Standardize the location parameter (#11745)

* adds the location fixes

* Updated variable name REGION to LOCATION

* fixed issue in comments

* fixes linter issues

* Update gemini_tuning.py

convert LOCATION to location

* Update generative_ai/multimodal_embedding_video.py

---------

Co-authored-by: rohith-egen <rohith.alla@egen.ai>
Co-authored-by: nileshspringml <nilesh.mahajan@egen.ai>
Co-authored-by: Holt Skinner <13262395+holtskinner@users.noreply.github.com>

generative_ai/gemini_tuning.py

@@ -21,6 +21,7 @@ def gemini_tuning_basic(project_id: str) -> sft.SupervisedTuningJob:
     # [START generativeaionvertexai_tuning_basic]
 
     import time
+
     import vertexai
     from vertexai.preview.tuning import sft
 
@@ -51,6 +52,7 @@ def gemini_tuning_advanced(project_id: str) -> sft.SupervisedTuningJob:
     # [START generativeaionvertexai_tuning_advanced]
 
     import time
+
     import vertexai
     from vertexai.preview.tuning import sft
 

generative_ai/gemini_tuning_test.py

@@ -19,7 +19,7 @@
 import gemini_tuning
 
 PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
-REGION = "us-central1"
+LOCATION = "us-central1"
 MODEL_ID = "gemini-1.5-pro-preview-0409"
 TUNING_JOB_ID = "4982013113894174720"
 
@@ -34,7 +34,8 @@ def test_gemini_tuning() -> None:
 
 
 def test_get_tuning_job() -> None:
-    response = gemini_tuning.get_tuning_job(PROJECT_ID, REGION, TUNING_JOB_ID)
+    response = gemini_tuning.get_tuning_job(
+        PROJECT_ID, LOCATION, TUNING_JOB_ID)
     assert response
 
 
@@ -45,4 +46,4 @@ def test_list_tuning_jobs() -> None:
 
 @pytest.mark.skip(reason="Skip due to tuning taking a long time.")
 def test_cancel_tuning_job() -> None:
-    gemini_tuning.cancel_tuning_job(PROJECT_ID, REGION, TUNING_JOB_ID)
+    gemini_tuning.cancel_tuning_job(PROJECT_ID, LOCATION, TUNING_JOB_ID)

generative_ai/inference/inference_api_test.py

@@ -21,29 +21,28 @@
 
 
 PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
-REGION = "us-central1"
 MODEL_ID = "gemini-1.5-pro-preview-0409"
 
 
 def test_non_stream_text_basic() -> None:
-    response = non_stream_text_basic.generate_content(PROJECT_ID, REGION, MODEL_ID)
+    response = non_stream_text_basic.generate_content(PROJECT_ID, MODEL_ID)
     assert response
 
 
 def test_non_stream_multi_modality_basic() -> None:
     response = non_stream_multimodality_basic.generate_content(
-        PROJECT_ID, REGION, MODEL_ID
+        PROJECT_ID, MODEL_ID
     )
     assert response
 
 
 def test_stream_text_basic() -> None:
-    responses = stream_text_basic.generate_content(PROJECT_ID, REGION, MODEL_ID)
+    responses = stream_text_basic.generate_content(PROJECT_ID, MODEL_ID)
     assert responses
 
 
 def test_stream_multi_modality_basic() -> None:
     responses = stream_multimodality_basic.generate_content(
-        PROJECT_ID, REGION, MODEL_ID
+        PROJECT_ID, MODEL_ID
     )
     assert responses

generative_ai/inference/non_stream_multimodality_basic.py

@@ -13,13 +13,13 @@
 # limitations under the License.
 
 
-def generate_content(PROJECT_ID: str, REGION: str, MODEL_ID: str) -> object:
+def generate_content(PROJECT_ID: str, MODEL_ID: str) -> object:
     # [START generativeaionvertexai_non_stream_multimodality_basic]
     import vertexai
 
     from vertexai.generative_models import GenerativeModel, Part
 
-    vertexai.init(project=PROJECT_ID, location=REGION)
+    vertexai.init(project=PROJECT_ID, location="us-central1")
 
     model = GenerativeModel(MODEL_ID)
     response = model.generate_content(

generative_ai/inference/non_stream_text_basic.py

@@ -13,13 +13,13 @@
 # limitations under the License.
 
 
-def generate_content(PROJECT_ID: str, REGION: str, MODEL_ID: str) -> object:
+def generate_content(PROJECT_ID: str, MODEL_ID: str) -> object:
     # [START generativeaionvertexai_non_stream_text_basic]
     import vertexai
 
     from vertexai.generative_models import GenerativeModel
 
-    vertexai.init(project=PROJECT_ID, location=REGION)
+    vertexai.init(project=PROJECT_ID, location="us-central1")
 
     model = GenerativeModel(MODEL_ID)
     response = model.generate_content("Write a story about a magic backpack.")

generative_ai/inference/stream_multimodality_basic.py

@@ -13,13 +13,13 @@
 # limitations under the License.
 
 
-def generate_content(PROJECT_ID: str, REGION: str, MODEL_ID: str) -> object:
+def generate_content(PROJECT_ID: str, MODEL_ID: str) -> object:
     # [START generativeaionvertexai_stream_multimodality_basic]
     import vertexai
 
     from vertexai.generative_models import GenerativeModel, Part
 
-    vertexai.init(project=PROJECT_ID, location=REGION)
+    vertexai.init(project=PROJECT_ID, location="us-central1")
 
     model = GenerativeModel(MODEL_ID)
     responses = model.generate_content(

generative_ai/inference/stream_text_basic.py

@@ -13,13 +13,13 @@
 # limitations under the License.
 
 
-def generate_content(PROJECT_ID: str, REGION: str, MODEL_ID: str) -> object:
+def generate_content(PROJECT_ID: str, MODEL_ID: str) -> object:
     # [START generativeaionvertexai_stream_text_basic]
     import vertexai
 
     from vertexai.generative_models import GenerativeModel
 
-    vertexai.init(project=PROJECT_ID, location=REGION)
+    vertexai.init(project=PROJECT_ID, location="us-central1")
 
     model = GenerativeModel(MODEL_ID)
     responses = model.generate_content(

generative_ai/multimodal_embedding_image.py

@@ -19,24 +19,22 @@
 
 def get_image_embeddings(
     project_id: str,
-    location: str,
     image_path: str,
     contextual_text: Optional[str] = None,
 ) -> MultiModalEmbeddingResponse:
     """Example of how to generate multimodal embeddings from image and text.
 
     Args:
         project_id: Google Cloud Project ID, used to initialize vertexai
-        location: Google Cloud Region, used to initialize vertexai
         image_path: Path to image (local or Google Cloud Storage) to generate embeddings for.
         contextual_text: Text to generate embeddings for.
     """
     # [START aiplatform_sdk_multimodal_embedding_image]
     import vertexai
     from vertexai.vision_models import Image, MultiModalEmbeddingModel
 
-    # TODO(developer): Update values for project_id, location, image_path & contextual_text
-    vertexai.init(project=project_id, location=location)
+    # TODO(developer): Update values for project_id, image_path & contextual_text
+    vertexai.init(project=project_id, location="us-central1")
 
     model = MultiModalEmbeddingModel.from_pretrained("multimodalembedding")
     image = Image.load_from_file(image_path)

generative_ai/multimodal_embedding_image_test.py

@@ -19,14 +19,12 @@
 import multimodal_embedding_image
 
 _PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
-_LOCATION = "us-central1"
 
 
 @backoff.on_exception(backoff.expo, ResourceExhausted, max_time=10)
 def test_multimodal_embedding_image() -> None:
     embeddings = multimodal_embedding_image.get_image_embeddings(
         project_id=_PROJECT_ID,
-        location=_LOCATION,
         image_path="gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png",
         contextual_text="Colosseum",
     )

generative_ai/multimodal_embedding_image_video_text.py

@@ -19,7 +19,6 @@
 
 def get_image_video_text_embeddings(
     project_id: str,
-    location: str,
     image_path: str,
     video_path: str,
     contextual_text: Optional[str] = None,
@@ -44,9 +43,9 @@ def get_image_video_text_embeddings(
 
     from vertexai.vision_models import Image, MultiModalEmbeddingModel, Video
 
-    # TODO(developer): Update values for project_id, location,
+    # TODO(developer): Update values for project_id,
     #            image_path, video_path, contextual_text, video_segment_config
-    vertexai.init(project=project_id, location=location)
+    vertexai.init(project=project_id, location="us-central1")
 
     model = MultiModalEmbeddingModel.from_pretrained("multimodalembedding")
     image = Image.load_from_file(image_path)

generative_ai/multimodal_embedding_image_video_text_test.py

@@ -19,14 +19,12 @@
 import multimodal_embedding_image_video_text
 
 _PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
-_LOCATION = "us-central1"
 
 
 @backoff.on_exception(backoff.expo, ResourceExhausted, max_time=10)
 def test_multimodal_embedding_image_video_text() -> None:
     embeddings = multimodal_embedding_image_video_text.get_image_video_text_embeddings(
         project_id=_PROJECT_ID,
-        location=_LOCATION,
         image_path="gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png",
         video_path="gs://cloud-samples-data/vertex-ai-vision/highway_vehicles.mp4",
         contextual_text="Cars on Highway",

generative_ai/multimodal_embedding_video.py

@@ -19,7 +19,6 @@
 
 def get_video_embeddings(
     project_id: str,
-    location: str,
     video_path: str,
     contextual_text: Optional[str] = None,
     dimension: Optional[int] = 1408,
@@ -42,9 +41,9 @@ def get_video_embeddings(
 
     from vertexai.vision_models import MultiModalEmbeddingModel, Video
 
-    # TODO(developer): Update values for project_id, location,
+    # TODO(developer): Update values for project_id,
     #               video_path, contextual_text, dimension, video_segment_config
-    vertexai.init(project=project_id, location=location)
+    vertexai.init(project=project_id, location="us-central1")
 
     model = MultiModalEmbeddingModel.from_pretrained("multimodalembedding")
     video = Video.load_from_file(video_path)

generative_ai/multimodal_embedding_video_test.py

@@ -19,14 +19,12 @@
 import multimodal_embedding_video
 
 _PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
-_LOCATION = "us-central1"
 
 
 @backoff.on_exception(backoff.expo, ResourceExhausted, max_time=10)
 def test_multimodal_embedding_video() -> None:
     embeddings = multimodal_embedding_video.get_video_embeddings(
         project_id=_PROJECT_ID,
-        location=_LOCATION,
         video_path="gs://cloud-samples-data/vertex-ai-vision/highway_vehicles.mp4",
         contextual_text="Cars on Highway",
     )