Update app.py

app.py

@@ -1,6 +1,17 @@
 import streamlit as st
-from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
+from transformers import pipeline
 from PIL import Image
+from langchain.chat_models import ChatGoogleGenerativeAI
+import os
+
+# Set up the Google API Key (add this as a secret in Hugging Face Spaces)
+os.environ["GOOGLE_API_KEY"] = st.secrets["GOOGLE_API_KEY"]
+
+# Initialize Google Gemini model
+llm = ChatGoogleGenerativeAI(
+    model="gemini-1.5-pro",
+    temperature=0
+)
 
 # Load the image classification pipeline
 @st.cache_resource
@@ -12,43 +23,29 @@ def load_image_classification_pipeline():
 
 pipe_classification = load_image_classification_pipeline()
 
-# Load Qwen tokenizer and model
-@st.cache_resource
-def load_qwen_model():
-    """
-    Load the Qwen/Qwen2.5-Coder-32B-Instruct model and tokenizer.
-    """
-    tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-Coder-32B-Instruct")
-    model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-32B-Instruct", device_map="auto")
-    return tokenizer, model
-
-# Function to generate ingredients using Qwen
-def get_ingredients_qwen(food_name, tokenizer, model):
+# Function to generate ingredients using Google Gemini
+def get_ingredients_google(food_name):
     """
-    Generate a list of ingredients for the given food item using the Qwen model.
+    Generate a list of ingredients for the given food item using Google Gemini AI.
     """
     prompt = f"List the main ingredients typically used to prepare {food_name}:"
-    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-    outputs = model.generate(**inputs, max_new_tokens=50)
-    return tokenizer.decode(outputs[0], skip_special_tokens=True).strip()
+    response = llm.predict(prompt)
+    return response.strip()
 
-# Streamlit app
+# Streamlit app setup
 st.title("Food Image Recognition with Ingredients")
 
-# # Add the provided image as a banner
-# st.image("CTP_Project/IR_IMAGE", caption="Food Recognition Model", use_column_width=True)
+# Add banner image
+st.image("IR_IMAGE.png", caption="Food Recognition Model", use_column_width=True)
 
 # Sidebar for model information
 st.sidebar.title("Model Information")
 st.sidebar.write("**Image Classification Model**: Shresthadev403/food-image-classification")
-st.sidebar.write("**LLM for Ingredients**: Qwen2.5-Coder-32B-Instruct")
+st.sidebar.write("**LLM for Ingredients**: Google Gemini 1.5 Pro")
 
 # Upload image
 uploaded_file = st.file_uploader("Choose a food image...", type=["jpg", "png", "jpeg"])
 
-# Load the Qwen model and tokenizer
-tokenizer, model = load_qwen_model()
-
 if uploaded_file is not None:
     # Display the uploaded image
     image = Image.open(uploaded_file)
@@ -65,7 +62,10 @@ if uploaded_file is not None:
     # Generate and display ingredients for the top prediction
     st.subheader("Ingredients")
     try:
-        ingredients = get_ingredients_qwen(top_food, tokenizer, model)
+        ingredients = get_ingredients_google(top_food)
         st.write(ingredients)
     except Exception as e:
-        st.error(f"Error generating ingredients: {e}")
+        st.error(f"Error generating ingredients: {e}")
+
+# Footer
+st.sidebar.markdown("Created with ❤️ using Streamlit and Hugging Face.")