How to run 🐳 DeepSite locally

#74
by enzostvs - opened

Hi everyone 👋

Some of you have asked me how to use DeepSite locally. It's actually super easy!
Thanks to Inference Providers, you'll be able to switch between different providers just like in the online application. The cost should also be very low (a few cents at most).

Run DeepSite locally

  1. Clone the repo using git
git clone https://huggingface.co/spaces/enzostvs/deepsite
  1. Install the dependencies (make sure node is installed on your machine)
npm install
  1. Create your .env file and add the HF_TOKEN variable
    Make sure to create a token with inference permissions and optionally write permissions (if you want to deploy your results in Spaces)

  2. Build the project

npm run build
  1. Start it and enjoy with a coffee ☕
npm run start

To make sure everything is correctly setup, you should see this banner on the top-right corner.
Screenshot 2025-04-16 at 11.40.21 AM.png

Feel free to ask or report issue related to the local usage below 👇
Thank you all!

enzostvs pinned discussion
victor changed discussion title from 🐳 How to use it locally to How to run 🐳 DeepSite locally

It would be cool to provide instructions for running this in docker. I tried it yesterday and got it running although it gave an error when trying to use it. I did not look into what was causing it yet though.

this works great thank you!

im getting Invalid credentials in Authorization header

not really that familiar with running stuff locally

getting error as "Invalid credentials in Authorization header"

getting error as "Invalid credentials in Authorization header"

Are you sure you did those steps correctly?

  1. Create a token with inference permissions: https://huggingface.co/settings/tokens/new?ownUserPermissions=repo.content.read&ownUserPermissions=repo.write&ownUserPermissions=inference.serverless.write&tokenType=fineGrained then copy it to your clipboard
  2. Create a new file named .env in the Deepsite folder you cloned and paste your token in it so it should look like this:
HF_TOKEN=THE_TOKEN_YOU_JUST_CREATED
  1. Launch the app again

We have not been able to find inference provider information for model deepseek-ai/DeepSeek-V3-0324.

do this come with a model or i have to add my own model?

j'essaye de creer une application, comment faire pour passer le code de deepsite en appli????

I have followed the steps, and was able to install it as well. When I got o localhost:3000, it loads, but I don't see the Local Usage tag, plus I am getting invalid headers even when I have the .env file with the token. How do I resolve this? Thanks for the help!
I have confirmed that I have latest git.

Hello, after local deployment, here's the message I receive when I execute the request: "Failed to execute 'json' on 'Response': Unexpected end of JSON input."
How can I resolve this issue, please?
Capture d’écran 2025-04-22 à 00.56.40.png

@web3gn did you manage to figure out this issue?

Is this all Available only on Linux?

The string did not match the expected pattern.

I Get this error

Criei um site como faço para copiar o link do site que criei

Sign up or log in to comment