refactor: (GenAI) Reorganized Video Samples (Group C) (GoogleCloudPlatform#12644)

Thoughtseize1 · web-flow · commit 9432a78c962c · 2024-10-08T14:29:42.000+02:00
* Reorganized Video Samples
diff --git a/generative_ai/test_gemini_examples.py b/generative_ai/test_gemini_examples.py
@@ -97,6 +97,7 @@ def test_gemini_safety_config_example() -> None:
     assert len(text) > 0
 
 
+# Delete after approval /understand_video/single_turn_video_example.py
 def test_gemini_single_turn_video_example() -> None:
     text = gemini_single_turn_video_example.generate_text()
     text = text.lower()
@@ -138,6 +139,7 @@ def test_transcript_audio() -> None:
     assert len(text) > 0
 
 
+# Delete after approval /understand_video/audio_video_example.py
 def test_analyze_video_with_audio() -> None:
     text = gemini_video_audio.analyze_video_with_audio()
     assert len(text) > 0
diff --git a/generative_ai/understand_video/audio_video_example.py b/generative_ai/understand_video/audio_video_example.py
@@ -0,0 +1,58 @@
+# Copyright 2024 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+import os
+
+PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
+
+
+def analyze_video_with_audio() -> str:
+    # [START generativeaionvertexai_gemini_video_with_audio]
+
+    import vertexai
+    from vertexai.generative_models import GenerativeModel, Part
+
+    # TODO(developer): Update and un-comment below line
+    # PROJECT_ID = "your-project-id"
+
+    vertexai.init(project=PROJECT_ID, location="us-central1")
+
+    model = GenerativeModel("gemini-1.5-flash-002")
+
+    prompt = """
+    Provide a description of the video.
+    The description should also contain anything important which people say in the video.
+    """
+
+    video_file = Part.from_uri(
+        uri="gs://cloud-samples-data/generative-ai/video/pixel8.mp4",
+        mime_type="video/mp4",
+    )
+
+    contents = [video_file, prompt]
+
+    response = model.generate_content(contents)
+    print(response.text)
+    # Example response:
+    # Here is a description of the video.
+    # ... Then, the scene changes to a woman named Saeko Shimada..
+    # She says, "Tokyo has many faces. The city at night is totally different
+    # from what you see during the day."
+    # ...
+
+    # [END generativeaionvertexai_gemini_video_with_audio]
+    return response.text
+
+
+if __name__ == "__main__":
+    analyze_video_with_audio()
diff --git a/generative_ai/understand_video/single_turn_video_example.py b/generative_ai/understand_video/single_turn_video_example.py
@@ -0,0 +1,53 @@
+# Copyright 2024 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+import os
+
+PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
+
+
+def generate_text() -> str:
+    # [START generativeaionvertexai_gemini_single_turn_video]
+    import vertexai
+
+    from vertexai.generative_models import GenerativeModel, Part
+
+    # TODO(developer): Update and un-comment below line
+    # PROJECT_ID = "your-project-id"
+
+    vertexai.init(project=PROJECT_ID, location="us-central1")
+
+    vision_model = GenerativeModel("gemini-1.5-flash-002")
+
+    # Generate text
+    response = vision_model.generate_content(
+        [
+            Part.from_uri(
+                "gs://cloud-samples-data/video/animals.mp4", mime_type="video/mp4"
+            ),
+            "What is in the video?",
+        ]
+    )
+    print(response.text)
+    # Example response:
+    # Here's a summary of the video's content.
+    # The video shows a series of animals at the Los Angeles Zoo interacting
+    # with waterproof cameras attached to various devices.
+    # ...
+
+    # [END generativeaionvertexai_gemini_single_turn_video]
+    return response.text
+
+
+if __name__ == "__main__":
+    generate_text()
diff --git a/generative_ai/understand_video/understand_video_test.py b/generative_ai/understand_video/understand_video_test.py
@@ -0,0 +1,30 @@
+# Copyright 2024 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import audio_video_example
+import single_turn_video_example
+
+
+def test_analyze_video_with_audio() -> None:
+    text = audio_video_example.analyze_video_with_audio()
+    assert len(text) > 0
+
+
+def test_gemini_single_turn_video_example() -> None:
+    text = single_turn_video_example.generate_text()
+    text = text.lower()
+    assert len(text) > 0
+    assert any(
+        [_ in text for _ in ("zoo", "tiger", "leaf", "water", "animals", "photos")]
+    )
