Adding function calling to AnyscaleLLM

[kylehh]

Problem

1. Enable function calling to Anyscale LLM
2. Add default {'type'='array'} for FunctionArrayProperty

Solution

Describe the approach you took. Link to any relevant bugs, issues, docs, or other resources.

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update
• Infrastructure change (CI configs, etc)
• Non-code change (docs, etc)
• None of the above: (explain here)

Test Plan

Describe specific steps for validating this change.

[igiloh-pinecone]

@kylehh All in all LGTM. Please see a few comments

[igiloh-pinecone]

@kylehh we've changed the format of test_openai.py in a manner where it parameterizes all LLM classes that inherit from OpenAILLM (like AnyscaleLLM), and runs the same test cases for all of these classes.
This way - we don't need a dedicated test_anyscale.py file which simply duplicates the entire test cases

[igiloh-pinecone]

LGTM!

I've changed the testing scheme and made AnyscalseLLM another parameterized case in test_openai.py