add support for Azure, OpenAI, Palm, Anthropic, Cohere Models - using litellm

automata/llm/providers/openai_llm.py

@@ -3,6 +3,7 @@
 
 import numpy as np
 import openai
+from litellm import completion
 import tiktoken
 from termcolor import colored
 
@@ -291,15 +292,15 @@ def get_next_assistant_completion(self) -> OpenAIChatMessage:
             f"Approximately {self.approximate_tokens_consumed} tokens were consumed prior to completion generation."
         )
         if functions:
-            response = openai.ChatCompletion.create(
+            response = completion(
                 model=self.model,
                 messages=self.conversation.get_messages_for_next_completion(),
                 functions=functions,
                 function_call="auto",  # auto is default, but we'll be explicit
                 stream=self.stream,
             )
         else:
-            response = openai.ChatCompletion.create(
+            response = completion(
                 model=self.model,
                 messages=self.conversation.get_messages_for_next_completion(),
                 stream=self.stream,