feat(generative-ai): Add compute token examples

[msampathkumar]

Add list_tokens_example

Description

Fixes b358102024

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

Checklist

• I have followed Sample Guidelines from AUTHORING_GUIDE.MD
• README is updated to include all relevant information
• Tests pass: nox -s py-3.9 (see Test Environment Setup)
• Lint pass: nox -s lint (see Test Environment Setup)
• 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 5 region tags.

• generative_ai/count_token/api_example.py:20, tag generativeaionvertexai_token_count_sample_with_genai
• generative_ai/count_token/list_tokens_example.py:20, tag generativeaionvertexai_compute_tokens
• generative_ai/count_token/local_sdk_example.py:17, tag generativeaionvertexai_token_count_sample_with_local_sdk
• generative_ai/count_token/multimodal_example.py:22, tag generativeaionvertexai_gemini_token_count_multimodal
• generative_ai/count_token/simple_example.py:22, tag generativeaionvertexai_gemini_token_count

You are about to delete 4 region tags.

• generative_ai/token_count/api_example.py:20, tag generativeaionvertexai_token_count_sample_with_genai
• generative_ai/token_count/local_sdk_example.py:17, tag generativeaionvertexai_token_count_sample_with_local_sdk
• generative_ai/token_count/multimodal_token_count_example.py:22, tag generativeaionvertexai_gemini_token_count_multimodal
• generative_ai/token_count/simple_example.py:22, 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

[msampathkumar]

CICD error google.api_core.exceptions.ResourceExhausted: 429 Resource exhausted.

Need to re-try after sometime.

[davidcavazos]

It's running 148 tests every time changes get pushed, which might explain the resource exhausted errors. It looks like it's running everything under generative_ai/ because the noxfile_config.py is located there. To avoid running everything, try adding a noxfile_config.py along with the necessary requirements.txt and requirements-test.txt under generative_ai/count_token/. That way you can also trim down the dependencies for that specific directory.

It would be nice to do the same for all the other subdirectories too. That would avoid running so many redundant tests and would lower resource usage.

[msampathkumar]

@davidcavazos - Thank you for the detailed steps. Will do as suggested. We are currently working on re-organising the samples into feature folder. go/runnable-snippets-execute

It's running 148 tests every time changes get pushed, which might explain the resource exhausted errors. It looks like it's running everything under generative_ai/ because the noxfile_config.py is located there. To avoid running everything, try adding a noxfile_config.py along with the necessary requirements.txt and requirements-test.txt under generative_ai/count_token/. That way you can also trim down the dependencies for that specific directory.

It would be nice to do the same for all the other subdirectories too. That would avoid running so many redundant tests and would lower resource usage.

[davidcavazos]

@msampathkumar thanks for providing the local directory test config. It looks like it's still running everything, not your fault.

After closer inspection at the code that detects the test package directory, it looks like it dives deeper from the repo root directory until it finds a requirements.txt file. I would have imagined it would bubble up from the diffs it found, so it'll keep running everything until the generative_ai/requirements.txt file is gone.

btlr run --max-cmd-duration=60m **/requirements.txt --git-diff origin/main... . -- /workspace/.kokoro/tests/run_single_test.sh

https://github.com/googleapis/btlr/blob/main/cmd/run.go#L325 <- finds most general instead of most specific

[msampathkumar]

All count token related tests are passing. Error are related to Embedding and FunctionCalling. Re-running the test

[msampathkumar]

Function calling code sample is failing repeatedly for 002 version and so using 001

[msampathkumar]

Raising fresh independent PRs

[msampathkumar]

#12684

#12683