- Support for multi-modal models using attachments in [LLM 0.17a0](https://llm.datasette.io/en/latest/changelog.html#a0-2024-10-28).
0.2
- Added support for the inexpensive [new Gemini 1.5 Flash-8B](https://developers.googleblog.com/en/gemini-15-flash-8b-is-now-generally-available-for-use/): `llm -m gemini-1.5-flash-8b-latest "say hi"` [#14](https://github.com/simonw/llm-gemini/issues/14) - First non-alpha release.
0.1a5
- New Gemini 001 and 002 models.
0.1a4
- Added support for the new [Gemini 1.5 Flash](https://deepmind.google/technologies/gemini/flash/) model. `llm -m gemini-1.5-flash-latest 'a short poem about otters'` [#9](https://github.com/simonw/llm-gemini/issues/9)
0.1a3
- Support for the `text-embedding-004` embedding model: `llm embed -m text-embedding-004 -c 'hello world'`. [7](https://github.com/simonw/llm-gemini/issues/7)
0.1a2
- Support for system instructions: `llm -m p15 'say hi three times three different ways' --system 'in german'`. [6](https://github.com/simonw/llm-gemini/issues/6)