Update main.py

main.py

@@ -20,7 +20,7 @@ def format_prompt(message, history):
 
 
 @app.post("/api/v1/generate_text")
-async def generate_text(request: Request, prompt: str = Body()):
+def generate_text(request: Request, prompt: str = Body()):
     history = []  # You might need to handle this based on your actual usage
     print(f"prompt + {prompt}")
     temperature = request.headers.get("temperature", 0.9)
@@ -40,16 +40,16 @@ async def generate_text(request: Request, prompt: str = Body()):
         repetition_penalty=repetition_penalty,
         do_sample=True,
         seed=random.randint(0, 10**7),
-        stream=False,
+        stream=True,
         details=True, 
-        return_full_text=True
+        return_full_text=False
     )
-    # output = ""
+    output = ""
 
-    # for response in stream:
-    #     output += response.token.text
-    #     yield output
-    #     print(f"output + {output}")
-    # return output
+    for response in stream:
+        output += response.token.text
+        yield output
+        print(f"output + {output}")
+    return output
 
-    return stream
+    # return stream