fix: Update GetTokenCount.java

[davenportjw]

Description

Fixes #

Note: Before submitting a pull request, please open an issue for discussion if you are not associated with Google.

Checklist

• I have followed Sample Format Guide
• pom.xml parent set to latest shared-configuration
• Appropriate changes to README are included in PR
• 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)
• Tests pass: mvn clean verify required
• Lint passes: mvn -P lint checkstyle:check required
• Static Analysis: mvn -P lint clean compile pmd:cpd-check spotbugs:check advisory only
• 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 2 region tags.

• vertexai/snippets/src/main/java/vertexai/gemini/GetTokenCount.java:20, tag generativeaionvertexai_gemini_token_count
• vertexai/snippets/src/main/java/vertexai/gemini/GetTokenCount.java:40, tag generativeaionvertexai_gemini_token_count

---

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

[minherz]

please, ensure that PR pass all checks

[minherz]

nit: is there a reason to duplicate region tags?

[iennae]

@minherz the wrong region tag was used; correct region tag is the generativeai one. Once the region tag has been updated, doc CL would be issued and then the original region tag can be removed.

[minherz]

In my experience this approach results in redundant and incorrect region tags in the code samples. It is because there is no good way to track documentation CL and following changes.. 🙁
If this code sample should not be used for aiplatform why not to remove the region tag now?
Alternatively why not to batch replacing the region tags to the doc CL?

[davenportjw]

i dont understand the 'no good way to track comment'. can you please elaborate?

[iennae]

@davenportjw any idea why change in model name might cause the error

tmpfs/docker/overlay2/85ba26e363cfea28217e7dc8e3c0363a0d8f95a8c884410d2f380c5b415db5f2/merged/sys/fs/cgroup/cpuset.
[ERROR] Tests run: 21, Failures: 0, Errors: 3, Skipped: 1, Time elapsed: 1,210.961 s <<< FAILURE! - in vertexai.gemini.SnippetsIT
[ERROR] vertexai.gemini.SnippetsIT.testMultimodalQuery Time elapsed: 591.885 s <<< ERROR!
java.lang.IllegalArgumentException: The response is blocked due to unauthorized citations.

[minherz]

@davenportjw any idea why change in model name might cause the error

It looks like you need to revise the input or to adjust the safety settings by updating the model with:

  SafetySetting safetySettings = SafetySetting.newBuilder()
         .setThreshold(SafetySetting.HarmBlockThreshold.BLOCK_NONE)
         .build();
  GenerativeModel model = new GenerativeModel(modelName, vertexAI)
         .withSafetySettings(safetySettings);