Gemini Flash API: Multimodal Queries with Google Generative AI

This repository provides a comprehensive guide on leveraging the Gemini Flash API for handling multimodal queries. You'll learn how to upload and process multiple file types such as audio, video, images, and text, and use these files within a single query using Google's Generative AI.

Features

• Upload various file types to the Gemini API
• Wait for files to be processed and ready
• Start a chat session with the generative model using uploaded files
• Compare different media types in a single query

Getting Started

1. Clone the repository:

   git clone https://github.com/developersdigest/gemini-flash-api.git

2. Install dependencies:

   npm install

   or if you are using Bun:

   bun install

3. Set up your API key: Ensure your GEMINI_API_KEY is set in your environment variables.

4. Run the script:

   node index.js

YouTube Video

License

This project is licensed under the MIT License. See the LICENSE file for details.