Create app.py

app.py

@@ -0,0 +1,173 @@
+import base64
+import streamlit as st
+from openai import OpenAI
+import os
+from dotenv import load_dotenv
+import pdf2image
+from PIL import Image
+import io
+import tempfile
+
+# Load environment variables
+
+# 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"""
+    with tempfile.NamedTemporaryFile(delete=False, suffix='.pdf') as tmp_file:
+        tmp_file.write(pdf_file.getvalue())
+        pdf_path = tmp_file.name
+    
+    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;
+        font-family: Arial, sans-serif;
+        box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+    ">
+    """
+    
+    # Split into pages
+    pages = text.split("Page")
+    
+    for page_num, page_content in enumerate(pages[1:], 1):  # Skip first empty split
+        # 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>'
+        
+        # Process each line
+        lines = page_content.split('\n')
+        for line in lines:
+            # Skip empty lines and lines with asterisks
+            if line.strip() and not line.strip().startswith('*') and not line.strip().startswith('Here'):
+                # Remove asterisks and dashes
+                line = line.replace('**', '').replace('- ', '')
+                
+                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 += '</div>'
+        
+        # Add separator between pages except for the last page
+        if page_num < len(pages) - 1:
+            formatted_text += '<hr style="border: 1px solid #eee; margin: 20px 0;">'
+    
+    formatted_text += '</div>'
+    return formatted_text
+
+def analyze_image(image):
+    """Analyze image using OpenAI API"""
+    try:
+        img_byte_arr = io.BytesIO()
+        image.save(img_byte_arr, format='PNG')
+        img_byte_arr = img_byte_arr.getvalue()
+        
+        base64_image = base64.b64encode(img_byte_arr).decode("utf-8")
+        
+        response = client.chat.completions.create(
+            model="gpt-4o-mini",
+            messages=[
+                {
+                    "role": "user",
+                    "content": [
+                        {
+                            "type": "text",
+                            "text": """Please analyze the image and extract the following information:
+                            - Sender information
+                            - Recipient information
+                            - Container details
+                            - Weights and measurements
+                            - Dates and reference numbers
+                            - Cargo details
+                            
+                            Format the response as 'Label: Value' pairs."""
+                        },
+                        {
+                            "type": "image_url",
+                            "image_url": {
+                                "url": f"data:image/jpeg;base64,{base64_image}"
+                            },
+                        },
+                    ],
+                }
+            ],
+            max_tokens=1000
+        )
+        
+        return response.choices[0].message.content
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
+
+def main():
+    st.set_page_config(page_title="Document Analysis App", layout="wide")
+    
+    # Custom CSS to set light background and improve button styling
+    st.markdown("""
+        <style>
+        .stApp {
+            background-color: white;
+        }
+        .stButton>button {
+            width: 100%;
+            background-color: #2c3e50;
+            color: white;
+            border: none;
+            padding: 10px 20px;
+            border-radius: 5px;
+            margin-top: 20px;
+            margin-bottom: 20px;
+        }
+        .stButton>button:hover {
+            background-color: #34495e;
+        }
+        .uploadedFile {
+            margin-bottom: 20px;
+        }
+        </style>
+    """, unsafe_allow_html=True)
+    
+    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":
+                # 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..."):
+                        result = analyze_image(image)
+                        st.markdown(format_response(result), unsafe_allow_html=True)
+
+if __name__ == "__main__":
+    main()