refactor: update default Gemini and Vertex AI embedder model to gemini-embedding-001 (#4571)

docs/components/embedders/models/google_AI.mdx

@@ -19,7 +19,7 @@ config = {
     "embedder": {
         "provider": "gemini",
         "config": {
-            "model": "models/text-embedding-004",
+            "model": "models/gemini-embedding-001",
         }
     }
 }
@@ -66,7 +66,7 @@ Here are the parameters available for configuring Gemini embedder:
 <Tab title="Python">
 | Parameter        | Description                          | Default Value           |
 | ---------------- | ------------------------------------ | ----------------------- |
-| `model`          | The name of the embedding model to use| `models/text-embedding-004` |
+| `model`          | The name of the embedding model to use| `models/gemini-embedding-001` |
 | `embedding_dims` | Dimensions of the embedding model     | `1536`                  |
 | `api_key`        | The Google API key                   | `None`                  |
 </Tab>

docs/components/embedders/models/vertexai.mdx

@@ -20,7 +20,7 @@ config = {
     "embedder": {
         "provider": "vertexai",
         "config": {
-            "model": "text-embedding-004",
+            "model": "gemini-embedding-001",
             "memory_add_embedding_type": "RETRIEVAL_DOCUMENT",
             "memory_update_embedding_type": "RETRIEVAL_DOCUMENT",
             "memory_search_embedding_type": "RETRIEVAL_QUERY"
@@ -51,7 +51,7 @@ Here are the parameters available for configuring the Vertex AI embedder:
 
 | Parameter                 | Description                                      | Default Value        |
 | ------------------------- | ------------------------------------------------ | -------------------- |
-| `model`                   | The name of the Vertex AI embedding model to use | `text-embedding-004` |
+| `model`                   | The name of the Vertex AI embedding model to use | `gemini-embedding-001` |
 | `vertex_credentials_json` | Path to the Google Cloud credentials JSON file   | `None`               |
 | `embedding_dims`          | Dimensions of the embedding model                | `256`                |
 | `memory_add_embedding_type` | The type of embedding to use for the add memory action | `RETRIEVAL_DOCUMENT` |

mem0/embeddings/gemini.py

@@ -12,7 +12,7 @@ class GoogleGenAIEmbedding(EmbeddingBase):
     def __init__(self, config: Optional[BaseEmbedderConfig] = None):
         super().__init__(config)
 
-        self.config.model = self.config.model or "models/text-embedding-004"
+        self.config.model = self.config.model or "models/gemini-embedding-001"
         self.config.embedding_dims = self.config.embedding_dims or self.config.output_dimensionality or 768
 
         api_key = self.config.api_key or os.getenv("GOOGLE_API_KEY")

mem0/embeddings/vertexai.py

@@ -12,7 +12,7 @@ class VertexAIEmbedding(EmbeddingBase):
     def __init__(self, config: Optional[BaseEmbedderConfig] = None):
         super().__init__(config)
 
-        self.config.model = self.config.model or "text-embedding-004"
+        self.config.model = self.config.model or "gemini-embedding-001"
         self.config.embedding_dims = self.config.embedding_dims or 256
 
         self.embedding_types = {

tests/embeddings/test_vertexai_embeddings.py

@@ -48,7 +48,7 @@ def mock_text_embedding_input():
 
 @patch("mem0.embeddings.vertexai.TextEmbeddingModel")
 def test_embed_default_model(mock_text_embedding_model, mock_os_environ, mock_config, mock_text_embedding_input):
-    mock_config.return_value.model = "text-embedding-004"
+    mock_config.return_value.model = "gemini-embedding-001"
     mock_config.return_value.embedding_dims = 256
 
     config = mock_config()
@@ -59,7 +59,7 @@ def test_embed_default_model(mock_text_embedding_model, mock_os_environ, mock_co
 
     embedder.embed("Hello world")
     mock_text_embedding_input.assert_called_once_with(text="Hello world", task_type="SEMANTIC_SIMILARITY")
-    mock_text_embedding_model.from_pretrained.assert_called_once_with("text-embedding-004")
+    mock_text_embedding_model.from_pretrained.assert_called_once_with("gemini-embedding-001")
 
     mock_text_embedding_model.from_pretrained.return_value.get_embeddings.assert_called_once_with(
         texts=[mock_text_embedding_input("Hello world")], output_dimensionality=256
@@ -92,7 +92,7 @@ def test_embed_custom_model(mock_text_embedding_model, mock_os_environ, mock_con
 def test_embed_with_memory_action(
     mock_text_embedding_model, mock_os_environ, mock_config, mock_embedding_types, mock_text_embedding_input
 ):
-    mock_config.return_value.model = "text-embedding-004"
+    mock_config.return_value.model = "gemini-embedding-001"
     mock_config.return_value.embedding_dims = 256
 
     for embedding_type in mock_embedding_types:
@@ -103,7 +103,7 @@ def test_embed_with_memory_action(
         config = mock_config()
         embedder = VertexAIEmbedding(config)
 
-        mock_text_embedding_model.from_pretrained.assert_called_with("text-embedding-004")
+        mock_text_embedding_model.from_pretrained.assert_called_with("gemini-embedding-001")
 
         for memory_action in ["add", "update", "search"]:
             embedder.embed("Hello world", memory_action=memory_action)
@@ -151,7 +151,7 @@ def test_embed_with_different_dimensions(mock_text_embedding_model, mock_os_envi
 
 @patch("mem0.embeddings.vertexai.TextEmbeddingModel")
 def test_invalid_memory_action(mock_text_embedding_model, mock_config):
-    mock_config.return_value.model = "text-embedding-004"
+    mock_config.return_value.model = "gemini-embedding-001"
     mock_config.return_value.embedding_dims = 256
 
     config = mock_config()