feat: migrate gemini default and deprecations to gemini-2.5-pro

packages/bigframes/bigframes/ml/llm.py

@@ -496,7 +496,7 @@ def __init__(
             warnings.warn(msg, category=exceptions.PreviewWarning)
 
         if model_name is None:
-            model_name = "gemini-2.0-flash-001"
+            model_name = "gemini-2.5-pro"
             msg = exceptions.format_message(_REMOVE_DEFAULT_MODEL_WARNING)
             warnings.warn(msg, category=FutureWarning, stacklevel=2)
 
@@ -522,15 +522,21 @@ 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-2.5-pro",
                     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/series.py

@@ -2258,11 +2258,13 @@ def mask(self, cond, other=None) -> Series:
         return self.where(~cond, other)
 
     def to_frame(self, name: blocks.Label = None) -> bigframes.dataframe.DataFrame:
-        provided_name = name if name else self.name
+        provided_name = name if name is not None else self.name
         # To be consistent with Pandas, it assigns 0 as the column name if missing. 0 is the first element of RangeIndex.
-        block = self._block.with_column_labels(
-            [provided_name] if provided_name else [0]
-        )
+        if provided_name is None or pandas.isna(provided_name):
+            column_names = [0]
+        else:
+            column_names = [provided_name]
+        block = self._block.with_column_labels(column_names)
         return bigframes.dataframe.DataFrame(block)
 
     def to_csv(

packages/bigframes/tests/system/large/bigquery/test_ai.py

@@ -33,7 +33,7 @@ def text_model(bq_connection, dataset_id):
     model_name = f"{dataset_id}.text_model"
     return ml.create_model(
         model_name=model_name,
-        options={"endpoint": "gemini-2.5-flash"},
+        options={"endpoint": "gemini-2.5-pro"},
         connection_name=bq_connection,
     )
 

packages/bigframes/tests/system/large/operations/conftest.py

@@ -22,7 +22,7 @@ def gemini_flash_model(session, bq_connection) -> llm.GeminiTextGenerator:
     return llm.GeminiTextGenerator(
         session=session,
         connection_name=bq_connection,
-        model_name="gemini-2.5-flash",
+        model_name="gemini-2.5-pro",
     )
 
 

packages/bigframes/tests/system/small/bigquery/test_ai.py

@@ -60,7 +60,7 @@ def test_ai_function_pandas_input(session):
     s2 = bpd.Series(["fruit", "tree"], session=session)
     prompt = (s1, " is a ", s2)
 
-    result = bbq.ai.generate_bool(prompt, endpoint="gemini-2.5-flash")
+    result = bbq.ai.generate_bool(prompt, endpoint="gemini-2.5-pro")
 
     assert _contains_no_nulls(result)
     assert result.dtype == pd.ArrowDtype(
@@ -81,7 +81,7 @@ def test_ai_function_string_input(session):
         mock_get_session.return_value = session
         prompt = "Is apple a fruit?"
 
-        result = bbq.ai.generate_bool(prompt, endpoint="gemini-2.5-flash")
+        result = bbq.ai.generate_bool(prompt, endpoint="gemini-2.5-pro")
 
         assert _contains_no_nulls(result)
         assert result.dtype == pd.ArrowDtype(
@@ -102,7 +102,7 @@ def test_ai_function_compile_model_params(session):
     model_params = {"generation_config": {"thinking_config": {"thinking_budget": 0}}}
 
     result = bbq.ai.generate_bool(
-        prompt, endpoint="gemini-2.5-flash", model_params=model_params
+        prompt, endpoint="gemini-2.5-pro", model_params=model_params
     )
 
     assert _contains_no_nulls(result)
@@ -121,7 +121,7 @@ def test_ai_generate(session):
     country = bpd.Series(["Japan", "Canada"], session=session)
     prompt = ("What's the capital city of ", country, "? one word only")
 
-    result = bbq.ai.generate(prompt, endpoint="gemini-2.5-flash")
+    result = bbq.ai.generate(prompt, endpoint="gemini-2.5-pro")
 
     assert _contains_no_nulls(result)
     assert result.dtype == pd.ArrowDtype(
@@ -141,7 +141,7 @@ def test_ai_generate_with_output_schema(session):
 
     result = bbq.ai.generate(
         prompt,
-        endpoint="gemini-2.5-flash",
+        endpoint="gemini-2.5-pro",
         output_schema={"population": "INT64", "is_in_north_america": "bool"},
     )
 
@@ -165,7 +165,7 @@ def test_ai_generate_with_invalid_output_schema_raise_error(session):
     with pytest.raises(ValueError):
         bbq.ai.generate(
             prompt,
-            endpoint="gemini-2.5-flash",
+            endpoint="gemini-2.5-pro",
             output_schema={"population": "INT64", "is_in_north_america": "JSON"},
         )
 
@@ -175,7 +175,7 @@ def test_ai_generate_bool(session):
     s2 = bpd.Series(["fruit", "tree"], session=session)
     prompt = (s1, " is a ", s2)
 
-    result = bbq.ai.generate_bool(prompt, endpoint="gemini-2.5-flash")
+    result = bbq.ai.generate_bool(prompt, endpoint="gemini-2.5-pro")
 
     assert _contains_no_nulls(result)
     assert result.dtype == pd.ArrowDtype(
@@ -216,7 +216,7 @@ def test_ai_generate_int(session):
     s = bpd.Series(["Cat"], session=session)
     prompt = ("How many legs does a ", s, " have?")
 
-    result = bbq.ai.generate_int(prompt, endpoint="gemini-2.5-flash")
+    result = bbq.ai.generate_int(prompt, endpoint="gemini-2.5-pro")
 
     assert _contains_no_nulls(result)
     assert result.dtype == pd.ArrowDtype(
@@ -259,7 +259,7 @@ def test_ai_generate_double(session):
     s = bpd.Series(["Cat"], session=session)
     prompt = ("How many legs does a ", s, " have?")
 
-    result = bbq.ai.generate_double(prompt, endpoint="gemini-2.5-flash")
+    result = bbq.ai.generate_double(prompt, endpoint="gemini-2.5-pro")
 
     assert _contains_no_nulls(result)
     assert result.dtype == pd.ArrowDtype(

packages/bigframes/tests/unit/core/compile/sqlglot/expressions/snapshots/test_ai_ops/test_ai_classify_with_params/out.sql

@@ -3,7 +3,7 @@ SELECT
     input => STRUCT(`string_col`),
     categories => ['greeting', 'rejection'],
     examples => [('hi', 'greeting'), ('bye', 'rejection')],
-    endpoint => 'gemini-2.5-flash',
+    endpoint => 'gemini-2.5-pro',
     max_error_ratio => 0.1
   ) AS `result`
 FROM `bigframes-dev`.`sqlglot_test`.`scalar_types` AS `bft_0`

packages/bigframes/tests/unit/core/compile/sqlglot/expressions/snapshots/test_ai_ops/test_ai_generate/out.sql

@@ -1,7 +1,7 @@
 SELECT
   AI.GENERATE(
     prompt => STRUCT(`string_col`, ' is the same as ', `string_col`),
-    endpoint => 'gemini-2.5-flash',
+    endpoint => 'gemini-2.5-pro',
     request_type => 'SHARED'
   ) AS `result`
 FROM `bigframes-dev`.`sqlglot_test`.`scalar_types` AS `bft_0`

packages/bigframes/tests/unit/core/compile/sqlglot/expressions/snapshots/test_ai_ops/test_ai_generate_bool/out.sql

@@ -1,6 +1,6 @@
 SELECT
   AI.GENERATE_BOOL(
     prompt => STRUCT(`string_col`, ' is the same as ', `string_col`),
-    endpoint => 'gemini-2.5-flash'
+    endpoint => 'gemini-2.5-pro'
   ) AS `result`
 FROM `bigframes-dev`.`sqlglot_test`.`scalar_types` AS `bft_0`

packages/bigframes/tests/unit/core/compile/sqlglot/expressions/snapshots/test_ai_ops/test_ai_generate_bool_with_connection_id/out.sql

@@ -2,6 +2,6 @@ SELECT
   AI.GENERATE_BOOL(
     prompt => STRUCT(`string_col`, ' is the same as ', `string_col`),
     connection_id => 'bigframes-dev.us.bigframes-default-connection',
-    endpoint => 'gemini-2.5-flash'
+    endpoint => 'gemini-2.5-pro'
   ) AS `result`
 FROM `bigframes-dev`.`sqlglot_test`.`scalar_types` AS `bft_0`

packages/bigframes/tests/unit/core/compile/sqlglot/expressions/snapshots/test_ai_ops/test_ai_generate_double/out.sql

@@ -1,6 +1,6 @@
 SELECT
   AI.GENERATE_DOUBLE(
     prompt => STRUCT(`string_col`, ' is the same as ', `string_col`),
-    endpoint => 'gemini-2.5-flash'
+    endpoint => 'gemini-2.5-pro'
   ) AS `result`
 FROM `bigframes-dev`.`sqlglot_test`.`scalar_types` AS `bft_0`

packages/bigframes/tests/unit/core/compile/sqlglot/expressions/snapshots/test_ai_ops/test_ai_generate_double_with_connection_id/out.sql

@@ -2,6 +2,6 @@ SELECT
   AI.GENERATE_DOUBLE(
     prompt => STRUCT(`string_col`, ' is the same as ', `string_col`),
     connection_id => 'bigframes-dev.us.bigframes-default-connection',
-    endpoint => 'gemini-2.5-flash'
+    endpoint => 'gemini-2.5-pro'
   ) AS `result`
 FROM `bigframes-dev`.`sqlglot_test`.`scalar_types` AS `bft_0`

packages/bigframes/tests/unit/core/compile/sqlglot/expressions/snapshots/test_ai_ops/test_ai_generate_int/out.sql

@@ -1,6 +1,6 @@
 SELECT
   AI.GENERATE_INT(
     prompt => STRUCT(`string_col`, ' is the same as ', `string_col`),
-    endpoint => 'gemini-2.5-flash'
+    endpoint => 'gemini-2.5-pro'
   ) AS `result`
 FROM `bigframes-dev`.`sqlglot_test`.`scalar_types` AS `bft_0`

packages/bigframes/tests/unit/core/compile/sqlglot/expressions/snapshots/test_ai_ops/test_ai_generate_int_with_connection_id/out.sql

@@ -2,6 +2,6 @@ SELECT
   AI.GENERATE_INT(
     prompt => STRUCT(`string_col`, ' is the same as ', `string_col`),
     connection_id => 'bigframes-dev.us.bigframes-default-connection',
-    endpoint => 'gemini-2.5-flash'
+    endpoint => 'gemini-2.5-pro'
   ) AS `result`
 FROM `bigframes-dev`.`sqlglot_test`.`scalar_types` AS `bft_0`

packages/bigframes/tests/unit/core/compile/sqlglot/expressions/snapshots/test_ai_ops/test_ai_generate_with_connection_id/out.sql

@@ -2,6 +2,6 @@ SELECT
   AI.GENERATE(
     prompt => STRUCT(`string_col`, ' is the same as ', `string_col`),
     connection_id => 'bigframes-dev.us.bigframes-default-connection',
-    endpoint => 'gemini-2.5-flash'
+    endpoint => 'gemini-2.5-pro'
   ) AS `result`
 FROM `bigframes-dev`.`sqlglot_test`.`scalar_types` AS `bft_0`

packages/bigframes/tests/unit/core/compile/sqlglot/expressions/snapshots/test_ai_ops/test_ai_generate_with_output_schema/out.sql

@@ -1,7 +1,7 @@
 SELECT
   AI.GENERATE(
     prompt => STRUCT(`string_col`, ' is the same as ', `string_col`),
-    endpoint => 'gemini-2.5-flash',
+    endpoint => 'gemini-2.5-pro',
     output_schema => 'x INT64, y FLOAT64'
   ) AS `result`
 FROM `bigframes-dev`.`sqlglot_test`.`scalar_types` AS `bft_0`

packages/bigframes/tests/unit/core/compile/sqlglot/expressions/snapshots/test_ai_ops/test_ai_if_with_endpoint/out.sql

@@ -1,6 +1,6 @@
 SELECT
   AI.IF(
     prompt => STRUCT(`string_col`, ' is the same as ', `string_col`),
-    endpoint => 'gemini-2.5-flash'
+    endpoint => 'gemini-2.5-pro'
   ) AS `result`
 FROM `bigframes-dev`.`sqlglot_test`.`scalar_types` AS `bft_0`

packages/bigframes/tests/unit/core/compile/sqlglot/expressions/snapshots/test_ai_ops/test_ai_score_with_endpoint_and_max_error_ratio/out.sql

@@ -1,7 +1,7 @@
 SELECT
   AI.SCORE(
     prompt => STRUCT(`string_col`, ' is the same as ', `string_col`),
-    endpoint => 'gemini-2.5-flash',
+    endpoint => 'gemini-2.5-pro',
     max_error_ratio => 0.5
   ) AS `result`
 FROM `bigframes-dev`.`sqlglot_test`.`scalar_types` AS `bft_0`

packages/bigframes/tests/unit/core/compile/sqlglot/expressions/test_ai_ops.py

@@ -30,7 +30,7 @@ def test_ai_generate(scalar_types_df: dataframe.DataFrame, snapshot):
 
     op = ops.AIGenerate(
         prompt_context=(None, " is the same as ", None),
-        endpoint="gemini-2.5-flash",
+        endpoint="gemini-2.5-pro",
         request_type="SHARED",
     )
 
@@ -47,7 +47,7 @@ def test_ai_generate_with_connection_id(scalar_types_df: dataframe.DataFrame, sn
     op = ops.AIGenerate(
         prompt_context=(None, " is the same as ", None),
         connection_id=CONNECTION_ID,
-        endpoint="gemini-2.5-flash",
+        endpoint="gemini-2.5-pro",
     )
 
     sql = utils._apply_ops_to_sql(
@@ -63,7 +63,7 @@ def test_ai_generate_with_output_schema(scalar_types_df: dataframe.DataFrame, sn
     op = ops.AIGenerate(
         prompt_context=(None, " is the same as ", None),
         connection_id=None,
-        endpoint="gemini-2.5-flash",
+        endpoint="gemini-2.5-pro",
         output_schema="x INT64, y FLOAT64",
     )
 
@@ -94,7 +94,7 @@ def test_ai_generate_bool(scalar_types_df: dataframe.DataFrame, snapshot):
 
     op = ops.AIGenerateBool(
         prompt_context=(None, " is the same as ", None),
-        endpoint="gemini-2.5-flash",
+        endpoint="gemini-2.5-pro",
     )
 
     sql = utils._apply_ops_to_sql(
@@ -112,7 +112,7 @@ def test_ai_generate_bool_with_connection_id(
     op = ops.AIGenerateBool(
         prompt_context=(None, " is the same as ", None),
         connection_id=CONNECTION_ID,
-        endpoint="gemini-2.5-flash",
+        endpoint="gemini-2.5-pro",
     )
 
     sql = utils._apply_ops_to_sql(
@@ -145,7 +145,7 @@ def test_ai_generate_int(scalar_types_df: dataframe.DataFrame, snapshot):
     op = ops.AIGenerateInt(
         # The prompt does not make semantic sense but we only care about syntax correctness.
         prompt_context=(None, " is the same as ", None),
-        endpoint="gemini-2.5-flash",
+        endpoint="gemini-2.5-pro",
     )
 
     sql = utils._apply_ops_to_sql(
@@ -164,7 +164,7 @@ def test_ai_generate_int_with_connection_id(
         # The prompt does not make semantic sense but we only care about syntax correctness.
         prompt_context=(None, " is the same as ", None),
         connection_id=CONNECTION_ID,
-        endpoint="gemini-2.5-flash",
+        endpoint="gemini-2.5-pro",
     )
 
     sql = utils._apply_ops_to_sql(
@@ -198,7 +198,7 @@ def test_ai_generate_double(scalar_types_df: dataframe.DataFrame, snapshot):
     op = ops.AIGenerateDouble(
         # The prompt does not make semantic sense but we only care about syntax correctness.
         prompt_context=(None, " is the same as ", None),
-        endpoint="gemini-2.5-flash",
+        endpoint="gemini-2.5-pro",
     )
 
     sql = utils._apply_ops_to_sql(
@@ -217,7 +217,7 @@ def test_ai_generate_double_with_connection_id(
         # The prompt does not make semantic sense but we only care about syntax correctness.
         prompt_context=(None, " is the same as ", None),
         connection_id=CONNECTION_ID,
-        endpoint="gemini-2.5-flash",
+        endpoint="gemini-2.5-pro",
     )
 
     sql = utils._apply_ops_to_sql(
@@ -322,7 +322,7 @@ def test_ai_if_with_endpoint(scalar_types_df: dataframe.DataFrame, snapshot):
 
     op = ops.AIIf(
         prompt_context=(None, " is the same as ", None),
-        endpoint="gemini-2.5-flash",
+        endpoint="gemini-2.5-pro",
     )
 
     sql = utils._apply_ops_to_sql(
@@ -354,7 +354,7 @@ def test_ai_classify_with_params(scalar_types_df: dataframe.DataFrame, snapshot)
         prompt_context=(None,),
         categories=("greeting", "rejection"),
         examples=(("hi", "greeting"), ("bye", "rejection")),
-        endpoint="gemini-2.5-flash",
+        endpoint="gemini-2.5-pro",
         max_error_ratio=0.1,
     )
 
@@ -421,7 +421,7 @@ def test_ai_score_with_endpoint_and_max_error_ratio(
 
     op = ops.AIScore(
         prompt_context=(None, " is the same as ", None),
-        endpoint="gemini-2.5-flash",
+        endpoint="gemini-2.5-pro",
         max_error_ratio=0.5,
     )