Update app.py

app.py

@@ -1,18 +1,33 @@
 import streamlit as st
-from transformers import pipeline, AutoImageProcessor, AutoModelForImageClassification
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
 from PIL import Image
 import requests
 
-# Load the model and processor
-st.title("Food Image Classification with Hugging Face")
-st.write("Upload an image to classify the type of food!")
-
-# Load the model
+# Load the image classification pipeline
 @st.cache_resource
-def load_pipeline():
+def load_image_classification_pipeline():
     return pipeline("image-classification", model="Shresthadev403/food-image-classification")
 
-pipe = load_pipeline()
+pipe_classification = load_image_classification_pipeline()
+
+# Load the Meta-Llama model and tokenizer for text generation
+@st.cache_resource
+def load_llama_pipeline():
+    tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-3B-Instruct")
+    model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B-Instruct")
+    return pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+pipe_llama = load_llama_pipeline()
+
+# Function to generate ingredients using Meta-Llama
+def get_ingredients(food_name):
+    prompt = f"List the main ingredients typically used to prepare {food_name}:"
+    response = pipe_llama(prompt, max_length=50, num_return_sequences=1)
+    return response[0]['generated_text']
+
+# Streamlit app
+st.title("Food Image Classification with Ingredients Generation")
+st.write("Upload an image to classify the type of food and get its ingredients!")
 
 # Upload image
 uploaded_file = st.file_uploader("Choose a food image...", type=["jpg", "png", "jpeg"])
@@ -24,13 +39,18 @@ if uploaded_file is not None:
     st.write("Classifying...")
     
     # Make predictions
-    predictions = pipe(image)
+    predictions = pipe_classification(image)
     
-    # Display top prediction
+    # Display only the top prediction
+    top_food = predictions[0]['label']
+    confidence = predictions[0]['score']
     st.subheader("Top Prediction")
-    st.write(f"**{predictions[0]['label']}** with confidence {predictions[0]['score']:.2f}")
+    st.write(f"**{top_food}** with confidence {confidence:.2f}")
     
-    # Display other predictions
-    st.subheader("Other Predictions")
-    for pred in predictions[1:]:
-        st.write(f"{pred['label']}: {pred['score']:.2f}")
+    # Generate and display ingredients for the top prediction
+    st.subheader("Ingredients")
+    try:
+        ingredients = get_ingredients(top_food)
+        st.write(ingredients)
+    except Exception as e:
+        st.write("Could not generate ingredients. Please try again later.")