DOC: Exceptions that can be raised by the invocation of LLM models are not described

[Mark531]

URL

https://python.langchain.com/api_reference/core/language_models/langchain_core.language_models.llms.BaseLLM.html

Checklist

• I added a very descriptive title to this issue.
• I included a link to the documentation page I am referring to (if applicable).

Issue with current documentation:

The invoke() or ainvoke() methods of BaseLLMs may raise exceptions, yet the latter are not described in a "Raises" section. Some specific implementations like OpenAI's models should have their own exceptions documented too (like RateLimitError I guess).

The problem is that it's currently difficult to write a code that properly handles all possible exceptions without knowing them.

Idea or request for content:

On top on the "Return type" section, a "Raises" section should be added for invoke() and ainvoke() and maybe other methods.