new change

main.py

@@ -43,13 +43,9 @@ def generate(item: Item):
 
     formatted_prompt = format_prompt(f"{item.system_prompt}, {item.prompt}", item.history)
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-    output = ""
-
-    # for response in stream:
-    #     output += response.token.text
-    # return output
+    
     for response in stream:
-        yield response.token.text
+        yield response.token.text.encode("utf-8")
 
 @app.post("/generate/")
 async def generate_text(item: Item):