A modern chat interface for Gemini 2.0 Flash with image understanding capabilities.
- Clean, modern UI with a neon aesthetic
- Text chat with Gemini 2.0 Flash
- Image understanding (upload or drag & drop images)
- Clipboard paste support for images
- Optional image generation through Replicate API
- Responsive design for all devices
- Node.js 18+ and npm/yarn
- Google Gemini API key (get one at Google AI Studio)
- (Optional) Replicate API token for image generation
-
Clone the repository:
git clone https://github.com/yourusername/neon-gemini-flash.git cd neon-gemini-flash
-
Install dependencies:
npm install # or yarn install
-
Create a
.env.local
file in the root directory with your API keys:GEMINI_API_KEY=your_gemini_api_key_here REPLICATE_API_TOKEN=your_replicate_token_here
npm run dev
# or
yarn dev
Open http://localhost:3000 with your browser to see the result.
The easiest way to deploy this app is to use the Vercel Platform:
- Push your code to a GitHub repository
- Import the project in Vercel
- Add the following environment variables in the Vercel project settings:
GEMINI_API_KEY
: Your Google Gemini API keyREPLICATE_API_TOKEN
: Your Replicate API token (if using image generation)
- Deploy!
- Never commit your API keys to GitHub! The
.env.local
file is in.gitignore
for a reason. - API keys are accessed via environment variables for security.
- The project uses Vercel's edge runtime for optimal performance.
src/app
: Next.js App Router pages and API routessrc/components
: React componentssrc/lib
: Utility functions and context providerspublic
: Static assets
This project is licensed under the MIT License - see the LICENSE file for details.
- Google Gemini for the AI model
- Next.js and React for the framework
- Tailwind CSS for styling
- Vercel for hosting