AI Chatbot based on Gemini

A comprehensive web UI for AI Chat.

Acknowledgements

This project is inspired by and based on the following open-source project:

• ChatGPT-Demo - For the foundational codebase and features.

Running Locally

Pre environment

1. Node: Check that both your development environment and deployment environment are using Node v18 or later. You can use nvm to manage multiple node versions locally.

    node -v

2. PNPM: We recommend using pnpm to manage dependencies. If you have never installed pnpm, you can install it with the following command:

    npm i -g pnpm

3. GEMINI_API_KEY: Before running this application, you need to obtain the API key from Google. You can register the API key at https://makersuite.google.com/app/apikey.

Getting Started

1. Install dependencies

    pnpm install

2. Copy the .env.example file, then rename it to .env, and add your GEMINI API key to the .env file.

    GEMINI_API_KEY=AIzaSy...

3. Run the application, the local project runs on http://localhost:3000/

    pnpm run dev

Environment Variables

You can control the website through environment variables.

Name	Description	Required
GEMINI_API_KEY	Your API Key for GEMINI. You can get it from here.	Yes
API_BASE_URL	Custom base url for GEMINI API. Click here to see when to use this.	No
HEAD_SCRIPTS	Inject analytics or other scripts before </head> of the page	No
PUBLIC_SECRET_KEY	Secret string for the project. Use for generating signatures for API calls	No
SITE_PASSWORD	Set password for site, support multiple password separated by comma. If not set, site will be public	No

Deploy

Deploy With Vercel(Recommended)

Just click the button above and follow the instructions to deploy your own copy of the app.

Note

Solution for "User location is not supported for the API use"

If you encounter the issue "User location is not supported for the API use", follow these steps to resolve it:

1. Go to this palm-proxy repo and click "Deploy With Vercel".
2. Once the deployment is complete, you will receive a domain name assigned by Vercel (e.g., https://xxx.vercel.app).
3. In your Gemini Pro Chat project, set an environment variable named API_BASE_URL with the value being the domain you got from deploying the gemini proxy (https://xxx.vercel.app).
4. Redeploy your Gemini Pro Chat project to finalize the configuration. This should resolve the issue.

Thanks to antergone for providing this solution.

Deploy With Docker

With the Dockerfile

docker build -t chatbotgemini .

and run

docker run -p 3000:3000 chatbotgemini

Star History