Update app.py

app.py

@@ -29,9 +29,9 @@ def multimodal_rag(image, question):
     context = query_engine.query(question)
     
     # Step 2: Process with LLaVA
-    prompt = f"Context: {context}\n\nQuestion: {question}"
+    prompt = f"""Context: {context}
 
-Question: {question}"
+Question: {question}"""
     inputs = processor(prompt, image, return_tensors="pt").to(model.device)
     output = model.generate(**inputs, max_new_tokens=100)
     answer = processor.decode(output[0], skip_special_tokens=True)