Explore Generative AI with the Gemini API in Vertex AI: Challenge Lab Reviews

Atul P. · Reviewed 4 months ago

Mahesh Kumar P. · Reviewed 4 months ago

mahesh kumar p. · Reviewed 4 months ago

将秀 高. · Reviewed 4 months ago

Rajesh S. · Reviewed 4 months ago

将秀 高. · Reviewed 4 months ago

Harish K. · Reviewed 4 months ago

Rodolfo R. · Reviewed 4 months ago

Oleksandr V. · Reviewed 4 months ago

Mohd M. · Reviewed 4 months ago

quik G. · Reviewed 4 months ago

Mohd M. · Reviewed 4 months ago

Afashan siddiqui G. · Reviewed 4 months ago

derek d. · Reviewed 4 months ago

Takao S. · Reviewed 4 months ago

信吾 古. · Reviewed 4 months ago

Still really bad. still getting 500 but using different models worked.

Daniel M. · Reviewed 4 months ago

Got InternalServerError for Task 3 response generation for video content

Rishi Yash P. · Reviewed 4 months ago

BHASKAR B. · Reviewed 4 months ago

Nothing works.

Daniel M. · Reviewed 4 months ago

Checks will not pass after completing the tasks

Will N. · Reviewed 4 months ago

https://github.com/google-gemini/generative-ai-python/issues/467

Joao P. · Reviewed 4 months ago

Aldair de Luis D. · Reviewed 4 months ago

Seems like Task 2 isn't finished. It only goes to getting the function that needs to be called but doesn't show the function calling code. # Task 3.2 Generate a video description # In this cell, update the prompt to ask Gemini to describe the video URL referenced. # You can use the documentation at the following link to assist. # https://cloud.google.com/vertex-ai/docs/generative-ai/multimodal/sdk-for-gemini/gemini-sdk-overview-reference#generate-content-from-video # # Video URI: gs://github-repo/img/gemini/multimodality_usecases_overview/mediterraneansea.mp4 # prompt = """ What is shown in this video? Where should I go to see it? What are the top 5 places in the world that look like this? """ video = Part.from_uri( uri="gs://github-repo/img/gemini/multimodality_usecases_overview/mediterraneansea.mp4", mime_type="video/mp4", ) contents = [video, prompt] responses = multimodal_model.generate_content(contents, stream=True) print("-------Prompt--------") print_multimodal_prompt(contents) print("\n-------Response--------") for response in responses: print(response.text, end="")

Daniel M. · Reviewed 4 months ago

Rodrigo A. · Reviewed 4 months ago