refactor(main.py): migrate vertex gemini calls to vertex_httpx

Completes migration to vertex_httpx

litellm/llms/vertex_httpx.py

@@ -50,6 +50,111 @@ from litellm.utils import CustomStreamWrapper, ModelResponse, Usage
 from .base import BaseLLM
 
 
+class VertexAIConfig:
+    """
+    Reference: https://cloud.google.com/vertex-ai/docs/generative-ai/chat/test-chat-prompts
+    Reference: https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference
+
+    The class `VertexAIConfig` provides configuration for the VertexAI's API interface. Below are the parameters:
+
+    - `temperature` (float): This controls the degree of randomness in token selection.
+
+    - `max_output_tokens` (integer): This sets the limitation for the maximum amount of token in the text output. In this case, the default value is 256.
+
+    - `top_p` (float): The tokens are selected from the most probable to the least probable until the sum of their probabilities equals the `top_p` value. Default is 0.95.
+
+    - `top_k` (integer): The value of `top_k` determines how many of the most probable tokens are considered in the selection. For example, a `top_k` of 1 means the selected token is the most probable among all tokens. The default value is 40.
+
+    - `response_mime_type` (str): The MIME type of the response. The default value is 'text/plain'.
+
+    - `candidate_count` (int): Number of generated responses to return.
+
+    - `stop_sequences` (List[str]): The set of character sequences (up to 5) that will stop output generation. If specified, the API will stop at the first appearance of a stop sequence. The stop sequence will not be included as part of the response.
+
+    - `frequency_penalty` (float): This parameter is used to penalize the model from repeating the same output. The default value is 0.0.
+
+    - `presence_penalty` (float): This parameter is used to penalize the model from generating the same output as the input. The default value is 0.0.
+
+    Note: Please make sure to modify the default parameters as required for your use case.
+    """
+
+    temperature: Optional[float] = None
+    max_output_tokens: Optional[int] = None
+    top_p: Optional[float] = None
+    top_k: Optional[int] = None
+    response_mime_type: Optional[str] = None
+    candidate_count: Optional[int] = None
+    stop_sequences: Optional[list] = None
+    frequency_penalty: Optional[float] = None
+    presence_penalty: Optional[float] = None
+
+    def __init__(
+        self,
+        temperature: Optional[float] = None,
+        max_output_tokens: Optional[int] = None,
+        top_p: Optional[float] = None,
+        top_k: Optional[int] = None,
+        response_mime_type: Optional[str] = None,
+        candidate_count: Optional[int] = None,
+        stop_sequences: Optional[list] = None,
+        frequency_penalty: Optional[float] = None,
+        presence_penalty: Optional[float] = None,
+    ) -> None:
+        locals_ = locals()
+        for key, value in locals_.items():
+            if key != "self" and value is not None:
+                setattr(self.__class__, key, value)
+
+    @classmethod
+    def get_config(cls):
+        return {
+            k: v
+            for k, v in cls.__dict__.items()
+            if not k.startswith("__")
+            and not isinstance(
+                v,
+                (
+                    types.FunctionType,
+                    types.BuiltinFunctionType,
+                    classmethod,
+                    staticmethod,
+                ),
+            )
+            and v is not None
+        }
+
+    def get_mapped_special_auth_params(self) -> dict:
+        """
+        Common auth params across bedrock/vertex_ai/azure/watsonx
+        """
+        return {"project": "vertex_project", "region_name": "vertex_location"}
+
+    def map_special_auth_params(self, non_default_params: dict, optional_params: dict):
+        mapped_params = self.get_mapped_special_auth_params()
+
+        for param, value in non_default_params.items():
+            if param in mapped_params:
+                optional_params[mapped_params[param]] = value
+        return optional_params
+
+    def get_eu_regions(self) -> List[str]:
+        """
+        Source: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations#available-regions
+        """
+        return [
+            "europe-central2",
+            "europe-north1",
+            "europe-southwest1",
+            "europe-west1",
+            "europe-west2",
+            "europe-west3",
+            "europe-west4",
+            "europe-west6",
+            "europe-west8",
+            "europe-west9",
+        ]
+
+
 class GoogleAIStudioGeminiConfig:  # key diff from VertexAI - 'frequency_penalty' and 'presence_penalty' not supported
     """
     Reference: https://ai.google.dev/api/rest/v1beta/GenerationConfig
@@ -326,6 +431,7 @@ class VertexGeminiConfig:
             "stop",
             "frequency_penalty",
             "presence_penalty",
+            "extra_headers",
         ]
 
     def map_tool_choice_values(
@@ -691,7 +797,9 @@ class VertexLLM(BaseLLM):
                     )
                     tools.append(_tool_response_chunk)
 
-                chat_completion_message["content"] = content_str
+                chat_completion_message["content"] = (
+                    content_str if len(content_str) > 0 else None
+                )
                 chat_completion_message["tool_calls"] = tools
 
                 choice = litellm.Choices(