-
Notifications
You must be signed in to change notification settings - Fork 7.3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Update model to 1.5-pro #1611
Update model to 1.5-pro #1611
Conversation
// Initialize a GenerativeModel with the `gemini-pro` AI model | ||
// for multimodal text generation | ||
val generativeModel = Firebase.vertexAI.generativeModel( | ||
modelName = "gemini-1.0-pro-vision", | ||
modelName = "gemini-1.5-pro-preview-0409", | ||
generationConfig = config | ||
) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
At this point I think we can initialize the model once (like before the return clause) and then pass to every ViewModel. The reason why I had different initializations was because of gemini-pro-vision
. But now that we use the same model for every use case, maybe we could simplify our code?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think anyway the model going to be same so their can focus on which is appropriate for use is necessary to add.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'll merge as is for now. We can discuss code reuse in a separate space. :)
* feat: add vertexai quickstart app * style: run ktlint * chore: add vertex ai to mock-google-services.json * add Vertex AI link to main README file * bump gradle to 8.6 * Remove properties not supported by java 17 (#1612) * Update model to 1.5-pro (#1611) --------- Co-authored-by: Rodrigo Lazo <rlazo@users.noreply.github.com>
No description provided.