Update: async methods were added to api

app.py

@@ -4,7 +4,7 @@ from pydantic import BaseModel
 from model import get_answer_from_llm
 
 
-class Prompt(BaseModel):
+class PromptType(BaseModel):
     prompt: str = ''
 
 
@@ -14,8 +14,8 @@ app = FastAPI(
 
 
 @app.post("/completion/")
-def get_answer(question: Prompt.prompt):
-    answer = get_answer_from_llm(question)
+async def get_answer(question: PromptType = None):
+    answer = await get_answer_from_llm(question=question.prompt)
     return answer
 
 

model.py

@@ -24,5 +24,5 @@ async def get_answer_from_llm(question: str = None):
         temperature=0.3,
         )
 
-    gen_text = await tokenizer.decode(gen_tokens[0])
+    gen_text = tokenizer.decode(gen_tokens[0])
     return gen_text