Great LLMs are best at general tasks.<p>However, once you know what you want, you should finetune and switch to your finetuned LLM.<p>Logos Shift Cloud handles this automatically<p>All you need is to add this to your call:<p>```
@logos_shift(dataset="story")
def get_story(model, messages):
"""Generates a story"""
completion = expensiveLLM.create(model=model, messages=messages)
story_d = {'story': completion['choices'][0]['message']}
return story_d
```<p>This will automatically log all inputs and outputs to this function unobtrusively.
Once your model is ready, it will automatically A/B rollout your finetuned LLM.<p>No code changes necessary.
Enjoy faster and cheaper results.<p>No proxies so you don't add one more dependency.
The client code is open sourced at <a href="https://github.com/virevolai/logos-shift-client/">https://github.com/virevolai/logos-shift-client/</a> which includes the instrumentation, router for switching, and exactly how this works.<p>It's only 530 lines of code. No complex libraries.<p>If you do not want to use the Cloud solution, you can always just use Logos Shift for saving to local host and finetune yourself.<p>```
logos_shift = LogosShift(api_key=None, filename="api_calls.log")
```<p>Let us know how we can make this experience better.