Update app.py

app.py

@@ -110,13 +110,22 @@ def answer_question_from_document(file, question):
     return response[0]["generated_text"]
 
 def answer_question_from_image(image, question):
-    print("🖼️ Generating caption for image...")
-    caption = image_captioning_pipeline(image)[0]['generated_text']
-    
-    print("🤖 Answering question based on caption...")
-    response = doc_qa_pipeline(f"Question: {question}\nContext: {caption}")
-    
-    return response[0]["generated_text"]
+    try:
+        print("🖼️ Converting image for processing...")
+        if isinstance(image, np.ndarray):  # If it's a NumPy array from Gradio
+            image = Image.fromarray(image)  # Convert to PIL Image
+
+        print("🖼️ Generating caption for image...")
+        caption = image_captioning_pipeline(image)[0]['generated_text']
+
+        print("🤖 Answering question based on caption...")
+        response = doc_qa_pipeline(f"Question: {question}\nContext: {caption}")
+
+        return response[0]["generated_text"]
+
+    except Exception as e:
+        return f"❌ Error processing image: {str(e)}"
+
 
 # Gradio UI for Document & Image QA
 doc_interface = gr.Interface(