Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -159,7 +159,7 @@ def convert_to_markdown_stream(
159
  if with_img_desc:
160
  user_prompt = """Extract the text from the above document as if you were reading it naturally. Return the tables in html format. Return the equations in LaTeX representation. If there is an image in the document and image caption is not present, add a small description of the image inside the <img></img> tag; otherwise, add the image caption inside <img></img>. Watermarks should be wrapped in brackets. Ex: <watermark>OFFICIAL COPY</watermark>. Page numbers should be wrapped in brackets. Ex: <page_number>14</page_number> or <page_number>9/22</page_number>. Prefer using ☐ and β˜‘ for check boxes."""
161
  else:
162
- user_prompt = """Extract the text from the above document as if you were reading it naturally. Return the tables in html format. Watermarks should be wrapped in brackets. Ex: <watermark>OFFICIAL COPY</watermark>. Page numbers should be wrapped in brackets. Ex: <page_number>14</page_number> or <page_number>9/22</page_number>. Prefer using ☐ and β˜‘ for check boxes."""
163
 
164
  # Accumulate results from all pages
165
  full_markdown_content = ""
 
159
  if with_img_desc:
160
  user_prompt = """Extract the text from the above document as if you were reading it naturally. Return the tables in html format. Return the equations in LaTeX representation. If there is an image in the document and image caption is not present, add a small description of the image inside the <img></img> tag; otherwise, add the image caption inside <img></img>. Watermarks should be wrapped in brackets. Ex: <watermark>OFFICIAL COPY</watermark>. Page numbers should be wrapped in brackets. Ex: <page_number>14</page_number> or <page_number>9/22</page_number>. Prefer using ☐ and β˜‘ for check boxes."""
161
  else:
162
+ user_prompt = """Extract the text from the above document as if you were reading it naturally. Return the tables in html format. Return the equations in LaTeX representation. Watermarks should be wrapped in brackets. Ex: <watermark>OFFICIAL COPY</watermark>. Page numbers should be wrapped in brackets. Ex: <page_number>14</page_number> or <page_number>9/22</page_number>. Prefer using ☐ and β˜‘ for check boxes."""
163
 
164
  # Accumulate results from all pages
165
  full_markdown_content = ""