Deprecate Vertex AI connector

Author: TaoChenOSU

python/README.md

@@ -4,7 +4,7 @@ Highlights
 - Flexible Agent Framework: build, orchestrate, and deploy AI agents and multi-agent systems
 - Multi-Agent Systems: Model workflows and collaboration between AI specialists
 - Plugin Ecosystem: Extend with Python, OpenAPI, Model Context Protocol (MCP), and more
-- LLM Support: OpenAI, Azure OpenAI, Hugging Face, Mistral, Vertex AI, ONNX, Ollama, NVIDIA NIM, and others
+- LLM Support: OpenAI, Azure OpenAI, Hugging Face, Mistral, Google AI, ONNX, Ollama, NVIDIA NIM, and others
 - Vector DB Support: Azure AI Search, Elasticsearch, Chroma, and more
 - Process Framework: Build structured business processes with workflow modeling
 - Multimodal: Text, vision, audio

python/samples/concepts/setup/ALL_SETTINGS.md

@@ -25,9 +25,9 @@
 | Google AI | [GoogleAIChatCompletion](../../../semantic_kernel/connectors/ai/google/google_ai/services/google_ai_chat_completion.py) | gemini_model_id, <br> api_key | GOOGLE_AI_GEMINI_MODEL_ID, <br> GOOGLE_AI_API_KEY | Yes, <br> Yes | [GoogleAISettings](../../../semantic_kernel/connectors/ai/google/google_ai/google_ai_settings.py) |
 |  | [GoogleAITextCompletion](../../../semantic_kernel/connectors/ai/google/google_ai/services/google_ai_text_completion.py) | gemini_model_id, <br> api_key | GOOGLE_AI_GEMINI_MODEL_ID, <br> GOOGLE_AI_API_KEY | Yes, <br> Yes |  |
 |  | [GoogleAITextEmbedding](../../../semantic_kernel/connectors/ai/google/google_ai/services/google_ai_text_embedding.py) | embedding_model_id, <br> api_key | GOOGLE_AI_EMBEDDING_MODEL_ID, <br> GOOGLE_AI_API_KEY | Yes, <br> Yes |  |
-| Vertex AI | [VertexAIChatCompletion](../../../semantic_kernel/connectors/ai/google/vertex_ai/services/vertex_ai_chat_completion.py) | project_id, <br> region, <br> gemini_model_id | VERTEX_AI_PROJECT_ID, <br> VERTEX_AI_REGION, <br> VERTEX_AI_GEMINI_MODEL_ID | Yes, <br> No, <br> Yes | [VertexAISettings](../../../semantic_kernel/connectors/ai/google/vertex_ai/vertex_ai_settings.py) |
-|  | [VertexAITextCompletion](../../../semantic_kernel/connectors/ai/google/google_ai/services/google_ai_text_completion.py) | project_id, <br> region, <br> gemini_model_id | VERTEX_AI_PROJECT_ID, <br> VERTEX_AI_REGION, <br> VERTEX_AI_GEMINI_MODEL_ID | Yes, <br> No, <br> Yes |  |
-|  | [VertexAITextEmbedding](../../../semantic_kernel/connectors/ai/google/google_ai/services/google_ai_text_embedding.py) | project_id, <br> region, <br> embedding_model_id | VERTEX_AI_PROJECT_ID, <br> VERTEX_AI_REGION, <br> VERTEX_AI_EMBEDDING_MODEL_ID | Yes, <br> No, <br> Yes |  |
+| Vertex AI | [GoogleAIChatCompletion](../../../semantic_kernel/connectors/ai/google/google_ai/services/google_ai_chat_completion.py) | project_id, <br> region, <br> gemini_model_id | GOOGLE_AI_CLOUD_PROJECT_ID, <br> GOOGLE_AI_CLOUD_REGION, <br> GOOGLE_AI_GEMINI_MODEL_ID, <br> GOOGLE_AI_USE_VERTEXAI | Yes, <br> No, <br> Yes, <br> Yes (must set to true) | [GoogleAISettings](../../../semantic_kernel/connectors/ai/google/google_ai/google_ai_settings.py) |
+|  | [GoogleAITextCompletion](../../../semantic_kernel/connectors/ai/google/google_ai/services/google_ai_text_completion.py) | project_id, <br> region, <br> gemini_model_id | GOOGLE_AI_CLOUD_PROJECT_ID, <br> GOOGLE_AI_CLOUD_REGION, <br> GOOGLE_AI_GEMINI_MODEL_ID, <br> GOOGLE_AI_USE_VERTEXAI | Yes, <br> No, <br> Yes, <br> Yes (must set to true) |  |
+|  | [GoogleAITextEmbedding](../../../semantic_kernel/connectors/ai/google/google_ai/services/google_ai_text_embedding.py) | project_id, <br> region, <br> embedding_model_id | GOOGLE_AI_CLOUD_PROJECT_ID, <br> GOOGLE_AI_CLOUD_REGION, <br> GOOGLE_AI_EMBEDDING_MODEL_ID, <br> GOOGLE_AI_USE_VERTEXAI | Yes, <br> No, <br> Yes, <br> Yes (must set to true) |  |
 | HuggingFace | [HuggingFaceTextCompletion](../../../semantic_kernel/connectors/ai/hugging_face/services/hf_text_completion.py) | ai_model_id | N/A | Yes | |
 |  | [HuggingFaceTextEmbedding](../../../semantic_kernel/connectors/ai/hugging_face/services/hf_text_embedding.py) | ai_model_id | N/A | Yes | |
 | NVIDIA NIM | [NvidiaChatCompletion](../../../semantic_kernel/connectors/ai/nvidia/services/nvidia_chat_completion.py) | ai_model_id, <br> api_key, <br> base_url | NVIDIA_CHAT_MODEL_ID, <br> NVIDIA_API_KEY, <br> NVIDIA_BASE_URL | Yes (default: meta/llama-3.1-8b-instruct), <br> Yes, <br> No | [NvidiaAISettings](../../../semantic_kernel/connectors/ai/nvidia/settings/nvidia_settings.py) |

python/samples/concepts/setup/chat_completion_services.py

@@ -249,10 +249,7 @@ def get_google_ai_chat_completion_service_and_request_settings() -> tuple[
     Please refer to the Semantic Kernel Python documentation for more information:
     https://learn.microsoft.com/en-us/python/api/semantic-kernel/semantic_kernel?view=semantic-kernel
     """
-    from semantic_kernel.connectors.ai.google.google_ai import (
-        GoogleAIChatCompletion,
-        GoogleAIChatPromptExecutionSettings,
-    )
+    from semantic_kernel.connectors.ai.google import GoogleAIChatCompletion, GoogleAIChatPromptExecutionSettings
 
     chat_service = GoogleAIChatCompletion(service_id=service_id)
     request_settings = GoogleAIChatPromptExecutionSettings(service_id=service_id)
@@ -356,13 +353,10 @@ def get_vertex_ai_chat_completion_service_and_request_settings() -> tuple[
     Please refer to the Semantic Kernel Python documentation for more information:
     https://learn.microsoft.com/en-us/python/api/semantic-kernel/semantic_kernel?view=semantic-kernel
     """
-    from semantic_kernel.connectors.ai.google.vertex_ai import (
-        VertexAIChatCompletion,
-        VertexAIChatPromptExecutionSettings,
-    )
+    from semantic_kernel.connectors.ai.google import GoogleAIChatCompletion, GoogleAIChatPromptExecutionSettings
 
-    chat_service = VertexAIChatCompletion(service_id=service_id)
-    request_settings = VertexAIChatPromptExecutionSettings(service_id=service_id)
+    chat_service = GoogleAIChatCompletion(service_id=service_id, use_vertexai=True)
+    request_settings = GoogleAIChatPromptExecutionSettings(service_id=service_id)
 
     return chat_service, request_settings
 

python/samples/concepts/setup/text_completion_services.py

@@ -262,12 +262,9 @@ def get_vertex_ai_text_completion_service_and_request_settings() -> tuple[
     Please refer to the Semantic Kernel Python documentation for more information:
     https://learn.microsoft.com/en-us/python/api/semantic-kernel/semantic_kernel?view=semantic-kernel
     """
-    from semantic_kernel.connectors.ai.google.vertex_ai import (
-        VertexAITextCompletion,
-        VertexAITextPromptExecutionSettings,
-    )
+    from semantic_kernel.connectors.ai.google import GoogleAITextCompletion, GoogleAITextPromptExecutionSettings
 
-    text_service = VertexAITextCompletion()
-    request_settings = VertexAITextPromptExecutionSettings()
+    text_service = GoogleAITextCompletion()
+    request_settings = GoogleAITextPromptExecutionSettings()
 
     return text_service, request_settings

python/samples/concepts/setup/text_embedding_services.py

@@ -296,13 +296,10 @@ def get_vertex_ai_text_embedding_service_and_request_settings() -> tuple[
     Please refer to the Semantic Kernel Python documentation for more information:
     https://learn.microsoft.com/en-us/python/api/semantic-kernel/semantic_kernel?view=semantic-kernel
     """
-    from semantic_kernel.connectors.ai.google.vertex_ai import (
-        VertexAIEmbeddingPromptExecutionSettings,
-        VertexAITextEmbedding,
-    )
+    from semantic_kernel.connectors.ai.google import GoogleAIEmbeddingPromptExecutionSettings, GoogleAITextEmbedding
 
-    embedding_service = VertexAITextEmbedding()
+    embedding_service = GoogleAITextEmbedding()
     # Note: not all models support specifying the dimensions or there may be constraints on the dimensions
-    request_settings = VertexAIEmbeddingPromptExecutionSettings(output_dimensionality=768)
+    request_settings = GoogleAIEmbeddingPromptExecutionSettings(output_dimensionality=768)
 
     return embedding_service, request_settings

python/semantic_kernel/connectors/ai/README.md

@@ -38,9 +38,9 @@ All base clients inherit from the [`AIServiceClientBase`](../../services/ai_serv
 | [Google AI](./google/README.md) | [`GoogleAIChatCompletion`](./google/google_ai/services/google_ai_chat_completion.py) |
 |           | [`GoogleAITextCompletion`](./google/google_ai/services/google_ai_text_completion.py) |
 |           | [`GoogleAITextEmbedding`](./google/google_ai/services/google_ai_text_embedding.py) |
-| [Vertex AI](./google/README.md) | [`VertexAIChatCompletion`](./google/vertex_ai/services/vertex_ai_chat_completion.py) |
-|           | [`VertexAITextCompletion`](./google/vertex_ai/services/vertex_ai_text_completion.py) |
-|           | [`VertexAITextEmbedding`](./google/vertex_ai/services/vertex_ai_text_embedding.py) |
+| [Vertex AI](./google/README.md) | [`GoogleAIChatCompletion`](./google/google_ai/services/google_ai_chat_completion.py) |
+|           | [`GoogleAITextCompletion`](./google/google_ai/services/google_ai_text_completion.py) |
+|           | [`GoogleAITextEmbedding`](./google/google_ai/services/google_ai_text_embedding.py) |
 | HuggingFace | [`HuggingFaceTextCompletion`](./hugging_face/services/hf_text_completion.py) |
 |             | [`HuggingFaceTextEmbedding`](./hugging_face/services/hf_text_embedding.py) |
 | Mistral AI | [`MistralAIChatCompletion`](./mistral_ai/services/mistral_ai_chat_completion.py) |

python/semantic_kernel/connectors/ai/google/README.md

@@ -14,7 +14,7 @@ Once you have an API key, you can start using Gemini models in SK using the `goo
 kernel = Kernel()
 kernel.add_service(
     GoogleAIChatCompletion(
-        gemini_model_id="gemini-1.5-flash",
+        gemini_model_id="gemini-2.5-flash",
         api_key="...",
     )
 )
@@ -39,9 +39,11 @@ Once you have your project and your environment is set up, you can start using G
 ```Python
 kernel = Kernel()
 kernel.add_service(
-    VertexAIChatCompletion(
+    GoogleAIChatCompletion(
         project_id="...",
-        gemini_model_id="gemini-1.5-flash",
+        region="...",
+        gemini_model_id="gemini-2.5-flash",
+        use_vertexai=True,
     )
 )
 ...

python/semantic_kernel/connectors/ai/google/__init__.py

@@ -0,0 +1,21 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+from semantic_kernel.connectors.ai.google.google_ai.google_ai_prompt_execution_settings import (
+    GoogleAIChatPromptExecutionSettings,
+    GoogleAIEmbeddingPromptExecutionSettings,
+    GoogleAIPromptExecutionSettings,
+    GoogleAITextPromptExecutionSettings,
+)
+from semantic_kernel.connectors.ai.google.google_ai.services.google_ai_chat_completion import GoogleAIChatCompletion
+from semantic_kernel.connectors.ai.google.google_ai.services.google_ai_text_completion import GoogleAITextCompletion
+from semantic_kernel.connectors.ai.google.google_ai.services.google_ai_text_embedding import GoogleAITextEmbedding
+
+__all__ = [
+    "GoogleAIChatCompletion",
+    "GoogleAIChatPromptExecutionSettings",
+    "GoogleAIEmbeddingPromptExecutionSettings",
+    "GoogleAIPromptExecutionSettings",
+    "GoogleAITextCompletion",
+    "GoogleAITextEmbedding",
+    "GoogleAITextPromptExecutionSettings",
+]

python/semantic_kernel/connectors/ai/google/google_ai/google_ai_settings.py

@@ -28,10 +28,19 @@ class GoogleAISettings(KernelBaseSettings):
     - api_key: SecretStr - The API key for the Google AI service deployment.
                 This value can be found in the Google AI service deployment.
                 (Env var GOOGLE_AI_API_KEY)
+    - cloud_project_id: str - The Google Cloud project ID.
+                (Env var GOOGLE_AI_CLOUD_PROJECT_ID)
+    - cloud_region: str - The Google Cloud region.
+                (Env var GOOGLE_AI_CLOUD_REGION)
+    - use_vertexai: bool - Whether to use Vertex AI. If true, cloud_project_id and cloud_region must be provided.
+                (Env var GOOGLE_AI_USE_VERTEXAI)
     """
 
     env_prefix: ClassVar[str] = "GOOGLE_AI_"
 
     gemini_model_id: str | None = None
     embedding_model_id: str | None = None
-    api_key: SecretStr
+    api_key: SecretStr | None = None
+    cloud_project_id: str | None = None
+    cloud_region: str | None = None
+    use_vertexai: bool = False

python/semantic_kernel/connectors/ai/google/google_ai/services/google_ai_base.py

@@ -3,6 +3,8 @@
 from abc import ABC
 from typing import ClassVar
 
+from google.genai import Client
+
 from semantic_kernel.connectors.ai.google.google_ai.google_ai_settings import GoogleAISettings
 from semantic_kernel.kernel_pydantic import KernelBaseModel
 
@@ -13,3 +15,5 @@ class GoogleAIBase(KernelBaseModel, ABC):
     MODEL_PROVIDER_NAME: ClassVar[str] = "googleai"
 
     service_settings: GoogleAISettings
+
+    client: Client | None = None