Mark Daoust
Mark Daoust
Yeah, this API is related, but separate from vertex. Hopefully this API will catch up soon.
This is fixed in the latest version: code: https://github.com/google-gemini/generative-ai-python/pull/561 tutorial: https://github.com/google-gemini/cookbook/blob/main/quickstarts/New_in_002.ipynb
> but it'd be nice if both the dict & DC params were tested explicitly Done.
This is fixed.
Right, sometimes the model doesn't return any text. `result.parts` or `result.candidates` will show you what it did return. You can check `response.prompt_feedback` to see if it had a problem with...
Right, there are a few ways that it can fail top return text. Look at `result.prompt_feedback` and `result.candidates[0]`, they will give youy mopre information about what went wrong.
TypedDict and Dataclass
Fixed in https://github.com/google-gemini/generative-ai-python/pull/230
I've seen this, but don't have steps to reproduce it. I think this had something to do with the namespace package configuration: https://github.com/google-gemini/generative-ai-python/commit/b28f2d1395d888fe149a031afbec359e1b523f8e Does this still happen for anyone, with...
Yeah, UsageMetadata was not ready to release at that time. It should work now. https://github.com/google-gemini/generative-ai-python/pull/315 For the question of price see https://ai.google.dev/pricing