feat(genai): update the gemini model name

Author: msampathkumar

discoveryengine/answer_query_sample.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 #
 
-# NOTE: This snippet has been partially generated by `gemini-1.5-pro-001`
+# NOTE: This snippet has been partially generated by `gemini-2.0-flash-001`
 
 # [START genappbuilder_answer_query]
 from google.api_core.client_options import ClientOptions
@@ -71,7 +71,7 @@ def answer_query_sample(
         ignore_non_answer_seeking_query=False,  # Optional: Ignore non-answer seeking query
         ignore_low_relevant_content=False,  # Optional: Return fallback answer when content is not relevant
         model_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.ModelSpec(
-            model_version="gemini-1.5-flash-001/answer_gen/v2",  # Optional: Model to use for answer generation
+            model_version="gemini-2.0-flash-001/answer_gen/v2",  # Optional: Model to use for answer generation
         ),
         prompt_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.PromptSpec(
             preamble="Give a detailed answer.",  # Optional: Natural language instructions for customizing the answer.

discoveryengine/session_sample.py

@@ -14,7 +14,7 @@
 # limitations under the License.
 #
 
-# NOTE: This snippet has been partially generated by `gemini-1.5-pro-001`
+# NOTE: This snippet has been partially generated by `gemini-2.0-flash-001`
 
 # [START genappbuilder_create_session]
 from google.cloud import discoveryengine_v1 as discoveryengine

generative_ai/batch_predict/gemini_batch_predict_bigquery.py

@@ -37,7 +37,7 @@ def batch_predict_gemini_createjob(output_uri: str) -> str:
 
     # Submit a batch prediction job with Gemini model
     batch_prediction_job = BatchPredictionJob.submit(
-        source_model="gemini-1.5-flash-002",
+        source_model="gemini-2.0-flash-001",
         input_dataset=input_uri,
         output_uri_prefix=output_uri,
     )

generative_ai/batch_predict/gemini_batch_predict_gcs.py

@@ -38,7 +38,7 @@ def batch_predict_gemini_createjob(output_uri: str) -> str:
 
     # Submit a batch prediction job with Gemini model
     batch_prediction_job = BatchPredictionJob.submit(
-        source_model="gemini-1.5-flash-002",
+        source_model="gemini-2.0-flash-001",
         input_dataset=input_uri,
         output_uri_prefix=output_uri,
     )

generative_ai/evaluation/pairwise_summarization_quality.py

@@ -52,11 +52,11 @@ def evaluate_output() -> EvalResult:
     eval_dataset = pd.DataFrame({"prompt": [prompt]})
 
     # Baseline model for pairwise comparison
-    baseline_model = GenerativeModel("gemini-1.5-pro-001")
+    baseline_model = GenerativeModel("gemini-2.0-flash-001")
 
     # Candidate model for pairwise comparison
     candidate_model = GenerativeModel(
-        "gemini-1.5-pro-002", generation_config={"temperature": 0.4}
+        "gemini-2.0-flash-001", generation_config={"temperature": 0.4}
     )
 
     prompt_template = MetricPromptTemplateExamples.get_prompt_template(

generative_ai/express_mode/api_key_example.py

@@ -21,7 +21,7 @@ def generate_content() -> None:
     # TODO(developer): Update below line
     vertexai.init(api_key="YOUR_API_KEY")
 
-    model = GenerativeModel("gemini-1.5-flash")
+    model = GenerativeModel("gemini-2.0-flash-001")
 
     response = model.generate_content("Explain bubble sort to me")
 

generative_ai/image/image_example01.py

@@ -26,7 +26,7 @@ def generate_text() -> str:
     # PROJECT_ID = "your-project-id"
     vertexai.init(project=PROJECT_ID, location="us-central1")
 
-    model = GenerativeModel("gemini-1.5-flash-002")
+    model = GenerativeModel("gemini-2.0-flash-001")
 
     response = model.generate_content(
         [

generative_ai/image/image_example02.py

@@ -26,7 +26,7 @@ def generate_text() -> None:
     # PROJECT_ID = "your-project-id"
     vertexai.init(project=PROJECT_ID, location="us-central1")
 
-    model = GenerativeModel("gemini-1.5-flash-002")
+    model = GenerativeModel("gemini-2.0-flash-001")
 
     image_file = Part.from_uri(
         "gs://cloud-samples-data/generative-ai/image/scones.jpg", "image/jpeg"

generative_ai/labels/labels_example.py

@@ -28,7 +28,7 @@ def generate_content() -> GenerationResponse:
     # PROJECT_ID = "your-project-id"
     vertexai.init(project=PROJECT_ID, location="us-central1")
 
-    model = GenerativeModel("gemini-1.5-flash-001")
+    model = GenerativeModel("gemini-2.0-flash-001")
 
     prompt = "What is Generative AI?"
     response = model.generate_content(

generative_ai/prompts/prompt_create.py

@@ -39,7 +39,7 @@ def prompt_create() -> Prompt:
             {"movie1": "The Lion King", "movie2": "Frozen"},
             {"movie1": "Inception", "movie2": "Interstellar"},
         ],
-        model_name="gemini-1.5-pro-002",
+        model_name="gemini-2.0-flash-001",
         system_instruction="You are a movie critic. Answer in a short sentence.",
         # generation_config=GenerationConfig, # Optional,
         # safety_settings=SafetySetting, # Optional,