I am interested in technology, especially artificial intelligence. When I got to know about the Google Gemini API, I was very excited to work with that API and create an application.

It is an image recognition chatbot that recognizes images. You can chat and ask questions about the image and get answers

It is built using the React JS framework, Google Gemini API link, and Cloudinary to store images in the cloud link.

The main problem I faced was accessing Chrome's built-in AI feature, so I used the Google Gemini API instead. Additionally, I encountered issues with storing the image and converting it to Base64 format.

I am proud and happy that I was able to fix the issue above and complete my project.

I got to learn Cloudinary to store images in the cloud, convert images to Base64 format before sending them to the server, and use the Google Gemini API link.

This image recognition chatbot can be used by students, teachers, and professionals from various fields to learn about historical places by analyzing images, as well as in many other situations and industries. I want to create my own image recognition bot instead of relying on the Gemini API and scale the application accordingly.

Built With

Share this project:

Updates