This project, Gemini Explorer, explores the possibilities of the Gemini API in Android development. You can generate sentences, texts, and even recipes based on chosen images and custom prompts.
- Clone the repository:
git clone https://github.com/angelica-oliv/geminiapiexplorer.git
- Open in Android Studio:
Import the project into Android Studio and run it on your device or emulator.
- Add your API key:
- Create a project on https://aistudio.google.com/ and obtain your API key.
- Never commit your API key to version control! Add it securely as a local property in Android Studio, following their documentation.
- Select an image:
Choose an image from your device or capture one with your camera.
- Generate text:
The chosen image will automatically receive a humorous description.
- Custom prompts:
For more granular control, you can modify the "prompt" value in GeminiExplorerViewModel.kt
(line 26). Explore different prompts and see what results you get!
While using Gemini API, the data submitted can be used to improve the model. According to the Gemini API Additional Terms of Service:
Do not submit sensitive, confidential, or personal information to the Services.
Consider reading the full terms here.
Feel free to fork this repository and contribute your own improvements or features. Please make sure to follow good coding practices and create pull requests for your changes.
For any questions or suggestions, feel free to open an issue on this repository.