Update app.py

app.py

@@ -1,12 +1,10 @@
 import streamlit as st
-from transformers import pipeline
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
 from PIL import Image
-import google.generativeai as palm
 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"]
-palm.configure(api_key=os.environ["GOOGLE_API_KEY"])
+# Hugging Face token login (add this as a secret in Hugging Face Spaces)
+os.environ["HF_TOKEN"] = st.secrets["HF_TOKEN"]
 
 # Load the image classification pipeline
 @st.cache_resource
@@ -18,18 +16,27 @@ def load_image_classification_pipeline():
 
 pipe_classification = load_image_classification_pipeline()
 
-# Function to generate ingredients using Google Gemini
-def get_ingredients_google(food_name):
+# Load the Llama model for ingredient generation
+@st.cache_resource
+def load_llama_pipeline():
+    """
+    Load the Llama model for ingredient generation.
+    """
+    tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-3B-Instruct", use_auth_token=os.environ["HF_TOKEN"])
+    model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B-Instruct", use_auth_token=os.environ["HF_TOKEN"])
+    return pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+pipe_llama = load_llama_pipeline()
+
+# Function to generate ingredients using the Llama model
+def get_ingredients_llama(food_name):
     """
-    Generate a list of ingredients for the given food item using Google Gemini AI.
+    Generate a list of ingredients for the given food item using the Llama model.
     """
     prompt = f"List the main ingredients typically used to prepare {food_name}."
     try:
-        response = palm.generate_text(prompt=prompt)
-        if response and "candidates" in response:
-            return response["candidates"][0]["output"]
-        else:
-            return "No ingredients found."
+        response = pipe_llama(prompt, max_length=50, num_return_sequences=1)
+        return response[0]["generated_text"].strip()
     except Exception as e:
         return f"Error generating ingredients: {e}"
 
@@ -42,7 +49,7 @@ 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**: Google Gemini")
+st.sidebar.write("**LLM for Ingredients**: meta-llama/Llama-3.2-3B-Instruct")
 
 # Upload image
 uploaded_file = st.file_uploader("Choose a food image...", type=["jpg", "png", "jpeg"])
@@ -63,7 +70,7 @@ if uploaded_file is not None:
     # Generate and display ingredients for the top prediction
     st.subheader("Ingredients")
     try:
-        ingredients = get_ingredients_google(top_food)
+        ingredients = get_ingredients_llama(top_food)
         st.write(ingredients)
     except Exception as e:
         st.error(f"Error generating ingredients: {e}")