yo- GPT
Back

Install & run in minutes

Open a terminal window and run the following commands

  • 1- Clone the repo:

    Terminalgit clone https://github.com/sylvainzircher/yo-GPT-2.0.git [your-name]
    cd [your-name]

  • 2- Install dependencies:

    Terminalnpm install

  • 3- Add your Fireworks API key:

    Create a .env.local file in the root directory and add your Fireworks API key (you can find it here):

    NEXT_PUBLIC_FIREWORKS_API_KEY=your_api_key_here

  • 4- Run Locally:

    Terminalnpm run dev

  • 5- Open http://localhost:3000 and start chatting!

More advanced set up

Allow Llama Models to Perform Web Searches

  • 1- Create a free account with SerpApi.

  • 2- After signing up, find your API key in your SerpAPI account dashboard.

  • 3- Add your SerpApi API key in the.env.local file.

    NEXT_PUBLIC_SERP_API=your_serpapi_key_here

Enable Chatting with Documents (PDFs)

  • 1- Create a folder namedembeddingsin the root directory.

  • 2- Go to fast textand within the download model section, download crawl-300d-2M.vec . Save it into the embeddings folder previously created & unzip it.

  • 3- Now your system is set up to chat with your PDFs using the embeddings model.