Update main.py

main.py

@@ -23,7 +23,7 @@ app = FastAPI()
 @app.post("/generate_response")
 async def generate_response(item: Validation):
     # Construct the complete prompt using the given system and user prompts in the required format
-    prompt = f"<|user|>\n{item.system_prompt}\n<|end|>\n<|user|>\n{item.user_prompt}\n<|end|>\n<|assistant|>"
+    prompt = f"<|user|>\n{item.system_prompt}\n {item.user_prompt}\n<|end|>\n<|assistant|>"
 
     # Call the Llama model to generate a response
     output = llm(prompt, max_tokens=item.max_tokens, temperature=item.temperature, echo=True)