Add VertexAI model provider (#1417)

* feat: add vertexai provider

* feat: add help documentation for Vertex AI provider authentication requirements

---------

Co-authored-by: hungnp <[email protected]>

Author: anthonyhungnguyen

packages/jupyter-ai-magics/jupyter_ai_magics/partner_providers/vertexai.py

@@ -0,0 +1,38 @@
+from jupyter_ai_magics.base_provider import BaseProvider
+from langchain_google_vertexai import VertexAI, VertexAIEmbeddings
+
+
+class VertexAIProvider(BaseProvider, VertexAI):
+    id = "vertexai"
+    name = "Vertex AI"
+    models = [
+        "gemini-2.5-pro",
+        "gemini-2.5-flash",
+    ]
+    model_id_key = "model"
+    auth_strategy = None
+    pypi_package_deps = ["langchain-google-vertexai"]
+    help = (
+        "To use Vertex AI Generative AI you must have the langchain-google-vertexai Python package installed and either:\n\n"
+        "- Have credentials configured for your environment (gcloud, workload identity, etc...)\n"
+        "- Store the path to a service account JSON file as the GOOGLE_APPLICATION_CREDENTIALS environment variable\n\n"
+        "This codebase uses the google.auth library which first looks for the application credentials variable mentioned above, and then looks for system-level auth. "
+        "For more information, see the [Vertex AI authentication documentation](https://python.langchain.com/docs/integrations/llms/google_vertex_ai_palm/)."
+    )
+
+class VertexAIEmbeddingsProvider(BaseProvider, VertexAIEmbeddings):
+    id = "vertexai"
+    name = "Vertex AI"
+    models = [
+        "text-embedding-004",
+    ]
+    model_id_key = "model"
+    auth_strategy = None
+    pypi_package_deps = ["langchain-google-vertexai"]
+    help = (
+        "To use Vertex AI Generative AI you must have the langchain-google-vertexai Python package installed and either:\n\n"
+        "- Have credentials configured for your environment (gcloud, workload identity, etc...)\n"
+        "- Store the path to a service account JSON file as the GOOGLE_APPLICATION_CREDENTIALS environment variable\n\n"
+        "This codebase uses the google.auth library which first looks for the application credentials variable mentioned above, and then looks for system-level auth. "
+        "For more information, see the [Vertex AI authentication documentation](https://python.langchain.com/docs/integrations/llms/google_vertex_ai_palm/)."
+    )

packages/jupyter-ai-magics/pyproject.toml

@@ -30,6 +30,7 @@ dependencies = [
     "pydantic>=2.10.0,<3",
     "click>=8.1.0,<9",
     "jsonpath-ng>=1.5.3,<2",
+    "langchain-google-vertexai",
 ]
 
 [project.optional-dependencies]
@@ -63,6 +64,7 @@ all = [
     "boto3",
     "qianfan",
     "together",
+    "langchain-google-vertexai",
 ]
 
 [project.entry-points."jupyter_ai.model_providers"]
@@ -86,6 +88,7 @@ together-ai = "jupyter_ai_magics:TogetherAIProvider"
 gemini = "jupyter_ai_magics.partner_providers.gemini:GeminiProvider"
 mistralai = "jupyter_ai_magics.partner_providers.mistralai:MistralAIProvider"
 openrouter = "jupyter_ai_magics.partner_providers.openrouter:OpenRouterProvider"
+vertexai = "jupyter_ai_magics.partner_providers.vertexai:VertexAIProvider"
 
 [project.entry-points."jupyter_ai.embeddings_model_providers"]
 azure = "jupyter_ai_magics.partner_providers.openai:AzureOpenAIEmbeddingsProvider"
@@ -98,6 +101,7 @@ ollama = "jupyter_ai_magics.partner_providers.ollama:OllamaEmbeddingsProvider"
 openai = "jupyter_ai_magics.partner_providers.openai:OpenAIEmbeddingsProvider"
 openai-custom = "jupyter_ai_magics.partner_providers.openai:OpenAIEmbeddingsCustomProvider"
 qianfan = "jupyter_ai_magics:QianfanEmbeddingsEndpointProvider"
+vertexai = "jupyter_ai_magics.partner_providers.vertexai:VertexAIEmbeddingsProvider"
 
 [tool.hatch.version]
 source = "nodejs"