Update app.py

app.py

@@ -1,4 +1,3 @@
-# main.py
 from fastapi import FastAPI, HTTPException, File, UploadFile
 from paddleocr import PaddleOCR
 import fitz
@@ -8,12 +7,22 @@ import os
 import requests
 import sqlite3
 from datetime import datetime
+import uvicorn
 
 app = FastAPI()
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
-ocr = PaddleOCR(use_angle_cls=True, lang='en')
 
+# Initialize PaddleOCR lazily to reduce startup memory usage
+ocr = None
+def get_ocr():
+    global ocr
+    if ocr is None:
+        logger.info("Initializing PaddleOCR")
+        ocr = PaddleOCR(use_angle_cls=False, lang='en', use_gpu=False)  # Disable angle classification and GPU
+    return ocr
+
+# Hugging Face API configuration
 HF_API_URL = "https://api-inference.huggingface.co/models/Abhisesh7/Invoice-Fraud-Detection"
 HF_API_KEY = os.getenv("HF_API_KEY")
 if not HF_API_KEY:
@@ -21,6 +30,7 @@ if not HF_API_KEY:
     raise RuntimeError("Hugging Face API key not set")
 HEADERS = {"Authorization": f"Bearer {HF_API_KEY}", "Content-Type": "application/json"}
 
+# Initialize SQLite database
 conn = sqlite3.connect("invoices.db")
 cursor = conn.cursor()
 cursor.execute("""
@@ -37,14 +47,18 @@ conn.commit()
 @app.post("/process_invoice/")
 async def process_invoice(file: UploadFile = File(...)):
     try:
+        # Validate file type
         if not file.filename.lower().endswith(('.pdf', '.png', '.jpg', '.jpeg')):
             raise HTTPException(status_code=400, detail="Invalid file type. Use PDF or image (PNG, JPG, JPEG).")
 
+        # Save uploaded file
         with tempfile.NamedTemporaryFile(delete=False, suffix=os.path.splitext(file.filename)[1]) as temp_file:
             content = await file.read()
             temp_file.write(content)
             temp_file_path = temp_file.name
 
+        # Extract text using PaddleOCR
+        ocr_instance = get_ocr()
         extracted_text = ""
         if temp_file_path.lower().endswith('.pdf'):
             pdf_document = fitz.open(temp_file_path)
@@ -53,11 +67,11 @@ async def process_invoice(file: UploadFile = File(...)):
                 pix = page.get_pixmap()
                 with tempfile.NamedTemporaryFile(delete=False, suffix=".png") as img_file:
                     pix.save(img_file.name)
-                    result = ocr.ocr(img_file.name, cls=True)
+                    result = ocr_instance.ocr(img_file.name, cls=False)
                     extracted_text += "\n".join([line[1][0] for line in result[0]]) + "\n"
             pdf_document.close()
         else:
-            result = ocr.ocr(temp_file_path, cls=True)
+            result = ocr_instance.ocr(temp_file_path, cls=False)
             extracted_text = "\n".join([line[1][0] for line in result[0]])
 
         os.unlink(temp_file_path)
@@ -65,6 +79,7 @@ async def process_invoice(file: UploadFile = File(...)):
         if not extracted_text.strip():
             raise HTTPException(status_code=400, detail="No text extracted from file.")
 
+        # Call Hugging Face API
         payload = {"text": extracted_text}
         response = requests.post(HF_API_URL, headers=HEADERS, json=payload)
 
@@ -77,11 +92,13 @@ async def process_invoice(file: UploadFile = File(...)):
         fraud_reasoning = result.get("fraud_reasoning", "")
         flagged = result.get("flagged", False)
 
+        # Extract invoice metadata
         vendor = entities.get("vendor", "Unknown")
         amount = float(entities.get("amount", 0))
         date_str = entities.get("date", "")
         invoice_date = datetime.strptime(date_str, "%Y-%m-%d").date().isoformat() if date_str else ""
 
+        # Check for duplicates
         cursor.execute("""
             SELECT id, timestamp FROM invoices 
             WHERE vendor = ? AND amount = ? AND date = ?
@@ -93,6 +110,7 @@ async def process_invoice(file: UploadFile = File(...)):
             fraud_reasoning += f" | {duplicate_info}"
             flagged = True
 
+        # Store invoice metadata
         timestamp = datetime.now().isoformat()
         cursor.execute("""
             INSERT INTO invoices (vendor, amount, date, timestamp)
@@ -116,4 +134,7 @@ async def process_invoice(file: UploadFile = File(...)):
 
 @app.on_event("shutdown")
 def shutdown_event():
-    conn.close()
+    conn.close()
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=int(os.getenv("PORT", 8000)))