Use supplied headers

[stanfea]

litellm.headers is not thread safe we should be using the supplied headers anyway
need to use headers to turn on/off helicone caching for example and will want to run some requests with cache on and some with cache off

 ChatLiteLLM(
                model_name='gpt-4',
                max_tokens=7000,
                temperature=0.7,
                model_kwargs={'headers': headers}
            )),

[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 1, 2023 1:39pm

[ishaan-jaff]

lgtm ! thanks for the contribution @stanfea. Would love to give you a shoutout in our daily changelog. What's your Linkedin / Twitter ?

[stanfea]

lgtm ! thanks for the contribution @stanfea. Would love to give you a shoutout in our daily changelog. What's your Linkedin / Twitter ?

wow that was fast https://www.linkedin.com/in/stefanbacon/

cheers I'll send more fixes