Update app.py

app.py

@@ -1,74 +1,36 @@
-import os
 import streamlit as st
-from transformers import pipeline, AutoImageProcessor, AutoModelForImageClassification
 from PIL import Image
+from transformers import pipeline
+import os
 
-def load_pipeline():
-    """Load the Hugging Face pipeline for image classification."""
-    try:
-        return pipeline("image-classification", model="dima806/pneumonia_chest_xray_image_detection")
-    except Exception as e:
-        st.error(f"Error loading pipeline: {e}")
-        return None
-
-def classify_image_with_pipeline(pipe, image):
-    """Classify an image using the pipeline."""
-    try:
-        results = pipe(image)
-        return results
-    except Exception as e:
-        st.error(f"Error classifying image: {e}")
-        return None
+# Check if Groq API key is set and load it if available
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+if GROQ_API_KEY:
+    from groq import Groq
+    client = Groq(api_key=GROQ_API_KEY)
+    # Use Groq API here if you want it for predictions or related tasks
 
-# Streamlit App
+# Streamlit setup
 st.title("Pneumonia Chest X-ray Image Detection")
-st.markdown(
-    """
-    This app detects signs of pneumonia in chest X-ray images using a pre-trained Hugging Face model.
-    """
-)
-
-# File uploader
-uploaded_file = st.file_uploader("Upload a chest X-ray image", type=["jpg", "jpeg", "png"])
 
-if uploaded_file:
-    image = Image.open(uploaded_file)
-    st.image(image, caption="Uploaded Chest X-ray", use_column_width=True)
+# Upload image
+uploaded_image = st.file_uploader("Choose a chest X-ray image...", type=["jpg", "jpeg", "png"])
 
-    # Load the model pipeline
-    pipe = load_pipeline()
-
-    if pipe:
-        st.write("Classifying the image...")
-        results = classify_image_with_pipeline(pipe, image)
-
-        if results:
-            st.write("### Classification Results:")
-            for result in results:
-                st.write(f"**Label:** {result['label']} | **Score:** {result['score']:.4f}")
-
-# Optional: Add Groq API integration if applicable
-if os.getenv("GROQ_API_KEY"):
-    from groq import Groq
+if uploaded_image is not None:
+    # Display the image
+    image = Image.open(uploaded_image)
+    st.image(image, caption="Uploaded X-ray Image", use_column_width=True)
 
-    client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
+    # Load the Hugging Face model using the pipeline
+    pipe = pipeline("image-classification", model="dima806/pneumonia_chest_xray_image_detection")
 
-    st.sidebar.markdown("### Groq API Integration")
-    question = st.sidebar.text_input("Ask a question about pneumonia or X-ray diagnosis:")
+    # Run prediction
+    with st.spinner("Classifying..."):
+        prediction = pipe(image)
 
-    if question:
-        try:
-            chat_completion = client.chat.completions.create(
-                messages=[
-                    {
-                        "role": "user",
-                        "content": question,
-                    }
-                ],
-                model="llama-3.3-70b-versatile",
-            )
+    # Display results
+    st.write(f"Prediction: {prediction[0]['label']}")
+    st.write(f"Confidence: {prediction[0]['score']:.4f}")
 
-            st.sidebar.write("**Groq API Response:**")
-            st.sidebar.write(chat_completion.choices[0].message.content)
-        except Exception as e:
-            st.sidebar.error(f"Error using Groq API: {e}")
+else:
+    st.warning("Please upload a chest X-ray image to begin detection.")