Facing issue running Open AI compatible server

Nobody has claimed this yet.

I am trying to create Open AI compatible API

Question. Should the controller and API server have the same port?

I tried the same port but also different ports.

My chat model is running successfully, but I am not seeing any models in the API call. Is this a know issue? Or am I missing anything?

// 20230705191047
// http://localhost:8003/v1/models

{
"object": "list",
"data": [

]
}

The below steps are the ones I ran.

First, launch the controller

python3 -m fastchat.serve.controller
Then, launch the model worker(s)

python3 -m fastchat.serve.model_worker --model-path lmsys/vicuna-7b-v1.3
Finally, launch the RESTful API server

python3 -m fastchat.serve.openai_api_server --host localhost --port 8000

Start with the documented entry points fastchat.serve.controller, fastchat.serve.model_worker, and fastchat.serve.openai_api_server, then reproduce the commands and query /v1/models. Check how the API server discovers registered workers and determine whether the model appears in the returned list when the controller and server ports are configured correctly.

Written by the indexing model from the issue text.