fix(litellm): call LiteLLMCallable instead of OpenAIChatCallable when…

[kaushikb11]

… llm_api is not passed

• Update get_llm_ask to check for LiteLLM first
• Allow LiteLLM usage without explicitly passing litellm.completion
• Maintain compatibility with other LLM providers
• Update relevant tests to reflect new LiteLLM usage

Script to reproduce the issue

from guardrails import Guard
import os
os.environ["AZURE_API_KEY"] = "" # "my-azure-api-key"
os.environ["AZURE_API_BASE"] = "" # "https://example-endpoint.openai.azure.com/"
os.environ["AZURE_API_VERSION"] = "" # "2023-05-15"

guard = Guard()

result = guard(
    model="azure/<your_deployment_name>",
    messages=[{"role":"user", "content":"How many moons does Jupiter have?"}],
)

print(f"{result.validated_output}")

[dtam]

ok closing this branch which is the right one

[dtam]

#958