This project demonstrates the capabilities of the Google Gemini API for both image-based and text-based prompts. It provides a user-friendly interface to experiment with this powerful AI technology.
Features
- Dual-Mode Input: Users can either:
- Upload an image and provide instructions to get an image-related response.
- Enter a text-based prompt or question for a text-focused response.
- Google Gemini Integration: Leverages the power of Gemini models for cutting-edge AI generation.
- Markdown Output: Responses are neatly formatted using Markdown for readability.
- Safety Settings: Includes built-in safety settings to help filter inappropriate content.
Setup
- Obtain a Google API Key: Get your API key from the Google Cloud console (https://console.cloud.google.com/).
- Install Dependencies:
npm install base64-js markdown-it