Skip to content
Closed
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -119,9 +119,12 @@ python main.py --query="Go to Google and type 'Hello World' into the search bar"

**Available Models:**

You can choose the model to use by specifying the ```--model <model name>``` flag. Available options:

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Motorola Edge 60pro

You can choose the model to use by specifying the ```--model <model name>``` flag. Available options on Gemini Developer API and Vertex AI Client:

- `gemini-2.5-computer-use-preview-10-2025`: This is the default model.

Available options on Gemini Developer API only:

- `gemini-3-flash-preview`: The preview version of Gemini 3 Flash.
- `gemini-3-pro-preview`: The preview version of Gemini 3 Pro.
Comment on lines +122 to 129
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

This is a helpful clarification in the documentation. However, it highlights an inconsistency with the current implementation in main.py. The code doesn't prevent a user from selecting a model that is incompatible with their chosen client (e.g., selecting a Gemini Developer API-only model while using the Vertex AI client). This will lead to a runtime error instead of a graceful failure with a clear error message.

To improve the user experience, I recommend adding validation in main.py to check for compatible model and client combinations. This would provide an immediate and clear error to the user if they make an invalid selection. This can be addressed in a follow-up.


Expand Down
Loading