Create app.py

app.py

@@ -0,0 +1,94 @@
+from flask import Flask, request, jsonify
+import re
+import pandas as pd
+import google.generativeai as genai
+import pypdf
+import json
+from datetime import datetime
+import os
+from flask_cors import CORS
+
+app = Flask(__name__)
+CORS(app)  # Enable CORS for all routes
+
+api_key = os.environ['Gemini']
+
+def configure_gemini(api_key):
+    genai.configure(api_key=api_key)
+    return genai.GenerativeModel('gemini-2.0-flash-exp')
+
+def read_pdf(file_path):
+    text_content = []
+    with open(file_path, 'rb') as file:
+        pdf_reader = pypdf.PdfReader(file)  
+        for page in pdf_reader.pages:
+            text = page.extract_text()
+            if text:
+                text_content.append(text)
+    return "\n".join(text_content)
+
+def process_with_gemini(model, text):
+    prompt = """Analyze this bank statement and extract transactions in JSON format with these fields:
+    - Date (format DD/MM/YYYY)
+    - Description
+    - Amount (just the integer value)
+    - Type (is 'income' if 'credit amount', else 'expense')
+    - Customer Name (Only If Type is 'income' and if no name is extracted write 'general income' and if type is not 'income' write 'expense')
+    - City (In address of bank statement)
+    
+    Return ONLY valid JSON with this structure:
+    {
+        "transactions": [
+            {
+                "Date": "string",
+                "Description": "string",
+                "Customer_name": "string",
+                "City": "string",
+                "Amount": number,
+                "Type": "string"
+            }
+        ]
+    }"""
+    
+    response = model.generate_content([prompt, text])
+    return response.text
+
+@app.route('/process-pdf', methods=['POST'])
+def process_pdf():
+    try:
+        if 'file' not in request.files:
+            return jsonify({'error': 'No file uploaded'}), 400
+            
+        file = request.files['file']
+        if file.filename == '':
+            return jsonify({'error': 'No file selected'}), 400
+            
+        if not file.filename.endswith('.pdf'):
+            return jsonify({'error': 'File must be a PDF'}), 400
+
+        # Save uploaded file temporarily
+        temp_path = "temp.pdf"
+        file.save(temp_path)
+        
+        # Configure Gemini and process PDF
+        model = configure_gemini(api_key)
+        pdf_text = read_pdf(temp_path)
+        json_response = process_with_gemini(model, pdf_text)
+        
+        # Clean JSON response
+        json_str = json_response[json_response.find('{'):json_response.rfind('}')+1]
+        json_str = json_str.replace('```json', '').replace('```', '')
+        
+        # Parse JSON and return
+        data = json.loads(json_str)
+        
+        # Clean up temp file
+        os.remove(temp_path)
+        
+        return jsonify(data)
+        
+    except Exception as e:
+        return jsonify({'error': str(e)}), 500
+
+if __name__ == '__main__':
+    app.run(debug=True,host="0.0.0.0", port=7860)