feat: support gemini-3.x models in loader and update default model to gemini-3.5-flash

packages/bigframes/bigframes/bigquery/_operations/ai.py

@@ -87,7 +87,7 @@ def generate(
             Specifies the connection to use to communicate with the model. For example, ``myproject.us.myconnection``.
             If not provided, the query uses your end-user credential.
         endpoint (str, optional):
-            Specifies the Vertex AI endpoint to use for the model. For example ``"gemini-2.5-flash"``. You can specify any
+            Specifies the Vertex AI endpoint to use for the model. For example ``"gemini-3.5-flash"``. You can specify any
             generally available or preview Gemini model. If you specify the model name, BigQuery ML automatically identifies and
             uses the full endpoint of the model. If you don't specify an ENDPOINT value, BigQuery ML selects a recent stable
             version of Gemini to use.
@@ -178,7 +178,7 @@ def generate_bool(
             Specifies the connection to use to communicate with the model. For example, ``myproject.us.myconnection``.
             If not provided, the query uses your end-user credential.
         endpoint (str, optional):
-            Specifies the Vertex AI endpoint to use for the model. For example ``"gemini-2.5-flash"``. You can specify any
+            Specifies the Vertex AI endpoint to use for the model. For example ``"gemini-3.5-flash"``. You can specify any
             generally available or preview Gemini model. If you specify the model name, BigQuery ML automatically identifies and
             uses the full endpoint of the model. If you don't specify an ENDPOINT value, BigQuery ML selects a recent stable
             version of Gemini to use.
@@ -252,7 +252,7 @@ def generate_int(
             Specifies the connection to use to communicate with the model. For example, ``myproject.us.myconnection``.
             If not provided, the query uses your end-user credential.
         endpoint (str, optional):
-            Specifies the Vertex AI endpoint to use for the model. For example ``"gemini-2.5-flash"``. You can specify any
+            Specifies the Vertex AI endpoint to use for the model. For example ``"gemini-3.5-flash"``. You can specify any
             generally available or preview Gemini model. If you specify the model name, BigQuery ML automatically identifies and
             uses the full endpoint of the model. If you don't specify an ENDPOINT value, BigQuery ML selects a recent stable
             version of Gemini to use.
@@ -326,7 +326,7 @@ def generate_double(
             Specifies the connection to use to communicate with the model. For example, ``myproject.us.myconnection``.
             If not provided, the query uses your end-user credential.
         endpoint (str, optional):
-            Specifies the Vertex AI endpoint to use for the model. For example ``"gemini-2.5-flash"``. You can specify any
+            Specifies the Vertex AI endpoint to use for the model. For example ``"gemini-3.5-flash"``. You can specify any
             generally available or preview Gemini model. If you specify the model name, BigQuery ML automatically identifies and
             uses the full endpoint of the model. If you don't specify an ENDPOINT value, BigQuery ML selects a recent stable
             version of Gemini to use.
@@ -809,7 +809,7 @@ def if_(
             Specifies the connection to use to communicate with the model. For example, ``myproject.us.myconnection``.
             If not provided, the query uses your end-user credential.
         endpoint (str, optional):
-            Specifies the Vertex AI endpoint to use for the model. For example ``"gemini-2.5-flash"``. You can specify any
+            Specifies the Vertex AI endpoint to use for the model. For example ``"gemini-3.5-flash"``. You can specify any
             generally available or preview Gemini model. If you specify the model name, BigQuery ML automatically identifies and
             uses the full endpoint of the model. If you don't specify an ENDPOINT value, BigQuery ML dynamically chooses a model based on your query to have the
             best cost to quality tradeoff for the task.
@@ -960,7 +960,7 @@ def score(
             Specifies the connection to use to communicate with the model. For example, ``myproject.us.myconnection``.
             If not provided, the query uses your end-user credential.
         endpoint (str, optional):
-            Specifies the Vertex AI endpoint to use for the model. For example ``"gemini-2.5-flash"``. You can specify any
+            Specifies the Vertex AI endpoint to use for the model. For example ``"gemini-3.5-flash"``. You can specify any
             generally available or preview Gemini model. If you specify the model name, BigQuery ML automatically identifies and
             uses the full endpoint of the model. If you don't specify an endpoint value, BigQuery ML dynamically chooses a model
             based on your query to have the best cost to quality tradeoff for the task.

packages/bigframes/bigframes/ml/llm.py

@@ -59,6 +59,8 @@
 _GEMINI_2P5_PRO_ENDPOINT = "gemini-2.5-pro"
 _GEMINI_2P5_FLASH_ENDPOINT = "gemini-2.5-flash"
 _GEMINI_2P5_FLASH_LITE_ENDPOINT = "gemini-2.5-flash-lite"
+_GEMINI_3P1_FLASH_LITE_ENDPOINT = "gemini-3.1-flash-lite"
+_GEMINI_3P5_FLASH_ENDPOINT = "gemini-3.5-flash"
 
 _GEMINI_ENDPOINTS = (
     _GEMINI_1P5_PRO_PREVIEW_ENDPOINT,
@@ -73,6 +75,8 @@
     _GEMINI_2P5_PRO_ENDPOINT,
     _GEMINI_2P5_FLASH_ENDPOINT,
     _GEMINI_2P5_FLASH_LITE_ENDPOINT,
+    _GEMINI_3P1_FLASH_LITE_ENDPOINT,
+    _GEMINI_3P5_FLASH_ENDPOINT,
 )
 _GEMINI_PREVIEW_ENDPOINTS = (
     _GEMINI_1P5_PRO_PREVIEW_ENDPOINT,
@@ -96,6 +100,8 @@
     _GEMINI_2P5_PRO_ENDPOINT,
     _GEMINI_2P5_FLASH_ENDPOINT,
     _GEMINI_2P5_FLASH_LITE_ENDPOINT,
+    _GEMINI_3P1_FLASH_LITE_ENDPOINT,
+    _GEMINI_3P5_FLASH_ENDPOINT,
 )
 
 _CLAUDE_3_SONNET_ENDPOINT = "claude-3-sonnet"
@@ -431,21 +437,22 @@ class GeminiTextGenerator(base.RetriableRemotePredictor):
     """Gemini text generator LLM model.
 
     .. note::
-        gemini-1.5-X are going to be deprecated. Use gemini-2.5-X (https://cloud.google.com/python/docs/reference/bigframes/latest/bigframes.ml.llm.GeminiTextGenerator) instead.
+        gemini-1.5-X are going to be deprecated. Use gemini-3.5-flash (https://cloud.google.com/python/docs/reference/bigframes/latest/bigframes.ml.llm.GeminiTextGenerator) instead.
 
     Args:
-        model_name (str, Default to "gemini-2.0-flash-001"):
+        model_name (str, Default to "gemini-3.5-flash"):
             The model for natural language tasks. Accepted values are
             "gemini-1.5-pro-preview-0514", "gemini-1.5-flash-preview-0514",
             "gemini-1.5-pro-001", "gemini-1.5-pro-002", "gemini-1.5-flash-001",
             "gemini-1.5-flash-002", "gemini-2.0-flash-exp",
             "gemini-2.0-flash-lite-001", "gemini-2.0-flash-001",
-            "gemini-2.5-pro", "gemini-2.5-flash" and "gemini-2.5-flash-lite".
-            If no setting is provided, "gemini-2.0-flash-001" will be used by
+            "gemini-2.5-pro", "gemini-2.5-flash", "gemini-2.5-flash-lite",
+            "gemini-3.1-flash-lite" and "gemini-3.5-flash".
+            If no setting is provided, "gemini-3.5-flash" will be used by
             default and a warning will be issued.
 
         .. note::
-            "gemini-1.5-X" is going to be deprecated. Please use gemini-2.5-X instead. For example, "gemini-2.5-flash".
+            "gemini-1.5-X" is going to be deprecated. Please use gemini-3.5-flash instead.
             "gemini-2.0-flash-exp", "gemini-1.5-pro-preview-0514" and "gemini-1.5-flash-preview-0514" is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the
             Service Specific Terms(https://cloud.google.com/terms/service-terms#1). Pre-GA products and features are available "as is"
             and might have limited support. For more information, see the launch stage descriptions
@@ -478,6 +485,8 @@ def __init__(
                 "gemini-2.5-pro",
                 "gemini-2.5-flash",
                 "gemini-2.5-flash-lite",
+                "gemini-3.1-flash-lite",
+                "gemini-3.5-flash",
             ]
         ] = None,
         session: Optional[bigframes.Session] = None,
@@ -496,7 +505,7 @@ def __init__(
             warnings.warn(msg, category=exceptions.PreviewWarning)
 
         if model_name is None:
-            model_name = "gemini-2.0-flash-001"
+            model_name = "gemini-3.5-flash"
             msg = exceptions.format_message(_REMOVE_DEFAULT_MODEL_WARNING)
             warnings.warn(msg, category=FutureWarning, stacklevel=2)
 
@@ -522,15 +531,21 @@ def _create_bqml_model(self):
                 )
             )
             warnings.warn(msg)
-        if self.model_name.startswith("gemini-1.5"):
+        if self.model_name.startswith(
+            ("gemini-2.0", "gemini-1.5")
+        ) or self.model_name in (
+            "gemini-2.5-flash",
+            "gemini-2.5-flash-lite",
+            "gemini-2.5-pro-preview-05-06",
+        ):
             msg = exceptions.format_message(
                 _MODEL_DEPRECATE_WARNING.format(
                     model_name=self.model_name,
-                    new_model_name="gemini-2.5-X",
+                    new_model_name="gemini-3.5-flash",
                     link="https://cloud.google.com/python/docs/reference/bigframes/latest/bigframes.ml.llm.GeminiTextGenerator",
                 )
             )
-            warnings.warn(msg)
+            warnings.warn(msg, category=exceptions.ApiDeprecationWarning)
 
         options = {"endpoint": self.model_name}
 

packages/bigframes/bigframes/ml/loader.py

@@ -70,6 +70,8 @@
         llm._GEMINI_2P5_FLASH_ENDPOINT: llm.GeminiTextGenerator,
         llm._GEMINI_2P5_FLASH_LITE_ENDPOINT: llm.GeminiTextGenerator,
         llm._GEMINI_2P5_PRO_ENDPOINT: llm.GeminiTextGenerator,
+        llm._GEMINI_3P1_FLASH_LITE_ENDPOINT: llm.GeminiTextGenerator,
+        llm._GEMINI_3P5_FLASH_ENDPOINT: llm.GeminiTextGenerator,
         llm._CLAUDE_3_HAIKU_ENDPOINT: llm.Claude3TextGenerator,
         llm._CLAUDE_3_SONNET_ENDPOINT: llm.Claude3TextGenerator,
         llm._CLAUDE_3_5_SONNET_ENDPOINT: llm.Claude3TextGenerator,

packages/bigframes/bigframes/operations/semantics.py

@@ -57,7 +57,7 @@ def agg(
             >>> bpd.options.compute.semantic_ops_confirmation_threshold = 25
 
             >>> import bigframes.ml.llm as llm
-            >>> model = llm.GeminiTextGenerator(model_name="gemini-2.0-flash-001") # doctest: +SKIP
+            >>> model = llm.GeminiTextGenerator(model_name="gemini-3.5-flash") # doctest: +SKIP
 
             >>> df = bpd.DataFrame(
             ... {
@@ -330,7 +330,7 @@ def filter(self, instruction: str, model, ground_with_google_search: bool = Fals
             >>> bpd.options.compute.semantic_ops_confirmation_threshold = 25
 
             >>> import bigframes.ml.llm as llm
-            >>> model = llm.GeminiTextGenerator(model_name="gemini-2.0-flash-001") # doctest: +SKIP
+            >>> model = llm.GeminiTextGenerator(model_name="gemini-3.5-flash") # doctest: +SKIP
 
             >>> df = bpd.DataFrame({"country": ["USA", "Germany"], "city": ["Seattle", "Berlin"]})
             >>> df.semantics.filter("{city} is the capital of {country}", model) # doctest: +SKIP
@@ -443,7 +443,7 @@ def map(
             >>> bpd.options.compute.semantic_ops_confirmation_threshold = 25
 
             >>> import bigframes.ml.llm as llm
-            >>> model = llm.GeminiTextGenerator(model_name="gemini-2.0-flash-001") # doctest: +SKIP
+            >>> model = llm.GeminiTextGenerator(model_name="gemini-3.5-flash") # doctest: +SKIP
 
             >>> df = bpd.DataFrame({"ingredient_1": ["Burger Bun", "Soy Bean"], "ingredient_2": ["Beef Patty", "Bittern"]})
             >>> df.semantics.map("What is the food made from {ingredient_1} and {ingredient_2}? One word only.", output_column="food", model=model) # doctest: +SKIP
@@ -565,7 +565,7 @@ def join(
             >>> bpd.options.compute.semantic_ops_confirmation_threshold = 25
 
             >>> import bigframes.ml.llm as llm
-            >>> model = llm.GeminiTextGenerator(model_name="gemini-2.0-flash-001") # doctest: +SKIP
+            >>> model = llm.GeminiTextGenerator(model_name="gemini-3.5-flash") # doctest: +SKIP
 
             >>> cities = bpd.DataFrame({'city': ['Seattle', 'Ottawa', 'Berlin', 'Shanghai', 'New Delhi']})
             >>> continents = bpd.DataFrame({'continent': ['North America', 'Africa', 'Asia']})
@@ -805,7 +805,7 @@ def top_k(
             >>> bpd.options.compute.semantic_ops_confirmation_threshold = 25
 
             >>> import bigframes.ml.llm as llm
-            >>> model = llm.GeminiTextGenerator(model_name="gemini-2.0-flash-001") # doctest: +SKIP
+            >>> model = llm.GeminiTextGenerator(model_name="gemini-3.5-flash") # doctest: +SKIP
 
             >>> df = bpd.DataFrame(
             ... {