Update anomaly_detection to sync with genai generate_embedding method

[BichengWang]

Description of the change

Update anomaly_detection to sync genai generate_embedding method:

• update method
• update embedding model

Motivation

The original method deprecated by genai and less runnable

Type of change

Choose one: (Bug fix)

Checklist

• [x ] I have performed a self-review of my code.
• [x ] I have added detailed comments to my code where applicable.
• [x ] I have verified that my change does not break existing code.
• [x ] My PR is based on the latest changes of the main branch (if unsure, please run git pull --rebase upstream main).
• [x ] I am familiar with the Google Style Guide for the language I have coded in.
• [x ] I have read through the Contributing Guide and signed the Contributor License Agreement.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[markmcd]

This change looks like it reverts the Gemini API to use the (deprecated) PaLM API. Is that intentional? Can you provide any more context?

[BichengWang]

This change looks like it reverts the Gemini API to use the (deprecated) PaLM API. Is that intentional? Can you provide any more context?

Error:
AttributeError: module 'google.generativeai' has no attribute 'embed_content'
Env:
google-generativeai==.07.2, python=3.9.19
Alternative replacement plan as above.

@markmcd

[markmcd]

The code in the notebook works as expected. If you can provide a repro case showing how it fails then please do so (in a bug would be appropriate). Any fix should use the Gemini API, not the deprecated PaLM API.

>>> import google.generativeai as genai
>>> genai.__version__
'0.7.2'
>>> r = genai.embed_content(model='models/embedding-001', content='the quick brown fox', task_type='clustering')
>>> len(r['embedding'])
768
>>> r['embedding'][:10]
[0.037379164, -0.042748366, -0.029110689, -0.042224124, 0.037183076, -0.0256457, -0.01939054, 0.015298519, 0.048082795, -0.019906988]