive_zip_path, show_pdf(new_pdf_path)
+    return md_content, txt_content, archive_zip_path, new_pdf_path
 
 
 # def show_pdf(file_path):
@@ -141,25 +142,25 @@ if __name__ == "__main__":
     with gr.Blocks() as demo:
         with gr.Row():
             with gr.Column(variant='panel', scale=5):
-                file = gr.File(label="Please upload pdf", file_types=[".pdf"])
+                # file = gr.File(label="Please upload pdf", file_types=[".pdf"])
+                pdf_show = gr.Markdown()
                 max_pages = gr.Slider(1, 10, 5, step=1, label="Max convert pages")
                 with gr.Row() as bu_flow:
                     change_bu = gr.Button("Convert")
-                    clear_bu = gr.ClearButton([file, max_pages], value="Clear")
-                gr.Markdown(value="### PDF preview")
+                    clear_bu = gr.ClearButton([pdf_show], value="Clear")
                 # pdf_show = gr.HTML(label="PDF preview")
-                pdf_show = PDF(label="PDF preview", interactive=True, height=1000)
+                pdf_show = PDF(label="Please upload pdf", interactive=True, height=800)
 
             with gr.Column(variant='panel', scale=5):
                 output_file = gr.File(label="convert result", interactive=False)
                 with gr.Tabs():
                     with gr.Tab("Markdown rendering"):
-                        md = gr.Markdown(label="Markdown rendering", height=1100, show_copy_button=True,
+                        md = gr.Markdown(label="Markdown rendering", height=900, show_copy_button=True,
                                          latex_delimiters=latex_delimiters, line_breaks=True)
                     with gr.Tab("Markdown text"):
-                        md_text = gr.TextArea(lines=55, show_copy_button=True)
-        file.upload(fn=show_pdf, inputs=file, outputs=pdf_show)
-        change_bu.click(fn=to_markdown, inputs=[file, max_pages], outputs=[md, md_text, output_file, pdf_show])
+                        md_text = gr.TextArea(lines=45, show_copy_button=True)
+        # file.upload(fn=show_pdf, inputs=file, outputs=pdf_show)
+        change_bu.click(fn=to_markdown, inputs=[pdf_show, max_pages], outputs=[md, md_text, output_file, pdf_show])
         clear_bu.add([md, pdf_show, md_text, output_file])
 
     demo.launch()