🛠️ [v1.0.2] Minor Changes

instructions/lumi_instructions.md

@@ -21,14 +21,14 @@ You are Lumi, an intelligent product nutrient analyzer. Your role is to categori
      - **positive_nutrient**:
        - List containing dictionaries, each representing a positive nutrient with the following keys:
          - `name`: Nutrient name
-         - `icon`: Icon name
+         - `icon`: Icon name (No emoji)
          - `quantity`: Nutrient quantity (e.g., "10.00 g")
          - `text`: Humorous analysis of the quantity (max 6 words)
          - `color`: Color indication based on quantity and nutrient type (#8AC449 for positive nutrients, #F8A72C for close to threshold, #DF5656 for negative nutrients)
      - **negative_nutrient**:
        - List containing dictionaries, each representing a negative nutrient with the following keys:
          - `name`: Nutrient name
-         - `icon`: Icon name
+         - `icon`: Icon name (No emoji)
          - `quantity`: Nutrient quantity (e.g., "10.00 g")
          - `text`: Humorous analysis of the quantity (max 6 words)
          - `color`: Color indication based on quantity and nutrient type (#8AC449 for positive nutrients, #F8A72C for close to threshold, #DF5656 for negative nutrients)

metadata/food_categories.json

@@ -25,9 +25,10 @@
   "Butter": ["Cocoa Butter"],
   "Calcium": ["Calcium Carbonate", "Calcium Pantothenate"],
   "Caffeine": ["Contains Caffeine", "Instant Coffee Chicory Mixture"],
-  "Carbohydrate": ["Carbohydrates"],
+  "Carbohydrates": ["Carbohydrate"],
   "Cocoa": ["Cocoa Mass", "Cocoa Solids", "Low-Fat Cocoa"],
-  "Corn": ["Corn Grits", "Corn Meal", "Corn Starch"],
+  "Chocolate": ["Milk Chocolate", "Chocolate Chips"],
+  "Corn": ["Corn Grits", "Corn Meal", "Corn Starch", "Corn Syrup"],
   "Cream": ["Choco Crème"],
   "Dal": ["Urad Dal"],
   "Emulsifiers": ["Emulsifier", "Emulsifier Of Vegetable"],
@@ -78,7 +79,7 @@
   "Spices": ["Mixed Spices"],
   "Sodium": ["Sodium Bicarbonate", "Sodium Carbonate"],
   "Stabilizers": ["Stabilizer"],
-  "Sugar": ["Added Sugar", "Added Sugars", "Sugars"],
+  "Sugars": ["Added Sugar", "Added Sugars", "Sugar"],
   "Sunflower-Oil": ["Refined Sunflower Oil"],
   "Syrup": [
     "Glucose-Fructose Syrup",

server/gemini.py

@@ -14,7 +14,12 @@
 
 # Blueprint for the ai routes
 ai_blueprint = Blueprint('ai', __name__)
-genai.configure(api_key=GEMINI_API_KEY) # Load Gemini API key from .env
+# Load the Gemini API key from the environment variables
+if GEMINI_API_KEY:
+    print('GEMINI_API_KEY is set.')
+else:
+    print('GEMINI_API_KEY is not set.')
+genai.configure(api_key=GEMINI_API_KEY)
 
 # Generation settings to control the model's output
 generation_config = {
@@ -107,7 +112,7 @@ def swapr(email: str, product_data: dict) -> Response:
         )
 
         if database_response.status_code != 200:
-            runtime_error('swapr', 'Database search failed.', middleware=database_response.json(), email=email)
+            # runtime_error('swapr', 'Database search failed.', middleware=database_response.json(), email=email)
             # return jsonify({'error': 'Database search failed.'}), database_response.status_code
             return {'product_name': filtered_response.strip()}
 
@@ -159,7 +164,6 @@ def savora() -> Response:
 
             # Delete the temporary file after processing
             os.remove(temp_path)
-
         else:
             return jsonify({'error': 'Invalid message type.'}), 400
 

server/search.py

@@ -13,7 +13,7 @@
 
 # Blueprint for the search routes
 search_blueprint = Blueprint('search', __name__)
-api = openfoodfacts.API(user_agent='Mivro/1.5') # Initialize the Open Food Facts API client
+api = openfoodfacts.API(user_agent='Mivro/1.0') # Initialize the Open Food Facts API client
 
 @search_blueprint.route('/barcode', methods=['POST'])
 def barcode() -> Response:
@@ -63,16 +63,20 @@ def barcode() -> Response:
             'ingredients': filter_ingredient(filtered_product_data.get('ingredients', [])),
             'nova_group_name': nova_name(filtered_product_data.get('nova_group', '')),
             'nutriments': lumi(filtered_product_data.get('nutriments', {})),
-            'total_nutriments': len(filtered_product_data.get('nutriments', {}).get('positive_nutrient', [])) + 
-                                len(filtered_product_data.get('nutriments', {}).get('negative_nutrient', [])),
             'nutriscore_grade_color': grade_color(filtered_product_data.get('nutriscore_grade', '')),
             'nutriscore_assessment': score_assessment(filtered_product_data.get('nutriscore_score', None)).title(),
             'health_risk': lumi(filtered_product_data.get('ingredients', [])),
-            'total_health_risks': len(filtered_product_data.get('health_risk', {}).get('ingredient_warnings', [])),
             'selected_images': filter_image(filtered_product_data.get('selected_images', [])),
             'recommeded_product': swapr(email, filtered_product_data)
         })
 
+        # Calculating derived fields outside as they're not directly provided by the API
+        filtered_product_data['total_nutriments'] = (
+            len(filtered_product_data.get('nutriments', {}).get('positive_nutrient', [])) +
+            len(filtered_product_data.get('nutriments', {}).get('negative_nutrient', []))
+        )
+        filtered_product_data['total_health_risks'] = len(filtered_product_data.get('health_risk', {}).get('ingredient_warnings', []))
+
         # Store the scan history for the product barcode in Firestore
         database_history(email, product_barcode, filtered_product_data)
         return jsonify(filtered_product_data)