feat: Hardcoded samples to be migrated - Text Translation Samples

[Thoughtseize1]

Description

4 Samples for this page:

• translate_v3_translate_text.py ✅
• translate_with_gemini.py ✅
• translate_with_llm.py ❌ Errors - Errors - Old approach
• translate_with_custom translations.py ❌ Errors - Errors - Old approach

Checklist

• [x] I have followed Sample Guidelines from AUTHORING_GUIDE.MD
• [ ] README is updated to include all relevant information
• [x] Tests pass: nox -s py-3.9 (see Test Environment Setup)
• [x] 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
• [x] Please merge this PR for me once it is approved

[Thoughtseize1]

All new files without tests yet

Samples for this page

I have issues with two files that use the endpoint and predict methods, specifically when working with the Vertex AI API and translation LLM and Custom translations. Both examples are designed to use an endpoint. However, when I try to replicate the sample code, I encounter the following error: ValueError: Resource projects/PROJECT/locations/us-central1/publishers/google/models/text-translation is not a valid resource ID.

Indeed, such an endpoint does not exist, and the model is not deployed there. When I attempt to use an existing endpoint with a deployed model (for example, I used code-bison since it was already deployed on my endpoint), everything works fine.

Additionally, the existing Text Translation model has a different Model ID: publishers/google/models/text-translation. It also doesn't seem like this model ID can be used with the endpoint.

How should I proceed? Which endpoint should be used in this scenario?

Furthermore, I made an assumption and created a file translate_with_llm_example.py, where I outlined how I envision using a specific endpoint from the list with the client. Could you please advise on the correct approach?

[Thoughtseize1]

🔷 First Sample with problem - translate_with_llm.py

🔷 Second Sample with problem - translate_with_custom translations.py

[snippet-bot[bot]]

Here is the summary of changes.

You are about to add 1 region tag.

- [translate/samples/snippets/translate_with_gemini.py:15](https://github.com/GoogleCloudPlatform/python-docs-samples/blob/ceffd285f1bf2ad74353c6b1dbbb382110b214dc/translate/samples/snippets/translate_with_gemini.py#L15), tag `aiplatform_gemini_translate`

---

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

[Thoughtseize1]

The decision was made to leave only work samples and update this documentation page.

• translate_v3_translate_text.py ✅
• translate_with_gemini.py ✅