Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add notebook on grounding with Vertex AI Agent Builder #472

Merged
merged 5 commits into from
Aug 5, 2024

Conversation

sanjanalreddy
Copy link
Collaborator

This notebook adds a how to use Vertex Agent Builder and ground responses using the PaLM model.

Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

@@ -0,0 +1,414 @@
{
Copy link
Collaborator

@BenoitDherin BenoitDherin May 22, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

  • The link "Vertex AI Agent Builder" goes to vertex search. Is that intended?
  • Something off with the sentence "By grounding model responses in data stores within Vertex AI Agent Builder, LLMs that are grounded in data can produce more accurate, up-to-date, and relevant responses." Maybe delete "that are grounded in data"

Reply via ReviewNB

@@ -0,0 +1,414 @@
{
Copy link
Collaborator

@BenoitDherin BenoitDherin May 22, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

  • Is it feasible to add a programatic version to these UI instructions? I think both are valuable.
  • In the instructions, I'd suggest concrete values to input: e.g. "enter the name of your app" --> "enter the name of your app (for example: Google Store App)
  • Maybe specify what "advanced website indexing" is and why we need to turn it off. Same thing for "Advanced LLM features"

Reply via ReviewNB

@@ -0,0 +1,414 @@
{
Copy link
Collaborator

@BenoitDherin BenoitDherin May 22, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It would be nice if we could retrieve DATA_STORE_ID programmatically if that's feasible.


Reply via ReviewNB

@@ -0,0 +1,414 @@
{
Copy link
Collaborator

@BenoitDherin BenoitDherin May 22, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I am not seeing any tools keyword arg in the cell below, only a goundig_source arg. Typo?


Reply via ReviewNB

@BenoitDherin BenoitDherin self-requested a review May 22, 2024 23:24
Copy link
Collaborator

@BenoitDherin BenoitDherin left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LTGM. See a few suggestions.

@takumiohym
Copy link
Collaborator

@sanjanalreddy Would you make this PR draft so far?

@sanjanalreddy
Copy link
Collaborator Author

@takumiohym I'm merging this PR. Benoit and I need this lab for an upcoming cohort and it seems to be working well now.

@sanjanalreddy sanjanalreddy merged commit dee223d into master Aug 5, 2024
5 checks passed
@sanjanalreddy sanjanalreddy deleted the agent_builder branch August 5, 2024 16:40
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants