chore: Updating documentation and adding exception handling for Vector Stores in RAG Tool and updating inference to use openai and updating memory implementation to use existing libraries

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

llama_stack/providers/remote/inference/vertexai/vertexai.py

@@ -6,16 +6,20 @@
 
 from typing import Any
 
+import google.auth.transport.requests
+from google.auth import default
+
 from llama_stack.apis.inference import ChatCompletionRequest
 from llama_stack.providers.utils.inference.litellm_openai_mixin import (
     LiteLLMOpenAIMixin,
 )
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
 from .config import VertexAIConfig
 from .models import MODEL_ENTRIES
 
 
-class VertexAIInferenceAdapter(LiteLLMOpenAIMixin):
+class VertexAIInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
     def __init__(self, config: VertexAIConfig) -> None:
         LiteLLMOpenAIMixin.__init__(
             self,
@@ -27,9 +31,30 @@ class VertexAIInferenceAdapter(LiteLLMOpenAIMixin):
         self.config = config
 
     def get_api_key(self) -> str:
-        # Vertex AI doesn't use API keys, it uses Application Default Credentials
-        # Return empty string to let litellm handle authentication via ADC
-        return ""
+        """
+        Get an access token for Vertex AI using Application Default Credentials.
+
+        Vertex AI uses ADC instead of API keys. This method obtains an access token
+        from the default credentials and returns it for use with the OpenAI-compatible client.
+        """
+        try:
+            # Get default credentials - will read from GOOGLE_APPLICATION_CREDENTIALS
+            credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
+            credentials.refresh(google.auth.transport.requests.Request())
+            return str(credentials.token)
+        except Exception:
+            # If we can't get credentials, return empty string to let LiteLLM handle it
+            # This allows the LiteLLM mixin to work with ADC directly
+            return ""
+
+    def get_base_url(self) -> str:
+        """
+        Get the Vertex AI OpenAI-compatible API base URL.
+
+        Returns the Vertex AI OpenAI-compatible endpoint URL.
+        Source: https://cloud.google.com/vertex-ai/generative-ai/docs/start/openai
+        """
+        return f"https://{self.config.location}-aiplatform.googleapis.com/v1/projects/{self.config.project}/locations/{self.config.location}/endpoints/openapi"
 
     async def _get_params(self, request: ChatCompletionRequest) -> dict[str, Any]:
         # Get base parameters from parent