Lorenze/supporting vertex embeddings (#4282)

* feat: introduce GoogleGenAIVertexEmbeddingFunction for dual SDK support

- Added a new embedding function to support both the legacy vertexai.language_models SDK and the new google-genai SDK for Google Vertex AI.
- Updated factory methods to route to the new embedding function.
- Enhanced VertexAIProvider and related configurations to accommodate the new model options.
- Added integration tests for Google Vertex embeddings with Crew memory, ensuring compatibility and functionality with both authentication methods.

This update improves the flexibility and compatibility of Google Vertex AI embeddings within the CrewAI framework.

* fix test count

* rm comment

* regen cassettes

* regen

* drop variable from .envtest

* dreict to relevant trest only

docs/en/concepts/memory.mdx

@@ -401,23 +401,58 @@ crew = Crew(
 
 ### Vertex AI Embeddings
 
-For Google Cloud users with Vertex AI access.
+For Google Cloud users with Vertex AI access. Supports both legacy and new embedding models with automatic SDK selection.
+
+<Note>
+**Deprecation Notice:** Legacy models (`textembedding-gecko*`) use the deprecated `vertexai.language_models` SDK which will be removed after June 24, 2026. Consider migrating to newer models like `gemini-embedding-001`. See the [Google migration guide](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/deprecations/genai-vertexai-sdk) for details.
+</Note>
 
 ```python
+# Recommended: Using new models with google-genai SDK
 crew = Crew(
     memory=True,
     embedder={
-        "provider": "vertexai",
+        "provider": "google-vertex",
         "config": {
             "project_id": "your-gcp-project-id",
-            "region": "us-central1",  # or your preferred region
-            "api_key": "your-service-account-key",
-            "model_name": "textembedding-gecko"
+            "location": "us-central1",
+            "model_name": "gemini-embedding-001",  # or "text-embedding-005", "text-multilingual-embedding-002"
+            "task_type": "RETRIEVAL_DOCUMENT",  # Optional
+            "output_dimensionality": 768  # Optional
+        }
+    }
+)
+
+# Using API key authentication (Exp)
+crew = Crew(
+    memory=True,
+    embedder={
+        "provider": "google-vertex",
+        "config": {
+            "api_key": "your-google-api-key",
+            "model_name": "gemini-embedding-001"
+        }
+    }
+)
+
+# Legacy models (backwards compatible, emits deprecation warning)
+crew = Crew(
+    memory=True,
+    embedder={
+        "provider": "google-vertex",
+        "config": {
+            "project_id": "your-gcp-project-id",
+            "region": "us-central1",  # or "location" (region is deprecated)
+            "model_name": "textembedding-gecko"  # Legacy model
         }
     }
 )
 ```
 
+**Available models:**
+- **New SDK models** (recommended): `gemini-embedding-001`, `text-embedding-005`, `text-multilingual-embedding-002`
+- **Legacy models** (deprecated): `textembedding-gecko`, `textembedding-gecko@001`, `textembedding-gecko-multilingual`
+
 ### Ollama Embeddings (Local)
 
 Run embeddings locally for privacy and cost savings.
@@ -569,7 +604,7 @@ mem0_client_embedder_config = {
             "project_id": "my_project_id", # Optional
             "api_key": "custom-api-key"    # Optional - overrides env var
             "run_id": "my_run_id",        # Optional - for short-term memory
-            "includes": "include1",       # Optional 
+            "includes": "include1",       # Optional
             "excludes": "exclude1",       # Optional
             "infer": True                 # Optional defaults to True
             "custom_categories": new_categories  # Optional - custom categories for user memory
@@ -591,7 +626,7 @@ crew = Crew(
 
 ### Choosing the Right Embedding Provider
 
-When selecting an embedding provider, consider factors like performance, privacy, cost, and integration needs.  
+When selecting an embedding provider, consider factors like performance, privacy, cost, and integration needs.
 Below is a comparison to help you decide:
 
 | Provider       | Best For                       | Pros                              | Cons                      |
@@ -749,7 +784,7 @@ Entity Memory supports batching when saving multiple entities at once. When you
 
 This improves performance and observability when writing many entities in one operation.
 
-## 2. External Memory 
+## 2. External Memory
 External Memory provides a standalone memory system that operates independently from the crew's built-in memory. This is ideal for specialized memory providers or cross-application memory sharing.
 
 ### Basic External Memory with Mem0
@@ -819,7 +854,7 @@ external_memory = ExternalMemory(
             "project_id": "my_project_id", # Optional
             "api_key": "custom-api-key"    # Optional - overrides env var
             "run_id": "my_run_id",        # Optional - for short-term memory
-            "includes": "include1",       # Optional 
+            "includes": "include1",       # Optional
             "excludes": "exclude1",       # Optional
             "infer": True                 # Optional defaults to True
             "custom_categories": new_categories  # Optional - custom categories for user memory