import streamlit as st
from transformers import pipeline
from PIL import Image
import openai

# Set your OpenAI API key
openai.api_key = "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"

# OpenAI model to use
OPENAI_MODEL = "gpt-4o"  # Replace with the model you want to display

# Load the image classification pipeline
@st.cache_resource
def load_image_classification_pipeline():
    return pipeline("image-classification", model="Shresthadev403/food-image-classification")

pipe_classification = load_image_classification_pipeline()

# Function to generate ingredients using OpenAI
def get_ingredients_openai(food_name):
    prompt = f"List the main ingredients typically used to prepare {food_name}:"
    response = openai.Completion.create(
        engine=OPENAI_MODEL,
        prompt=prompt,
        max_tokens=50
    )
    return response['choices'][0]['text'].strip()

# Streamlit app
st.title("Food Image Recognition with Ingredients")

# Display OpenAI model being used
st.sidebar.title("Model Information")
st.sidebar.write(f"**OpenAI Model Used**: {OPENAI_MODEL}")

# Upload image
uploaded_file = st.file_uploader("Choose a food image...", type=["jpg", "png", "jpeg"])

if uploaded_file is not None:
    # Display the uploaded image
    image = Image.open(uploaded_file)
    st.image(image, caption="Uploaded Image", use_column_width=True)
    st.write("Classifying...")
    
    # Make predictions
    predictions = pipe_classification(image)
    
    # Display only the top prediction
    top_food = predictions[0]['label']
    st.header(f"Food: {top_food}")
    
    # Generate and display ingredients for the top prediction
    st.subheader("Ingredients")
    try:
        ingredients = get_ingredients_openai(top_food)
        st.write(ingredients)
    except Exception as e:
        st.write("Could not generate ingredients. Please try again later.")