Update app.py

app.py

@@ -1,14 +1,17 @@
 import base64
 import streamlit as st
-import openai
+from openai import OpenAI
 import os
+from dotenv import load_dotenv
+import pdf2image
 from PIL import Image
 import io
 import tempfile
-import pdf2image
 
-# Set OpenAI API key from Streamlit secrets
-openai.api_key = st.secrets["OPENAI_API_KEY"]
+# Load environment variables
+load_dotenv()
+# Initialize OpenAI client
+client = OpenAI(api_key=os.getenv('OPENAI_API_KEY'))
 
 def convert_pdf_to_images(pdf_file):
     """Convert PDF to list of images"""
@@ -16,35 +19,35 @@ def convert_pdf_to_images(pdf_file):
         tmp_file.write(pdf_file.getvalue())
         pdf_path = tmp_file.name
     
-    try:
-        images = pdf2image.convert_from_path(pdf_path)
-        os.unlink(pdf_path)
-        return images
-    except Exception as e:
-        st.error(f"Error converting PDF: {str(e)}")
-        return []
+    images = pdf2image.convert_from_path(pdf_path)
+    os.unlink(pdf_path)
+    return images
 
 def format_response(text):
-    """Format the analysis response with clean styling"""
     formatted_text = """
     <div style="
         background-color: white;
-        padding: 20px;
-        border-radius: 5px;
+        padding: 30px;
+        border-radius: 10px;
         font-family: Arial, sans-serif;
-        box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+        box-shadow: 0 2px 8px rgba(0,0,0,0.1);
+        margin: 20px 0;
     ">
     """
     
-    # Split into pages
     pages = text.split("Page")
     
     for page_num, page_content in enumerate(pages[1:], 1):
-        # Add page header
-        formatted_text += f'<div style="margin-bottom: 30px;">'
-        formatted_text += f'<h3 style="color: #2c3e50; margin-bottom: 15px;">Page {page_num}</h3>'
+        formatted_text += f'''
+            <div style="margin-bottom: 40px;">
+                <h3 style="color: #2c3e50; 
+                          margin-bottom: 20px;
+                          padding-bottom: 10px;
+                          border-bottom: 2px solid #eee;">
+                    Page {page_num}
+                </h3>
+        '''
         
-        # Process each line
         lines = page_content.split('\n')
         for line in lines:
             if line.strip() and not line.strip().startswith('*') and not line.strip().startswith('Here'):
@@ -52,15 +55,26 @@ def format_response(text):
                 
                 if ':' in line:
                     label, value = line.split(':', 1)
-                    formatted_text += f'<div style="margin-bottom: 10px; display: flex;">'
-                    formatted_text += f'<span style="font-weight: bold; color: #2c3e50; min-width: 200px;">{label.strip()}</span>'
-                    formatted_text += f'<span style="color: #34495e; flex: 1;">{value.strip()}</span>'
-                    formatted_text += '</div>'
+                    formatted_text += f'''
+                        <div style="margin-bottom: 15px; 
+                                  display: flex;
+                                  align-items: baseline;
+                                  gap: 20px;">
+                            <span style="font-weight: 600; 
+                                     color: #2c3e50; 
+                                     min-width: 200px;">
+                                {label.strip()}
+                            </span>
+                            <span style="color: #34495e; flex: 1;">
+                                {value.strip()}
+                            </span>
+                        </div>
+                    '''
         
         formatted_text += '</div>'
         
         if page_num < len(pages) - 1:
-            formatted_text += '<hr style="border: 1px solid #eee; margin: 20px 0;">'
+            formatted_text += '<hr style="border: none; border-top: 1px solid #eee; margin: 30px 0;">'
     
     formatted_text += '</div>'
     return formatted_text
@@ -74,7 +88,7 @@ def analyze_image(image):
         
         base64_image = base64.b64encode(img_byte_arr).decode("utf-8")
         
-        response = openai.ChatCompletion.create(
+        response = client.chat.completions.create(
             model="gpt-4-vision-preview",
             messages=[
                 {
@@ -104,124 +118,93 @@ def analyze_image(image):
             max_tokens=1000
         )
         
-        return response.choices[0].message['content']
+        return response.choices[0].message.content
     except Exception as e:
-        st.error(f"API Error: {str(e)}")
         return f"An error occurred: {str(e)}"
+
 def main():
     st.set_page_config(page_title="Document Analysis App", layout="wide")
     
-    # Updated styling with better contrast and modern look
+    # Custom CSS
     st.markdown("""
         <style>
         .stApp {
-            background-color: #f8f9fa;
+            background-color: #ffffff !important;
+        }
+        .main {
+            padding: 20px;
+            max-width: 1200px;
+            margin: 0 auto;
         }
         .stButton>button {
             width: 100%;
-            background-color: #0066cc;  /* Changed to a more vibrant blue */
+            background-color: #2c3e50;
             color: white;
             border: none;
-            padding: 12px 24px;
-            border-radius: 6px;
-            margin-top: 20px;
-            margin-bottom: 20px;
-            font-weight: 500;
-            transition: background-color 0.3s ease;
+            padding: 10px 20px;
+            border-radius: 5px;
+            margin: 20px 0;
         }
         .stButton>button:hover {
-            background-color: #0052a3;
+            background-color: #34495e;
         }
         .uploadedFile {
-            margin-bottom: 20px;
-            background-color: white;
-            padding: 15px;
-            border-radius: 6px;
-            border: 1px solid #e0e0e0;
-        }
-        div[data-testid="stFileUploader"] {
-            background-color: white;
-            padding: 20px;
-            border-radius: 10px;
-            border: 2px dashed #cccccc;
             margin: 20px 0;
+            padding: 20px;
+            background-color: #f8f9fa;
+            border-radius: 5px;
+        }
+        [data-testid="stHeader"] {
+            background-color: transparent;
+        }
+        .stDeployButton {
+            display: none !important;
         }
-        h1 {
-            color: #1a1a1a;
-            margin-bottom: 30px;
-            text-align: center;
+        .main .block-container {
+            padding-top: 2rem;
+            padding-bottom: 2rem;
         }
         </style>
     """, unsafe_allow_html=True)
-
-    # Update the format_response function styling
-    def format_response(text):
-        formatted_text = """
-        <div style="
-            background-color: white;
-            padding: 30px;
-            border-radius: 10px;
-            font-family: 'Segoe UI', Arial, sans-serif;
-            box-shadow: 0 4px 6px rgba(0,0,0,0.1);
-            margin: 20px 0;
-            border: 1px solid #e0e0e0;
-        ">
-        """
-        
-        pages = text.split("Page")
+    
+    # Main container
+    with st.container():
+        col1, col2, col3 = st.columns([1,3,1])
         
-        for page_num, page_content in enumerate(pages[1:], 1):
-            formatted_text += f'<div style="margin-bottom: 30px;">'
-            formatted_text += f'<h3 style="color: #0066cc; margin-bottom: 20px; padding-bottom: 10px; border-bottom: 2px solid #f0f0f0;">Page {page_num}</h3>'
+        with col2:
+            st.title("Document Analysis App")
             
-            lines = page_content.split('\n')
-            for line in lines:
-                if line.strip() and not line.strip().startswith('*') and not line.strip().startswith('Here'):
-                    line = line.replace('**', '').replace('- ', '')
-                    
-                    if ':' in line:
-                        label, value = line.split(':', 1)
-                        formatted_text += f'<div style="margin-bottom: 15px; display: flex; align-items: center;">'
-                        formatted_text += f'<span style="font-weight: 600; color: #2c3e50; min-width: 200px; padding-right: 20px;">{label.strip()}</span>'
-                        formatted_text += f'<span style="color: #333333; flex: 1;">{value.strip()}</span>'
-                        formatted_text += '</div>'
-            
-            formatted_text += '</div>'
+            upload_container = st.container()
+            with upload_container:
+                uploaded_file = st.file_uploader(
+                    "Upload document (PDF/Image)", 
+                    type=['pdf', 'png', 'jpg', 'jpeg']
+                )
             
-            if page_num < len(pages) - 1:
-                formatted_text += '<hr style="border: none; height: 1px; background-color: #e0e0e0; margin: 30px 0;">'
-        
-        formatted_text += '</div>'
-        return formatted_text
-    
-    col1, col2, col3 = st.columns([1,2,1])
-    with col2:
-        st.title("Document Analysis App")
-        
-        uploaded_file = st.file_uploader("Upload document (PDF/Image)", type=['pdf', 'png', 'jpg', 'jpeg'])
-        
-        if uploaded_file is not None:
-            if uploaded_file.type == "application/pdf":
-                with st.spinner("Processing PDF..."):
-                    images = convert_pdf_to_images(uploaded_file)
+            if uploaded_file is not None:
+                if uploaded_file.type == "application/pdf":
+                    # Handle PDF
+                    with st.spinner("Processing PDF..."):
+                        images = convert_pdf_to_images(uploaded_file)
+                        
+                        if st.button("Extract Information"):
+                            with st.spinner("Analyzing document..."):
+                                all_results = []
+                                for i, image in enumerate(images, 1):
+                                    result = analyze_image(image)
+                                    all_results.append(f"Page {i} Information:\n{result}")
+                                
+                                combined_results = "\n\n".join(all_results)
+                                st.markdown(format_response(combined_results), unsafe_allow_html=True)
+                                
+                else:
+                    # Handle single image
+                    image = Image.open(uploaded_file)
                     
                     if st.button("Extract Information"):
                         with st.spinner("Analyzing document..."):
-                            all_results = []
-                            for i, image in enumerate(images, 1):
-                                result = analyze_image(image)
-                                all_results.append(f"Page {i} Information:\n{result}")
-                            
-                            combined_results = "\n\n".join(all_results)
-                            st.markdown(format_response(combined_results), unsafe_allow_html=True)
-                            
-            else:
-                image = Image.open(uploaded_file)
-                
-                if st.button("Extract Information"):
-                    with st.spinner("Analyzing document..."):
-                        result = analyze_image(image)
-                        st.markdown(format_response(result), unsafe_allow_html=True)
+                            result = analyze_image(image)
+                            st.markdown(format_response(f"Page 1\n{result}"), unsafe_allow_html=True)
 
 if __name__ == "__main__":
     main()