Add OpenLM LLM multi-provider

[r2d4]

OpenLM is a zero-dependency OpenAI-compatible LLM provider that can call different inference endpoints directly via HTTP. It implements the OpenAI Completion class so that it can be used as a drop-in replacement for the OpenAI API. This changeset utilizes BaseOpenAI for minimal added code.

[dev2049]

thanks @r2d4! could we add a simple example notebook (a la docs/modules/models/llms/integrations/openai.ipynb)

[r2d4]

Thanks for the feedback @dev2049

• Added documentation in the form of a notebook
• Added the dependency to extras so it isn't downloaded automatically

Let me know if there are any other changes!