Google-generativeai

Adds the `Content` family of methods to support Gemini models.

- Handle maximum batch size for `embed_text`.
- Restore `types.ModelNameOptions`.
- Update tuning to handle more dataset types (json, pandas, urls, google-sheets).
- Expose `count_text_tokens`
- Expose operations management.
- Allow users to pass custom `metadata` (HTML headers).
- Add dataclass prettyprinting.

- Bugfix: Add missing enum names to `saftey_types.py`
- Update to `google.ai.generativelanguage` v0.3.3
- replace generativelanguage_v1beta3 with generativelanguage
since that's the default in `v0.3.3`.

* Add support for tuning:
* Add get_tuned_model.
* Add list_tuned_models.
* Add create_tuned_model.
* More flexible safety settings:
* Accept strings and ints for enums.
* Accept a {category:threshold} dict in addition to the list of dicts format (`[{"category": category, "threshold": threshold}, ...]`).
* Add support for batched embeddings.

* First real release.
* Support for text generation, chat and embeddings.