Update main.py

main.py

@@ -72,7 +72,7 @@ def generate_text(request: Request, input_data: InputData):
         max_new_tokens = min(max_new_tokens, 29500 - len(input_text))
         history = []
         generated_response = generate(input_text, history, temperature, max_new_tokens, top_p, repetition_penalty)
-        generated_response = generated_response.replace('"', '')
+        #generated_response = generated_response.replace('"', '')
         LoggaTesto("RISPOSTA", {"response": generated_response})
         return {"response": generated_response}
     else: 
@@ -82,7 +82,7 @@ def generate_text(request: Request, input_data: InputData):
             input_data.input = input_data.input + msgEliminaRisposteNonPertinenti
             input_data.systemRole = input_data.systemRole + msgEliminaRisposteNonPertinenti
         result_data = asyncio.run(GeneraTestoAsync("https://matteoscript-fastapi.hf.space/Genera", input_data))
-        result_data = result_data.replace('"', '')
+        #result_data = result_data.replace('"', '')
         LoggaTesto("RISPOSTA ASINCRONA", {"response": result_data})
         if input_data.EliminaRisposteNonPertinenti:
             result_data = [item for item in result_data if "NOTFOUND" not in item["response"]]
@@ -92,7 +92,7 @@ def generate_text(request: Request, input_data: InputData):
             input_data.systemStyle = 'Rispondi in ITALIANO'
             input_data.instruction =''
             result_data = asyncio.run(GeneraTestoAsync("https://matteoscript-fastapi.hf.space/Genera", input_data))
-            result_data = result_data.replace('"', '')
+            #result_data = result_data.replace('"', '')
             LoggaTesto("RISPOSTA ASINCRONA UNIFICATA", {"response": result_data})
         return {"response": result_data}