Update app.py

app.py

@@ -34,7 +34,7 @@ if hasattr(transformers_import_utils, "is_cuda_stream_capturing"):
 
 # 1. Initialize LLM
 print("Loading BioMistral LLM...")
-llm = pipeline('text-generation', model='BioMistral/BioMistral-7B', torch_dtype=torch.bfloat16, device_map="auto")
+llm = pipeline('text-generation', model='BioMistral/BioMistral-7B', torch_dtype=torch.bfloat16, device_map="cuda")
 
 # 2. Load Datasets
 print("Loading datasets...")
@@ -132,9 +132,9 @@ def respond_to_query(user_query: str) -> str:
 # 9. Gradio Web Interface
 demo = gr.Interface(
     fn=respond_to_query,
-    inputs=gr.Textbox(lines=2, placeholder="e.g., What is necrosis? or What is cholera?"),
+    inputs=gr.Textbox(lines=2, label="User Question", placeholder="e.g., What is necrosis? or What is cholera?"),
     outputs=gr.Textbox(label="BioMistral RAG Response", lines=4),
-    title="🩺 Medical Terminology RAG Assistant",
+    title="Medical Terminology RAG Assistant",
     description="Ask a medical question to retrieve context from Med-EASi + custom terms and generate simplified explanations.",
     examples=[
         ["What causes necrosis?"],