add in CPU switch

app.py

@@ -10,6 +10,16 @@ from docquery.document import load_document
 # Chatbot model 
 #model = pipeline("document-question-answering", model="impira/layoutlm-document-qa")
 
+def construct_pipeline(task, model):
+    global PIPELINES
+    if model in PIPELINES:
+        return PIPELINES[model]
+
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    ret = pipeline(task=task, model=CHECKPOINTS[model], device=device)
+    PIPELINES[model] = ret
+    return ret
+    
 def run_pipeline(question, document):
     pipeline = construct_pipeline("document-question-answering", "impira/layoutlm-document-qa")
     return pipeline(question=question, **document.context, top_k=3)