Update handler.py

handler.py

@@ -33,15 +33,6 @@ class EndpointHandler():
         # os.environ["LANGCHAIN_API_KEY"] = 
 
         # Create LLM
-
-        # load the tokenizer and the quantized mistral model
-        # chat = HuggingFacePipeline.from_model_id(
-        #     model_id=path,
-        #     task="text-generation",
-        #     device=0,
-        #     pipeline_kwargs={"max_new_tokens": 1024},
-        # )
-
         model_id = path
         
         tokenizer = AutoTokenizer.from_pretrained(
@@ -157,7 +148,7 @@ class EndpointHandler():
         # This will be improved in the future
         # For now you need to save it yourself
 
-        self.memory.save_context(inputs, {"answer": result["answer"].content})
-        self.memory.load_memory_variables({})
+        # self.memory.save_context(inputs, {"answer": result["answer"].content})
+        # self.memory.load_memory_variables({})
         
-        return result
+        return result