feat: VAIS Web Result Summarize using Gemini Notebook

[nshivhar]

Description

Thank you for opening a Pull Request!
Before submitting your PR, there are a few things you can do to make sure it goes smoothly:

• Follow the CONTRIBUTING Guide.
• You are listed as the author in your notebook or README file.
  • Your account is listed in CODEOWNERS for the file(s).
• Make your Pull Request title in the https://www.conventionalcommits.org/ specification.
• Ensure the tests and linter pass (Run nox -s format from the repository root to format).
• Appropriate docs were updated (if necessary)

Fixes #<issue_number_goes_here> 🦕

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[holtskinner]

We have some notebooks already with similar workflows here https://github.com/GoogleCloudPlatform/generative-ai/tree/main/search/retrieval-augmented-generation/examples

Could you see about adding this to the Question Answering Notebook? Or maybe the RAG Google Documentation one?

[nshivhar]

We have some notebooks already with similar workflows here https://github.com/GoogleCloudPlatform/generative-ai/tree/main/search/retrieval-augmented-generation/examples

Could you see about adding this to the Question Answering Notebook? Or maybe the RAG Google Documentation one?

Hi Holt,

Thank you for reviewing this pull request and for your feedback.

The notebook differs from the typical RAG workflow. In this implementation, I am using the Discovery Engine API to connect to a Vertex AI Search website datastore. It fetches matching results for a user query and extracts the top result URL. The workflow then makes an HTTP request to the URL to retrieve the webpage content, which is sent to Gemini for summarization. This approach does not rely on advanced indexing of the webpage.

Given its alignment with Vertex AI Search workflows, I felt it was more suitable to place it under the search folder. However, if you believe it would be better suited under the Question Answering or RAG Google Documentation folders, I’m happy to move it there.

Please let me know your thoughts. I appreciate your insights and guidance.

Thank you again for your feedback! @holtskinner