Add application file

app.py

@@ -0,0 +1,40 @@
+import gradio as gr
+from transformers import pipeline
+from PIL import Image
+import requests
+
+# Load pre-trained model
+classifier = pipeline("image-classification", model="Anwarkh1/Skin_Cancer-Image_Classification")
+
+def classify_image(image):
+    results = classifier(image)
+    label = results[0]['label']
+    confidence = results[0]['score']
+    explanation = f"The model predicts **{label}** with a confidence of {confidence:.2%}."
+    return label, confidence, explanation
+
+def fetch_research():
+    url = "https://api.semanticscholar.org/graph/v1/paper/search"
+    params = {"query": "cancer research", "fields": "title,abstract,url", "limit": 5}
+    response = requests.get(url, params=params)
+    papers = response.json().get("data", [])
+    return "\n".join([f"{paper['title']}: {paper['url']}" for paper in papers])
+
+# Interface
+with gr.Blocks() as demo:
+    gr.Markdown("# AI-Powered Universal Cancer Detection and Research Assistant 🌍🩺")
+    
+    with gr.Tab("Cancer Detection"):
+        image = gr.Image(label="Upload Cancer Image")
+        label = gr.Textbox(label="Predicted Label")
+        confidence = gr.Slider(label="Confidence")
+        explanation = gr.Textbox(label="Explanation")
+        detect_btn = gr.Button("Classify")
+        detect_btn.click(classify_image, inputs=[image], outputs=[label, confidence, explanation])
+    
+    with gr.Tab("Research Papers"):
+        fetch_btn = gr.Button("Fetch Research Papers")
+        papers = gr.Textbox(label="Latest Research Papers", lines=5)
+        fetch_btn.click(fetch_research, inputs=[], outputs=papers)
+    
+demo.launch()