feat(vertex_httpx.py): Moving to call vertex ai via httpx (instead of their sdk). Allows us to support all their api updates.

litellm/main.py

@@ -1893,6 +1893,7 @@ def completion(
                 or optional_params.pop("vertex_ai_credentials", None)
                 or get_secret("VERTEXAI_CREDENTIALS")
             )
+
             new_params = deepcopy(optional_params)
             if "claude-3" in model:
                 model_response = vertex_ai_anthropic.completion(
@@ -1910,6 +1911,26 @@ def completion(
                     logging_obj=logging,
                     acompletion=acompletion,
                 )
+            elif (
+                model in litellm.vertex_language_models
+                or model in litellm.vertex_vision_models
+            ):
+                model_response = vertex_chat_completion.completion(  # type: ignore
+                    model=model,
+                    messages=messages,
+                    model_response=model_response,
+                    print_verbose=print_verbose,
+                    optional_params=new_params,
+                    litellm_params=litellm_params,
+                    logger_fn=logger_fn,
+                    encoding=encoding,
+                    vertex_location=vertex_ai_location,
+                    vertex_project=vertex_ai_project,
+                    vertex_credentials=vertex_credentials,
+                    logging_obj=logging,
+                    acompletion=acompletion,
+                    timeout=timeout,
+                )
             else:
                 model_response = vertex_ai.completion(
                     model=model,