feat: add 2 more textgen samples to the batch

Author: Valeriy-Burlaka

genai/text_generation/test_text_generation.py

@@ -12,12 +12,22 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import os
+
+import textgen_transcript_with_gcs_audio
+import textgen_with_gcs_audio
 import textgen_with_multi_img
 import textgen_with_multi_local_img
 import textgen_with_mute_video
 import textgen_with_video
 
 
+os.environ["GOOGLE_GENAI_USE_VERTEXAI"] = "True"
+os.environ["GOOGLE_CLOUD_LOCATION"] = "us-central1"
+# The project name is included in the CICD pipeline
+# os.environ['GOOGLE_CLOUD_PROJECT'] = "add-your-project-name"
+
+
 def test_textgen_with_multi_img() -> None:
     response = textgen_with_multi_img.generate_content()
     assert response
@@ -36,3 +46,13 @@ def test_textgen_with_mute_video() -> None:
 def test_textgen_with_video() -> None:
     response = textgen_with_video.generate_content()
     assert response
+
+
+def test_textgen_with_gcs_audio() -> None:
+    response = textgen_with_gcs_audio.generate_content()
+    assert response
+
+
+def test_textgen_transcript_with_gcs_audio() -> None:
+    response = textgen_transcript_with_gcs_audio.generate_content()
+    assert response

genai/text_generation/textgen_transcript_with_gcs_audio.py

@@ -0,0 +1,49 @@
+# Copyright 2025 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.
+
+
+def generate_content() -> str:
+    # [START googlegenaisdk_textgen_transcript_with_gcs_audio]
+    from google import genai
+    from google.genai.types import Part
+
+    client = genai.Client()
+
+    prompt = """
+    Transcribe the interview, in the format of timecode, speaker, caption.
+    Use speaker A, speaker B, etc. to identify speakers.
+    """
+    response = client.models.generate_content(
+        model="gemini-2.0-flash-001",
+        contents=[
+            prompt,
+            Part.from_uri(
+                "gs://cloud-samples-data/generative-ai/audio/pixel.mp3",
+                mime_type="audio/mpeg"
+            )
+        ]
+    )
+    print(response.text)
+    # Example response:
+    # [00:00:00] **Speaker A:** your devices are getting better over time. And so ...
+    # [00:00:14] **Speaker B:** Welcome to the Made by Google podcast where we meet ...
+    # [00:00:20] **Speaker B:** Here's your host, Rasheed Finch.
+    # [00:00:23] **Speaker C:** Today we're talking to Aisha Sharif and DeCarlos Love. ...
+    # ...
+    # [END googlegenaisdk_textgen_transcript_with_gcs_audio]
+    return response.text
+
+
+if __name__ == "__main__":
+    generate_content()

genai/text_generation/textgen_with_gcs_audio.py

@@ -0,0 +1,52 @@
+# Copyright 2025 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.
+
+
+def generate_content() -> str:
+    # [START googlegenaisdk_textgen_with_gcs_audio]
+    from google import genai
+    from google.genai.types import Part
+
+    client = genai.Client()
+
+    prompt = """
+    Provide the summary of the audio file.
+    Summarize the main points of the audio concisely.
+    Create a chapter breakdown with timestamps for key sections or topics discussed.
+    """
+    response = client.models.generate_content(
+        model="gemini-2.0-flash-001",
+        contents=[
+            prompt,
+            Part.from_uri(
+                "gs://cloud-samples-data/generative-ai/audio/pixel.mp3",
+                mime_type="audio/mpeg"
+            )
+        ]
+    )
+    print(response.text)
+    # Example response:
+    # This episode of the Made by Google podcast features product managers ...
+    #
+    # **Chapter Breakdown:**
+    #
+    # * **[0:00-1:14] Introduction:** Host Rasheed Finch introduces Aisha and DeCarlos and ...
+    # * **[1:15-2:44] Transformative Features:** Aisha and DeCarlos discuss their ...
+    # ...
+    # [END googlegenaisdk_textgen_with_gcs_audio]
+    return response.text
+
+
+if __name__ == "__main__":
+    generate_content()