Update inference_server.py

inference_server.py

@@ -23,7 +23,7 @@ def predict(input_text: str):
     # Use the BERT LM to generate for all input strings
     with torch.no_grad():
         outputs = model(input_ids)
-        logits = output[0]
+        logits = outputs[0]
 
     # Find the input string that is most similar to the new input string, according to the BERT LM
     similarity_scores = torch.nn.functional.csine_similarity(logits[:, 0, :],