add v1/completions

main.py

@@ -42,6 +42,11 @@ async def index():
 class ChatCompletionRequest(BaseModel):
     prompt: str
 
+@app.post("/v1/completions")
+async def completion(request: ChatCompletionRequest, response_mode=None):
+    response = llm(request.prompt)
+    return response
+
 @app.post("/v1/chat/completions")
 async def chat(request: ChatCompletionRequest, response_mode=None):
     tokens = llm.tokenize(request.prompt)