refactor(genai): Update samples to use latest version of Gen AI SDK (#13257)

msampathkumar · web-flow · commit 23f40477fbf5 · 2025-03-26T13:13:50.000-04:00
* feat(genai): Update samples to use latest version of GenAI SDK

* refactor(genai): minor code formatting changes

* refactor(genai): code reformatting changes

* refactor(genai): Update README.md

* fix(genai): lint error

* fix(genai): lint error
diff --git a/genai/README.md b/genai/README.md
@@ -16,41 +16,76 @@ To run these samples, we recommend using either Google Cloud Shell, Cloud Code I
 
 The samples are organized into the following categories:
 
-### Batch Prediction (`batch_prediction`)
+### [Batch Prediction](https://github.com/GoogleCloudPlatform/python-docs-samples/tree/main/genai/batch_prediction/)
 
-Demonstrates how to use batch prediction with Generative AI models. This allows efficient processing of large datasets. See the [Batch Prediction documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/batch-prediction-gemini) for more details.
+Demonstrates how to use batch prediction with Generative AI models. This allows efficient processing of large datasets.
+See the [Batch Prediction documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/batch-prediction-gemini)
+for more details.
 
-### Content Cache (`content_cache`)
+### [Bounding Box](https://github.com/GoogleCloudPlatform/python-docs-samples/tree/main/genai/bounding_box/)
 
-Illustrates how to create, update, use, and delete content caches. Caches store frequently used content to improve performance and reduce costs. See the [Content Cache documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/context-cache/context-cache-overview) for more information.
+Demonstrates how to use Bounding Box with Generative AI models. This allows for object detection and localization within
+images and video. see the [Bounding Box documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/bounding-box-detection)
+for more details.
 
-### Controlled Generation (`controlled_generation`)
+### [Content Cache](https://github.com/GoogleCloudPlatform/python-docs-samples/tree/main/genai/content_cache/)
 
-Provides examples of how to control various aspects of the generated content, such as length, format, safety attributes, and more. This allows for tailoring the output to specific requirements and constraints. See the [Controlled Generation documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/control-generated-output) for details.
+Illustrates how to create, update, use, and delete content caches. Caches store frequently used content to improve
+performance and reduce costs. See the [Content Cache documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/context-cache/context-cache-overview)
+for more information.
 
-### Count Tokens (`count_tokens`)
+### [Controlled Generation](https://github.com/GoogleCloudPlatform/python-docs-samples/tree/main/genai/controlled_generation/)
 
-Shows how to estimate token usage for inputs and outputs of Generative AI models. Understanding token consumption is crucial for managing costs and optimizing performance. See the [Token Counting documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/list-token) for more details.
+Provides examples of how to control various aspects of the generated content, such as length, format, safety attributes,
+and more. This allows for tailoring the output to specific requirements and constraints.
+See the [Controlled Generation documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/control-generated-output)
+for details.
 
-### Express Mode (`express_mode`)
+### [Count Tokens](https://github.com/GoogleCloudPlatform/python-docs-samples/tree/main/genai/count_tokens/)
 
-Demonstrates how to use Express Mode for simpler and faster interactions with Generative AI models using an API key. This mode is ideal for quick prototyping and experimentation. See the [Express Mode documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/start/express-mode/overview) for details.
+Shows how to estimate token usage for inputs and outputs of Generative AI models. Understanding token consumption is
+crucial for managing costs and optimizing performance. See the [Token Counting documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/list-token)
+for more details.
 
-### Live API (`live_api`)
+### [Express Mode](https://github.com/GoogleCloudPlatform/python-docs-samples/tree/main/genai/express_mode/)
 
-Provides examples of using the Generative AI [Live API](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal-live-api). This allows for real-time interactions and dynamic content generation.
+Demonstrates how to use Express Mode for simpler and faster interactions with Generative AI models using an API key.
+This mode is ideal for quick prototyping and experimentation. See the [Express Mode documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/start/express-mode/overview)
+for details.
 
-### Safety (`safety`)
+### [Live API](https://github.com/GoogleCloudPlatform/python-docs-samples/tree/main/genai/live_api/)
 
-Provides examples demonstrating how to configure and apply safety settings to Generative AI models. This includes techniques for content filtering and moderation to ensure responsible AI usage. See the [Safety documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/configure-safety-attributes) for details.
+Provides examples of using the Generative AI [Live API](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal-live-api).
+This allows for real-time interactions and dynamic content generation.
 
-### Text Generation (`text_generation`)
+### [Provisioned Throughput](https://github.com/GoogleCloudPlatform/python-docs-samples/tree/main/genai/live_api/)
 
-Provides examples of generating text using various input modalities (text, images, audio, video) and features like asynchronous generation, chat, and text streaming. See the [Text Generation documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/send-chat-prompts-gemini) for details.
+Provides examples demonstrating how to use Provisioned Throughput with Generative AI models. This feature provides a
+fixed-cost monthly subscription or weekly service that reserves throughput for supported generative AI models on Vertex AI.
+See the [Provisioned Throughput](https://cloud.google.com/vertex-ai/generative-ai/docs/provisioned-throughput) for details.
 
-### Tools (`tools`)
+### [Safety](https://github.com/GoogleCloudPlatform/python-docs-samples/tree/main/genai/safety/)
 
-Showcases how to use tools like function calling, code execution, and grounding with Google Search to enhance Generative AI interactions. See the [Tools documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/function-calling) for more information.
+Provides examples demonstrating how to configure and apply safety settings to Generative AI models. This includes
+techniques for content filtering and moderation to ensure responsible AI usage. See the
+[Safety documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/configure-safety-attributes)
+for details.
+
+### [Text Generation](https://github.com/GoogleCloudPlatform/python-docs-samples/tree/main/genai/text_generation/)
+
+Provides examples of generating text using various input modalities (text, images, audio, video) and features like
+asynchronous generation, chat, and text streaming. See the[Text Generation documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/send-chat-prompts-gemini)
+for details.
+
+### [Tools](https://github.com/GoogleCloudPlatform/python-docs-samples/tree/main/genai/tools/)
+
+Showcases how to use tools like function calling, code execution, and grounding with Google Search to enhance
+Generative AI interactions. See the [Tools documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/function-calling) for more information.
+
+### [Video Generation](https://github.com/GoogleCloudPlatform/python-docs-samples/tree/main/genai/video_generation/)
+
+Provides examples of generating videos using text & images input modalities. See the
+[Video Generation documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/video/generate-videos) for details.
 
 ## Contributing
 
diff --git a/genai/batch_prediction/batchpredict_embeddings_with_gcs.py b/genai/batch_prediction/batchpredict_embeddings_with_gcs.py
@@ -59,7 +59,6 @@ def generate_content(output_uri: str) -> str:
     # Job state: JOB_STATE_RUNNING
     # ...
     # Job state: JOB_STATE_SUCCEEDED
-
     # [END googlegenaisdk_batchpredict_embeddings_with_gcs]
     return job.state
 
diff --git a/genai/batch_prediction/batchpredict_with_bq.py b/genai/batch_prediction/batchpredict_with_bq.py
@@ -54,7 +54,6 @@ def generate_content(output_uri: str) -> str:
     # Job state: JOB_STATE_RUNNING
     # ...
     # Job state: JOB_STATE_SUCCEEDED
-
     # [END googlegenaisdk_batchpredict_with_bq]
     return job.state
 
diff --git a/genai/batch_prediction/batchpredict_with_gcs.py b/genai/batch_prediction/batchpredict_with_gcs.py
@@ -55,7 +55,6 @@ def generate_content(output_uri: str) -> str:
     # Job state: JOB_STATE_RUNNING
     # ...
     # Job state: JOB_STATE_SUCCEEDED
-
     # [END googlegenaisdk_batchpredict_with_gcs]
     return job.state
 
diff --git a/genai/batch_prediction/requirements.txt b/genai/batch_prediction/requirements.txt
@@ -1 +1 @@
-google-genai==1.2.0
+google-genai==1.7.0
diff --git a/genai/bounding_box/boundingbox_with_txt_img.py b/genai/bounding_box/boundingbox_with_txt_img.py
@@ -18,17 +18,13 @@ def generate_content() -> str:
     import requests
 
     from google import genai
-    from google.genai.types import (
-        GenerateContentConfig,
-        HttpOptions,
-        Part,
-        SafetySetting,
-    )
+    from google.genai.types import GenerateContentConfig, HttpOptions, Part, SafetySetting
 
     from PIL import Image, ImageColor, ImageDraw
 
     from pydantic import BaseModel
 
+    # Helper class to represent a bounding box
     class BoundingBox(BaseModel):
         """
         Represents a bounding box with its 2D coordinates and associated label.
@@ -42,6 +38,7 @@ class BoundingBox(BaseModel):
         box_2d: list[int]
         label: str
 
+    # Helper function to plot bounding boxes on an image
     def plot_bounding_boxes(image_uri: str, bounding_boxes: list[BoundingBox]) -> None:
         """
         Plots bounding boxes on an image with markers for each a name, using PIL, normalized coordinates, and different colors.
@@ -51,7 +48,6 @@ def plot_bounding_boxes(image_uri: str, bounding_boxes: list[BoundingBox]) -> No
             bounding_boxes: A list of bounding boxes containing the name of the object
             and their positions in normalized [y1 x1 y2 x2] format.
         """
-
         with Image.open(requests.get(image_uri, stream=True, timeout=10).raw) as im:
             width, height = im.size
             draw = ImageDraw.Draw(im)
@@ -92,7 +88,7 @@ def plot_bounding_boxes(image_uri: str, bounding_boxes: list[BoundingBox]) -> No
             ),
         ],
         response_mime_type="application/json",
-        response_schema=list[BoundingBox],
+        response_schema=list[BoundingBox],  # Add BoundingBox class to the response schema
     )
 
     image_uri = "https://storage.googleapis.com/generativeai-downloads/images/socks.jpg"
diff --git a/genai/bounding_box/requirements.txt b/genai/bounding_box/requirements.txt
@@ -1,2 +1,2 @@
-google-genai==1.2.0
+google-genai==1.7.0
 pillow==11.1.0
diff --git a/genai/content_cache/requirements.txt b/genai/content_cache/requirements.txt
@@ -1 +1 @@
-google-genai==1.2.0
+google-genai==1.7.0
diff --git a/genai/controlled_generation/ctrlgen_with_class_schema.py b/genai/controlled_generation/ctrlgen_with_class_schema.py
@@ -54,7 +54,6 @@ class Recipe(BaseModel):
     #     ],
     #     "recipe_name": "Classic Chocolate Chip Cookies"
     #   }, ... ]
-
     # [END googlegenaisdk_ctrlgen_with_class_schema]
     return response.text
 
diff --git a/genai/controlled_generation/ctrlgen_with_enum_class_schema.py b/genai/controlled_generation/ctrlgen_with_enum_class_schema.py
@@ -40,7 +40,6 @@ class InstrumentClass(enum.Enum):
     print(response.text)
     # Example output:
     # String
-
     # [END googlegenaisdk_ctrlgen_with_enum_class_schema]
     return response.text
 
diff --git a/genai/controlled_generation/ctrlgen_with_enum_schema.py b/genai/controlled_generation/ctrlgen_with_enum_schema.py
@@ -34,7 +34,6 @@ def generate_content() -> str:
     print(response.text)
     # Example output:
     # Woodwind
-
     # [END googlegenaisdk_ctrlgen_with_enum_schema]
     return response.text
 
diff --git a/genai/controlled_generation/ctrlgen_with_nested_class_schema.py b/genai/controlled_generation/ctrlgen_with_nested_class_schema.py
@@ -47,7 +47,6 @@ class Recipe(BaseModel):
     print(response.text)
     # Example output:
     # [{"rating": "a+", "recipe_name": "Classic Chocolate Chip Cookies"}, ...]
-
     # [END googlegenaisdk_ctrlgen_with_nested_class_schema]
     return response.text
 
diff --git a/genai/controlled_generation/ctrlgen_with_nullable_schema.py b/genai/controlled_generation/ctrlgen_with_nullable_schema.py
@@ -68,7 +68,6 @@ def generate_content() -> str:
     #   {"Day": "Thursday", "Forecast": "cloudy", "Temperature": 66, "Wind Speed": null, "Humidity": "60%"},
     #   {"Day": "Friday", "Forecast": "partly cloudy", "Temperature": 73, "Wind Speed": 12},
     #   {"Day": "Saturday", "Forecast": "sunny", "Temperature": 80, "Wind Speed": 8, "Humidity": "40%"}]}
-
     # [END googlegenaisdk_ctrlgen_with_nullable_schema]
     return response.text
 
diff --git a/genai/controlled_generation/requirements.txt b/genai/controlled_generation/requirements.txt
@@ -1 +1 @@
-google-genai==1.2.0
+google-genai==1.7.0
diff --git a/genai/count_tokens/counttoken_compute_with_txt.py b/genai/count_tokens/counttoken_compute_with_txt.py
@@ -25,15 +25,14 @@ def compute_tokens_example() -> int:
         model="gemini-2.0-flash-001",
         contents="What's the longest word in the English language?",
     )
-    print(response)
 
+    print(response)
     # Example output:
     # tokens_info=[TokensInfo(
     #    role='user',
     #    token_ids=[1841, 235303, 235256, 573, 32514, 2204, 575, 573, 4645, 5255, 235336],
     #    tokens=[b'What', b"'", b's', b' the', b' longest', b' word', b' in', b' the', b' English', b' language', b'?']
     #  )]
-
     # [END googlegenaisdk_counttoken_compute_with_txt]
     # [END googlegenaisdk_count_tokens_compute_with_txt]
     return response.tokens_info
diff --git a/genai/count_tokens/counttoken_resp_with_txt.py b/genai/count_tokens/counttoken_resp_with_txt.py
@@ -37,7 +37,6 @@ def count_tokens_example() -> int:
     #  candidates_token_count=311
     #  prompt_token_count=6
     #  total_token_count=317
-
     # [END googlegenaisdk_counttoken_resp_with_txt]
     # [END googlegenaisdk_count_tokens_resp_with_txt]
     return response.usage_metadata
diff --git a/genai/count_tokens/counttoken_with_txt.py b/genai/count_tokens/counttoken_with_txt.py
@@ -29,7 +29,6 @@ def count_tokens() -> int:
     # Example output:
     # total_tokens=10
     # cached_content_token_count=None
-
     # [END googlegenaisdk_counttoken_with_txt]
     # [END googlegenaisdk_count_tokens_with_txt]
     return response.total_tokens
diff --git a/genai/count_tokens/counttoken_with_txt_vid.py b/genai/count_tokens/counttoken_with_txt_vid.py
@@ -35,10 +35,8 @@ def count_tokens() -> int:
         contents=contents,
     )
     print(response)
-
     # Example output:
     # total_tokens=16252 cached_content_token_count=None
-
     # [END googlegenaisdk_counttoken_with_txt_vid]
     # [END googlegenaisdk_count_tokens_with_txt_img_vid]
     return response.total_tokens
diff --git a/genai/count_tokens/requirements.txt b/genai/count_tokens/requirements.txt
@@ -1 +1 @@
-google-genai==1.2.0
+google-genai==1.7.0
diff --git a/genai/embeddings/requirements.txt b/genai/embeddings/requirements.txt
@@ -1 +1 @@
-google-genai==1.2.0
+google-genai==1.7.0
diff --git a/genai/express_mode/api_key_example.py b/genai/express_mode/api_key_example.py
@@ -24,7 +24,7 @@ def generate_content() -> str:
 
     response = client.models.generate_content(
         model="gemini-2.0-flash-001",
-        contents="""Explain bubble sort to me.""",
+        contents="Explain bubble sort to me.",
     )
 
     print(response.text)
diff --git a/genai/express_mode/requirements.txt b/genai/express_mode/requirements.txt
@@ -1 +1 @@
-google-genai==1.2.0
+google-genai==1.7.0
diff --git a/genai/live/live_with_txt.py b/genai/live/live_with_txt.py
@@ -40,9 +40,7 @@ async def generate_content() -> list[str]:
         print("".join(response))
     # Example output:
     # >  Hello? Gemini, are you there?
-
     # Yes, I'm here. What would you like to talk about?
-
     # [END googlegenaisdk_live_with_txt]
     return response
 
diff --git a/genai/live/requirements.txt b/genai/live/requirements.txt
@@ -1 +1 @@
-google-genai==1.2.0
+google-genai==1.7.0
diff --git a/genai/provisioned_throughput/provisionedthroughput_with_txt.py b/genai/provisioned_throughput/provisionedthroughput_with_txt.py
@@ -15,7 +15,6 @@
 
 def generate_content() -> str:
     # [START googlegenaisdk_provisionedthroughput_with_txt]
-
     from google import genai
     from google.genai.types import HttpOptions
 
@@ -36,7 +35,6 @@ def generate_content() -> str:
         contents="How does AI work?",
     )
     print(response.text)
-
     # Example response:
     # Okay, let's break down how AI works. It's a broad field, so I'll focus on the ...
     #
diff --git a/genai/provisioned_throughput/requirements.txt b/genai/provisioned_throughput/requirements.txt
@@ -1 +1 @@
-google-genai==1.3.0
+google-genai==1.7.0
diff --git a/genai/safety/requirements.txt b/genai/safety/requirements.txt
@@ -1 +1 @@
-google-genai==1.2.0
+google-genai==1.7.0
diff --git a/genai/safety/safety_with_txt.py b/genai/safety/safety_with_txt.py
@@ -64,20 +64,51 @@ def generate_content() -> GenerateContentResponse:
 
     # Response will be `None` if it is blocked.
     print(response.text)
+    # Example response:
+    #     None
+
     # Finish Reason will be `SAFETY` if it is blocked.
     print(response.candidates[0].finish_reason)
-    # Safety Ratings show the levels for each filter.
-    for safety_rating in response.candidates[0].safety_ratings:
-        print(safety_rating)
-
     # Example response:
-    # None
-    # FinishReason.SAFETY
-    # blocked=None category=<HarmCategory.HARM_CATEGORY_HATE_SPEECH: 'HARM_CATEGORY_HATE_SPEECH'> probability=<HarmProbability.NEGLIGIBLE: 'NEGLIGIBLE'> probability_score=1.767152e-05 severity=<HarmSeverity.HARM_SEVERITY_NEGLIGIBLE: 'HARM_SEVERITY_NEGLIGIBLE'> severity_score=None
-    # blocked=None category=<HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT: 'HARM_CATEGORY_DANGEROUS_CONTENT'> probability=<HarmProbability.NEGLIGIBLE: 'NEGLIGIBLE'> probability_score=2.399503e-06 severity=<HarmSeverity.HARM_SEVERITY_NEGLIGIBLE: 'HARM_SEVERITY_NEGLIGIBLE'> severity_score=0.061250776
-    # blocked=True category=<HarmCategory.HARM_CATEGORY_HARASSMENT: 'HARM_CATEGORY_HARASSMENT'> probability=<HarmProbability.MEDIUM: 'MEDIUM'> probability_score=0.64129734 severity=<HarmSeverity.HARM_SEVERITY_MEDIUM: 'HARM_SEVERITY_MEDIUM'> severity_score=0.2686556
-    # blocked=None category=<HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT: 'HARM_CATEGORY_SEXUALLY_EXPLICIT'> probability=<HarmProbability.NEGLIGIBLE: 'NEGLIGIBLE'> probability_score=5.2786977e-06 severity=<HarmSeverity.HARM_SEVERITY_NEGLIGIBLE: 'HARM_SEVERITY_NEGLIGIBLE'> severity_score=0.043162167
+    #     FinishReason.SAFETY
 
+    # For details on all the fields in the response
+    for each in response.candidates[0].safety_ratings:
+        print('\nCategory: ', str(each.category))
+        print('Is Blocked:', True if each.blocked else False)
+        print('Probability: ', each.probability)
+        print('Probability Score: ', each.probability_score)
+        print('Severity:', each.severity)
+        print('Severity Score:', each.severity_score)
+    # Example response:
+    #
+    #     Category:  HarmCategory.HARM_CATEGORY_HATE_SPEECH
+    #     Is Blocked: False
+    #     Probability:  HarmProbability.NEGLIGIBLE
+    #     Probability Score:  2.547714e-05
+    #     Severity: HarmSeverity.HARM_SEVERITY_NEGLIGIBLE
+    #     Severity Score: None
+    #
+    #     Category:  HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT
+    #     Is Blocked: False
+    #     Probability:  HarmProbability.NEGLIGIBLE
+    #     Probability Score:  3.6103818e-06
+    #     Severity: HarmSeverity.HARM_SEVERITY_NEGLIGIBLE
+    #     Severity Score: None
+    #
+    #     Category:  HarmCategory.HARM_CATEGORY_HARASSMENT
+    #     Is Blocked: True
+    #     Probability:  HarmProbability.MEDIUM
+    #     Probability Score:  0.71599233
+    #     Severity: HarmSeverity.HARM_SEVERITY_MEDIUM
+    #     Severity Score: 0.30782545
+    #
+    #     Category:  HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT
+    #     Is Blocked: False
+    #     Probability:  HarmProbability.NEGLIGIBLE
+    #     Probability Score:  1.5624657e-05
+    #     Severity: HarmSeverity.HARM_SEVERITY_NEGLIGIBLE
+    #     Severity Score: None
     # [END googlegenaisdk_safety_with_txt]
     return response
 
diff --git a/genai/template_folder/requirements.txt b/genai/template_folder/requirements.txt
@@ -1 +1 @@
-google-genai==1.2.0
+google-genai==1.7.0
diff --git a/genai/text_generation/requirements.txt b/genai/text_generation/requirements.txt
@@ -1 +1 @@
-google-genai==1.3.0
+google-genai==1.7.0
diff --git a/genai/text_generation/textgen_chat_stream_with_txt.py b/genai/text_generation/textgen_chat_stream_with_txt.py
@@ -19,10 +19,10 @@ def generate_content() -> str:
     from google.genai.types import HttpOptions
 
     client = genai.Client(http_options=HttpOptions(api_version="v1"))
-    chat = client.chats.create(model="gemini-2.0-flash-001")
+    chat_session = client.chats.create(model="gemini-2.0-flash-001")
     response_text = ""
 
-    for chunk in chat.send_message_stream("Why is the sky blue?"):
+    for chunk in chat_session.send_message_stream("Why is the sky blue?"):
         print(chunk.text, end="")
         response_text += chunk.text
     # Example response:
diff --git a/genai/text_generation/textgen_chat_with_txt.py b/genai/text_generation/textgen_chat_with_txt.py
diff --git a/genai/tools/requirements.txt b/genai/tools/requirements.txt
diff --git a/genai/tools/tools_code_exec_with_txt.py b/genai/tools/tools_code_exec_with_txt.py
diff --git a/genai/tools/tools_func_desc_with_txt.py b/genai/tools/tools_func_desc_with_txt.py
diff --git a/genai/video_generation/requirements.txt b/genai/video_generation/requirements.txt
diff --git a/model_garden/anthropic/requirements.txt b/model_garden/anthropic/requirements.txt

Original file line number	Diff line number	Diff line change
`@@ -1 +1 @@`
`1`		`-google-genai==1.2.0`
	`1`	`+google-genai==1.7.0`
Original file line number	Diff line number	Diff line change
`@@ -1,2 +1,2 @@`
`1`		`-google-genai==1.2.0`
	`1`	`+google-genai==1.7.0`
`2`	`2`	`pillow==11.1.0`