Update app.py

app.py

@@ -1,107 +1,74 @@
-import gradio as gr
-from tensorflow.keras.models import load_model
-import numpy as np
-from PIL import Image
+import os
+import streamlit as st
+from groq import Groq
 
-# Load model
-model = load_model('xray_image_classifier_model.keras')
+# ✅ Fix TensorFlow CPU warnings
+os.environ["TF_ENABLE_ONEDNN_OPTS"] = "0"
 
-# Define solutions
-solutions = {
-    "Pneumonia": "Consult a doctor immediately. Follow prescribed antibiotics if given, rest well, and stay hydrated.",
-    "Normal": "Your X-ray appears normal. However, if you experience symptoms, consult a doctor for further evaluation."
-}
-
-# Prediction function
-def predict(image):
-    img = image.resize((150, 150))
-    img_array = np.array(img) / 255.0
-    img_array = np.expand_dims(img_array, axis=0)
-    
-    prediction = model.predict(img_array)
-    predicted_class = "Pneumonia" if prediction > 0.5 else "Normal"
-    
-    # Get the corresponding solution
-    solution = solutions.get(predicted_class, "No specific advice available.")
-    
-    return predicted_class, solution
-
-# CSS Styling
-css = """
-    .gradio-container {
-        background-color: #f5f5f5;
-        font-family: Arial, sans-serif;
-    }
-    
-    .gr-button {
-        background-color:#007bff;
-        color: white; 
-        border: none;
-        border-radius: 5px;
-        font-size: 16px;
-        padding: 10px 20px;
-        cursor: pointer;
-        transition: background-color 0.3s ease;
-    }
-
-    .gr-button:hover {
-        background-color: #0056b3;
-    }
-
-    .gr-textbox, .gr-image {
-        border: 2px dashed #007bff;
-        padding: 20px;
-        border-radius: 10px;
-        background-color: #ffffff;
-    }
+# ✅ Set up the Groq API Key
+GROQ_API_KEY = "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"
+os.environ["GROQ_API_KEY"] = GROQ_API_KEY
 
-    .gr-box-text {
-        color: #007bff;
-        font-size: 22px;
-        font-weight: bold;
-        text-align: center;
-    }
+# ✅ Initialize the Groq client (Fixed 'proxies' issue)
+client = Groq(api_key=GROQ_API_KEY)
 
-    h1 {
-        font-size: 36px;
-        color: #007bff;
-        text-align: center;
-    }
+# ✅ Streamlit UI setup
+st.set_page_config(page_title="AI Disease Detection Assistant", page_icon="🩺", layout="wide")
+st.title("🩺 AI Disease Detection Chatbot")
+st.write("Hello! I'm your AI assistant for disease-related queries. Ask me about symptoms, treatments, or general health advice.")
 
-    p {
-        font-size: 20px;
-        color: #333;
-        text-align: center;
-    }
-"""
+# ✅ Sidebar settings
+st.sidebar.header("⚙️ Settings")
+chat_theme = st.sidebar.radio("Choose a theme:", ["Light", "Dark", "Blue", "Green"])
 
-# Description
-description = """
-**Automated Pneumonia Detection via Chest X-ray Classification**
+# ✅ Apply themes
+themes = {
+    "Dark": "#1e1e1e",
+    "Blue": "#e3f2fd",
+    "Green": "#e8f5e9",
+    "Light": "#ffffff"
+}
+st.markdown(f"""
+    <style>
+        body {{ background-color: {themes[chat_theme]}; color: black; }}
+        .stButton>button {{ background-color: #4CAF50; color: white; }}
+        .chat-bubble {{ background-color: #f1f1f1; border-radius: 10px; padding: 10px; }}
+    </style>
+""", unsafe_allow_html=True)
 
-This model leverages deep learning techniques to classify chest X-ray images as either 'Pneumonia' or 'Normal.' By utilizing the InceptionV3 architecture for transfer learning, combined with data preprocessing and augmentation, the model aims to deliver powerful performance in medical image analysis. It enhances the automation of diagnostic processes, aiding in the detection of pneumonia with high accuracy.
+# ✅ Session state for chat history
+if 'conversation_history' not in st.session_state:
+    st.session_state.conversation_history = []
 
-**Technologies Employed:**
-- TensorFlow & Keras for model development
-- InceptionV3 for transfer learning
-- Numpy, Pandas, and Matplotlib for data handling and visualization
-- Flask and Gradio for deployment and user interaction
-"""
+# ✅ Function to generate AI response
+def generate_chatbot_response(user_message):
+    # Custom responses
+    if "who created you" in user_message.lower():
+        return "I was created by Abdel Basit. 😊"
 
-# Gradio UI
-with gr.Blocks(css=css) as interface:
-    gr.Markdown("<h1>Automated Pneumonia Detection via Chest X-ray Classification</h1>")
-    gr.Markdown("<p>Submit a chest X-ray image below.</p>")
+    # AI model response
+    prompt = f"You are a medical AI assistant. The user asks: {user_message}. Provide a detailed, accurate medical response."
     
-    with gr.Row():
-        image_input = gr.Image(label="Drop Image Here", type="pil", elem_classes=["gr-image", "gr-box-text"])
-        output_prediction = gr.Textbox(label="Model Analysis Output", elem_classes=["gr-textbox", "gr-box-text"])
-        output_solution = gr.Textbox(label="Recommended Solution", elem_classes=["gr-textbox", "gr-box-text"])
+    try:
+        chat_completion = client.chat.completions.create(
+            messages=[{"role": "user", "content": prompt}],
+            model="llama3-8b-8192"
+        )
+        return chat_completion.choices[0].message.content
+    except Exception as e:
+        return f"⚠️ Error: {str(e)}"
 
-    submit_btn = gr.Button("Initiate Diagnostic Analysis", elem_classes=["gr-button"])
-    submit_btn.click(fn=predict, inputs=image_input, outputs=[output_prediction, output_solution])
-    
-    gr.Markdown(description)
+# ✅ User chat input
+st.markdown("### 💬 Chat with me")
+user_input = st.chat_input("Ask me a health-related question:")
+
+if user_input:
+    chatbot_response = generate_chatbot_response(user_input)
+    st.session_state.conversation_history.append(("User: " + user_input, "Chatbot: " + chatbot_response))
 
-# Launch the app
-interface.launch()
+# ✅ Display chat history
+st.markdown("---")
+st.markdown("### 🗨️ Chat History")
+for question, answer in st.session_state.conversation_history:
+    st.write(f"<div class='chat-bubble'><b>{question}</b></div>", unsafe_allow_html=True)
+    st.write(f"<div class='chat-bubble'>{answer}</div>", unsafe_allow_html=True)