AI-Content-Generator

Features:

Follow the steps mentioned below to install and run the project. You may find more details about Gemini from Google's official documentation.

Clone or download the repository
Obtain your free API key from Get API Key. and paste it into the .env file in place of your-api-key
Open cmd in the same directory and install Node using npm i command
Run the "gemini.js" server by npm start command from terminal or using VS Code's run feature. You will also need to install all the necessary dependencies. See "package.json" file for those
In "Modules" folder you will find the text and image pages. You can open them and use their respective functionality

Gemini Pro and Gemini Pro Vision models have been used for text and image processing
Both functionalities have separate HTML pages
Image Analysis makes use of a hardcoded prompt "Describe this image". You can change it inside the JavaScript part of the image.html page
The prompt for image analysis can also be made dynamic to accept input from the user. I have not done it here but it is possible
Image needs to be lesser than 4MB. This is Gemini's current limitation

Name		Name	Last commit message	Last commit date
Latest commit History 13 Commits
Modules		Modules
.env		.env
.gitattributes		.gitattributes
.gitignore		.gitignore
README.md		README.md
gemini.js		gemini.js
package-lock.json		package-lock.json
package.json		package.json