removed 2 LLM calls, replaced with 1

app.py

@@ -6,7 +6,7 @@ from PIL import Image
 import gradio as gr
 import requests
 from io import BytesIO
-
+import json
 
 # Load environment variables from .env
 load_dotenv()
@@ -16,8 +16,13 @@ from groq import Groq
 client = Groq(
     api_key=os.environ.get("GROQ_API_KEY"),
 )
+genai.configure(api_key=os.environ.get("GENAI_API_KEY"))
 
-
+#I'm using a virtual environment for this locally
+#python -m venv eccomercespace
+#source eccomercespace/Scripts/activate  (for windows)
+#pip install -r requirements.txt
+#python app.py
 
 
 # Fetch variables
@@ -28,8 +33,6 @@ HF_TOKEN = os.getenv("HF_TOKEN")
 
 
 def product_identification_response(image_path=r"C:\Users\JoeJo\Downloads\XyAaqBEtYtb8YffjKZ68Gb.jpg"):
-    # Authenticate
-    genai.configure(api_key=os.environ.get("GENAI_API_KEY"))
     
     # Load Gemini Pro Vision
     model = genai.GenerativeModel('gemini-2.5-flash')
@@ -45,21 +48,42 @@ def product_identification_response(image_path=r"C:\Users\JoeJo\Downloads\XyAaqB
     else:
         image = Image.open(clean_path)
     
-    # Ask Gemini
+    #structured output
+    schema = {
+        "type": "object",
+        "properties": {
+            "product": {"type": "string", "description": "Name of the product in the image"},
+            "condition": {"type": "string", "enum": ["new", "like new", "good", "fair", "poor"], "description": "Condition of the product"},
+            },
+            "required": ["product", "condition"]
+        }
+
     response = model.generate_content(
-        ["What product is in this image, and what is the condition of the product?", image]
+        contents=["What product is in this image, and what is the condition of the product?", image],
+        generation_config={
+            "response_mime_type": "application/json",
+            "response_schema": schema
+        }
     )
+    print(f"response is: {response}")
+
+    data = json.loads(response.text)
+    return data
+
+    # Ask Gemini
+    #response = model.generate_content(
+        #["What product is in this image, and what is the condition of the product?", image]
+    #)
+    
+    #print(f"gemini-2.5-flash answer is: {response.text}")
     
-    print(f"gemini-1.5-flash answer is: {response.text}")
     
-    prompt = f"""Your task is to returned structured JSON of product and condition in the following format: {{ "product": "the identity of the product", "condition": "the condition of the product"}}.
-    The condition of the product must be one of the following: (*) New, (*) Like New, (*) Good or (*) Poor.
-    Use the data from {response} as the source for your response
-    """
     prompt2 = f"""Your task is to returned structured JSON of product and condition in the following format: {{ "product": "the identity of the product", "condition": "the condition of the product"}}.
     The condition of the product must be one of the following: (*) New or (*) Used.
     Use the data from {response} as the source for your response"""
-    
+
+
+    #this is a second LLM call, to LLama using Grok, to format identified image data - need to remove this unneccesary call
     chat_completion = client.chat.completions.create(
         messages=[
             {