app.py

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

# Image classification for plant diseases
plant_disease_pipeline = pipeline(task="image-classification", model="microsoft/resnet-50")

# Load an LLM for remedy generation
llm_pipeline = pipeline("text-generation", model="deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B")

st.title("LLM-Powered Plant Disease Identifier 🌿")

# Upload the plant leaf image
file_name = st.file_uploader("Upload a plant leaf image")

if file_name is not None:
    col1, col2 = st.columns(2)

    # Display the uploaded image
    image = Image.open(file_name)
    col1.image(image, use_container_width=True, caption="Uploaded Image")

    # Make predictions
    predictions = plant_disease_pipeline(image)

    # Display disease predictions and generate LLM-based remedies
    col2.header("Disease Predictions 🌱")
    for p in predictions[:3]:
        disease = p['label'].lower()
        confidence = round(p['score'] * 100, 1)
        col2.subheader(f"**{disease.capitalize()}**: {confidence}%")

        # Query LLM for remedy suggestion
        prompt = f"Provide a remedy and care tips for a plant affected by {disease}."
        llm_response = llm_pipeline(prompt, max_length=50, num_return_sequences=1)
        
        remedy = llm_response[0]['generated_text'].strip()
        col2.write(f"**Suggested Remedy:** {remedy}")