feat(vertexai): Non-stream basic text sample

[ianlewis]

Description

Go version of the Python sample at
https://github.com/GoogleCloudPlatform/python-docs-samples/blob/main/generative_ai/inference/non_stream_text_basic.py

Region tag generativeaionvertexai_non_stream_text_basic.

Checklist

• I have followed Contributing Guidelines from CONTRIBUTING.MD
• Tests pass: go test -v ./.. (see Testing)
• Code formatted: gofmt (see Formatting)
• Vetting pass: go vet (see Formatting)
• These samples need a new API enabled in testing projects to pass (let us know which ones)
• These samples need a new/updated env vars in testing projects set to pass (let us know which ones)
• This sample adds a new sample directory, and I updated the CODEOWNERS file with the codeowners for this sample
• This sample adds a new Product API, and I updated the Blunderbuss issue/PR auto-assigner with the codeowners for this sample
• Please merge this PR for me once it is approved

[snippet-bot]

Here is the summary of changes.

You are about to add 1 region tag.

• vertexai/non-stream-text-basic/nonstreamtextbasic.go:17, tag generativeaionvertexai_non_stream_text_basic

---

This comment is generated by snippet-bot.
If you find problems with this result, please file an issue at:
https://github.com/googleapis/repo-automation-bots/issues.
To update this comment, add snippet-bot:force-run label or use the checkbox below:

• Refresh this comment

[grayside]

This sample is LGTM, but before approving I wanted to confirm we should create this sample instead of somehow reuse https://github.com/GoogleCloudPlatform/golang-samples/blob/main/vertexai/snippets/text_input.go#L16, which seems very similar. @gericdong

[Deleplace]

We're leaning towards reusing the existing code samples, when possible

[ianlewis]

This sample is LGTM, but before approving I wanted to confirm we should create this sample instead of somehow reuse https://github.com/GoogleCloudPlatform/golang-samples/blob/main/vertexai/snippets/text_input.go#L16, which seems very similar. @gericdong

I think the page contexts are a bit different, the sample on the quickstarts page looks like it should support replacing the PROJECT_ID like the Python sample does.

However, I kind of agree that the inference API samples and these quickstart samples could probably just be reused.
https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#non-stream-text

[ianlewis]

I do wonder about the difference in structure for the prompt passed to generateContent in the Quickstart Node.js sample and the model inference API reference Node.js sample but I based on the surrounding docs it doesn't seem germane.

I propose that we just use the quickstart samples for text-only and audio and video on the model inference page for non-streaming text and non-streaming multimodal samples.

Though I think we will need to have streaming examples on the model inference page. WDUT? @grayside @gericdong

[gericdong]

@ianlewis I agree with your assessment. Thanks.

[ianlewis]

Closing. Will submit changes to the doc to reuse the existing samples.