Create app.py

app.py

@@ -0,0 +1,102 @@
+import gradio as gr
+import numpy as np
+import tensorflow as tf
+from tensorflow.keras.preprocessing import image
+from huggingface_hub import InferenceClient
+
+# Load the trained disease detection model
+model = tf.keras.models.load_model("Tomato_Leaf_Disease_Model.h5")
+
+# Disease categories
+class_labels = [
+    "Tomato Bacterial Spot",
+    "Tomato Early Blight",
+    "Tomato Late Blight",
+    "Tomato Mosaic Virus",
+    "Tomato Yellow Leaf Curl Virus"
+]
+
+# AI Assistant (Zephyr-7B)
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+# Image preprocessing
+def preprocess(img):
+    img = img.resize((224, 224))  # Resize for the model
+    img = image.img_to_array(img) / 255.0  # Normalize
+    img = np.expand_dims(img, axis=0)  # Add batch dimension
+    return img
+
+# Disease detection function
+def detect_disease(img):
+    img = preprocess(img)
+    prediction = model.predict(img)
+    class_idx = np.argmax(prediction)  # Class with highest probability
+    confidence = np.max(prediction) * 100  # Confidence score
+    disease_name = class_labels[class_idx]
+    return f"{disease_name} (Confidence: {confidence:.2f}%)", disease_name
+
+# AI Assistant function
+def get_disease_advice(disease_name):
+    prompt = f"A farmer detected {disease_name} on their tomato plant. How should they manage it?"
+    
+    messages = [{"role": "system", "content": "You are an expert agricultural advisor."}]
+    messages.append({"role": "user", "content": prompt})
+
+    response = ""
+    for message in client.chat_completion(messages, max_tokens=512, stream=True, temperature=0.7, top_p=0.95):
+        token = message.choices[0].delta.content
+        response += token
+    
+    return response
+
+# Combined function
+def diagnose_and_advise(image):
+    detected_disease, disease_name = detect_disease(image)
+    
+    if "Healthy" in detected_disease:
+        return detected_disease, "Your tomato plant looks healthy! 😊"
+    
+    advice = get_disease_advice(disease_name)
+    return detected_disease, advice
+
+# AI Chatbot for General Questions
+def chatbot_response(user_message, history, system_message, max_tokens, temperature, top_p):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": user_message})
+
+    response = ""
+    for message in client.chat_completion(messages, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p):
+        token = message.choices[0].delta.content
+        response += token
+
+    return response
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("# 🍅 Tomato Sentry: Disease Detection & AI Assistant")
+    
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("### 📸 Disease Detection")
+            image_input = gr.Image(type="pil", label="Upload a Tomato Leaf Image")
+            detect_button = gr.Button("Detect Disease")
+            disease_output = gr.Textbox(label="Detected Disease & Confidence")
+            advice_output = gr.Textbox(label="AI Farming Advice")
+        
+        with gr.Column():
+            gr.Markdown("### 🤖 AI Chatbot for Farmers")
+            user_input = gr.Textbox(label="Ask a farming question")
+            chat_button = gr.Button("Get Advice")
+            chat_output = gr.Textbox(label="AI Response")
+    
+    detect_button.click(diagnose_and_advise, inputs=image_input, outputs=[disease_output, advice_output])
+    chat_button.click(chatbot_response, inputs=[user_input, [], "You are a farming expert.", 512, 0.7, 0.95], outputs=chat_output)
+
+demo.launch()