Update app.py

app.py

@@ -11,7 +11,7 @@ from io import BytesIO
 from fuzzywuzzy import process
 import kaleido  # Ensure kaleido is imported
 
-# Attribute mappings: readable names to Salesforce API names
+# ✅ Attribute mappings: readable names to Salesforce API names
 ATTRIBUTE_MAPPING = {
     "Product name": "Productname__c",
     "Type": "Type__c",
@@ -23,25 +23,21 @@ ATTRIBUTE_MAPPING = {
     "Model": "Model__c"
 }
 
-# List of product names to match
+# ✅ List of product names to match
 PRODUCT_NAMES = [
     "CG COMMERCIAL MOTORS", "Fusion", "Agroking", "Openwell"
 ]
 
-# List of model names to match
+# ✅ List of model names to match
 MODEL_NAMES = [
     "V9", "V4", "V3", "V7", "V6"
 ]
 
-# Initialize PaddleOCR
-ocr = PaddleOCR(use_angle_cls=True, lang='en')
-
-def extract_text_from_image(image_array):
+def extract_text(image_path):
     """
     Extracts text from an image using PaddleOCR.
-    Accepts an image as a numpy array (cv2 image or similar).
     """
-    result = ocr.ocr(image_array)
+    result = ocr.ocr(image_path)
     extracted_text = []
     
     for line in result[0]:
@@ -79,14 +75,29 @@ def match_model_name(extracted_text):
 
     return best_match if best_score >= 70 else None  # Threshold of 70 for a match
 
-# Example Usage: Load an image file into a numpy array (cv2 format)
-def process_image(image_path):
-    image = cv2.imread(image_path)  # Read the image
-    extracted_text = extract_text_from_image(image)  # Extract text
+def extract_attributes(extracted_text):
+    """
+    Extracts key attributes like Model, H.P, Stage, Voltage, etc., from the extracted text.
+    """
+    attributes = {}
+    
+    for text in extracted_text.split("\n"):
+        if "Model" in text:
+            attributes["Model"] = text.split("Model")[-1].strip(" :")
+        elif "H.P" in text or "HP" in text:
+            attributes["H.P"] = text.split("H.P")[-1].strip(" :")
+        elif "Stage" in text:
+            attributes["Stage"] = text.split("Stage")[-1].strip(" :")
+        elif "Outlet" in text:
+            attributes["Outlet"] = text.split("Outlet")[-1].strip(" :")
+        elif "Voltage" in text:
+            attributes["Voltage"] = text.split("Voltage")[-1].strip(" :")
+        elif "Phase" in text:
+            attributes["Phase"] = text.split("Phase")[-1].strip(" :")
+        elif "Year of Mfg" in text:
+            attributes["Year of Mfg"] = text.split("Year of Mfg")[-1].strip(" :")
 
-    # Matching extracted text with product and model names
-    matched_product = match_product_name(extracted_text)
-    matched_model = match_model_name(extracted_text)
+    return attributes
 
 # Function to extract attributes and their values
 def extract_attributes(extracted_text):