fix: fix bug for the case --model is not specified

[clalanliu]

When you following instruction to use a config.yaml file, you will not specify --model when you launch the server, and you will get error even with config file detected:

CONFIG FILE DETECTED
data: {'model': 'huggingface/some_model', 'messages': [{'role': 'user', 'content': 'How are you?'}], 'max_tokens': 150}
Traceback (most recent call last):
  File "/app/main.py", line 110, in chat_completion
    server_settings.get("completion_model", None) # server default
AttributeError: 'NoneType' object has no attribute 'get'

Not sure whether we should always specify server_settings in config.yaml.

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
litellm	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Nov 8, 2023 4:03pm

[ishaan-jaff]

lgtm

[ishaan-jaff]

thanks for the contribution - would love to give you a shoutout on our daily changelog what's your linkedin / twitter @clalanliu ?

[clalanliu]

thanks for the contribution - would love to give you a shoutout on our daily changelog what's your linkedin / twitter @clalanliu ?

This is my linkedin.