Update prompt

main.py

@@ -7,7 +7,7 @@ app = FastAPI()
 
 @app.get("/llm_inference")
 def read_root(
-        prompts: List[str],
+        prompt: str,
         model: str = "meta-llama/Llama-2-7b-hf",
         temperature: float = 0.,
         max_tokens: int = 1024) -> List:
@@ -15,6 +15,6 @@ def read_root(
 
     llm = LLM(model=model)
 
-    response = llm.generate(prompts, sampling_params)
+    response = llm.generate([prompt], sampling_params)
 
     return response