Update app.py

app.py

@@ -1,18 +1,12 @@
 import streamlit as st
 from transformers import pipeline
 from PIL import Image
-from langchain_community.chat_models import ChatGoogleGenerativeAI
-from langchain_community.llms import HuggingFacePipeline
+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"]
-
-# Initialize Google Gemini model
-llm = ChatGoogleGenerativeAI(
-    model="gemini-1.5-pro",
-    temperature=0
-)
+palm.configure(api_key=os.environ["GOOGLE_API_KEY"])
 
 # Load the image classification pipeline
 @st.cache_resource
@@ -30,8 +24,8 @@ def get_ingredients_google(food_name):
     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}:"
-    response = llm.predict(prompt)
-    return response.strip()
+    response = palm.chat(messages=[{"content": prompt}])
+    return response.last.strip() if response else "Could not generate ingredients."
 
 # Streamlit app setup
 st.title("Food Image Recognition with Ingredients")
@@ -42,7 +36,7 @@ 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 1.5 Pro")
+st.sidebar.write("**LLM for Ingredients**: Google Gemini")
 
 # Upload image
 uploaded_file = st.file_uploader("Choose a food image...", type=["jpg", "png", "jpeg"])