update to py3.12, use uv and add hf-mount

Dockerfile

@@ -1,69 +1,11 @@
-FROM nvidia/cuda:11.3.1-base-ubuntu20.04
-
-ENV DEBIAN_FRONTEND=noninteractive \
-	TZ=Europe/Paris
-
-# Remove any third-party apt sources to avoid issues with expiring keys.
-# Install some basic utilities
-RUN rm -f /etc/apt/sources.list.d/*.list && \
-    apt-get update && apt-get install -y --no-install-recommends \
-    curl \
-    ca-certificates \
-    sudo \
-    git \
-    wget \
-    procps \
-    git-lfs \
-    zip \
-    unzip \
-    htop \
-    vim \
-    nano \
-    bzip2 \
-    libx11-6 \
-    build-essential \
-    libsndfile-dev \
-    software-properties-common \
- && rm -rf /var/lib/apt/lists/*
-
-RUN add-apt-repository ppa:flexiondotorg/nvtop && \
-    apt-get upgrade -y && \
-    apt-get install -y --no-install-recommends nvtop
-
-RUN curl -sL https://deb.nodesource.com/setup_20.x  | bash - && \
-    apt-get install -y nodejs && \
-    npm install -g configurable-http-proxy
+FROM astral/uv:python3.12-bookworm
 
 # Create a working directory
 WORKDIR /app
 
-# Create a non-root user and switch to it
-RUN adduser --disabled-password --gecos '' --shell /bin/bash user \
- && chown -R user:user /app
-RUN echo "user ALL=(ALL) NOPASSWD:ALL" > /etc/sudoers.d/90-user
-USER user
-
-# All users can use /home/user as their home directory
 ENV HOME=/home/user
-RUN chmod -R 777 $HOME
-
-# Set up the Conda environment
-ENV CONDA_AUTO_UPDATE_CONDA=false \
-    PATH=$HOME/miniconda/bin:$PATH
-RUN curl -sLo ~/miniconda.sh https://repo.continuum.io/miniconda/Miniconda3-py39_4.10.3-Linux-x86_64.sh \
- && chmod +x ~/miniconda.sh \
- && ~/miniconda.sh -b -p ~/miniconda \
- && rm ~/miniconda.sh \
- && conda clean -ya
-
 WORKDIR $HOME/app
 
-#######################################
-# Start root user section
-#######################################
-
-USER root
-
 # User Debian packages
 ## Security warning : Potential user code executed as root (build time)
 RUN --mount=target=/root/packages.txt,source=packages.txt \
@@ -74,17 +16,11 @@ RUN --mount=target=/root/packages.txt,source=packages.txt \
 RUN --mount=target=/root/on_startup.sh,source=on_startup.sh,readwrite \
 	bash /root/on_startup.sh
 
-RUN mkdir /data && chown user:user /data
-
-#######################################
-# End root user section
-#######################################
-
-USER user
+RUN mkdir /data
 
 # Jupyterlab
-RUN pip install jupyterlab==3.6.1 jupyter-server==2.3.0 tornado==6.2 ipywidgets plotly
-RUN pip install catppuccin-jupyterlab
+RUN uv pip install --system jupyterlab==3.6.1 jupyter-server==2.3.0 tornado==6.2 ipywidgets plotly
+RUN uv pip install --system catppuccin-jupyterlab
 RUN mkdir -p $HOME/.jupyter/lab/user-settings/@jupyterlab/apputils-extension
 RUN mkdir -p $HOME/.jupyter/lab/user-settings/catppuccin_jupyterlab
 RUN echo '{"theme": "Catppuccin Frappé"}' > $HOME/.jupyter/lab/user-settings/@jupyterlab/apputils-extension/themes.jupyterlab-settings
@@ -92,14 +28,14 @@ RUN echo '{"brandColor": "peach", "accentColor": "green"}' > $HOME/.jupyter/lab/
 
 # User Python packages
 RUN --mount=target=requirements.txt,source=requirements.txt \
-    pip install --no-cache-dir --upgrade -r requirements.txt
+    uv pip install --system --no-cache-dir --upgrade -r requirements.txt
 
 # Copy the current directory contents into the container at $HOME/app setting the owner to the user
-COPY --chown=user . $HOME/app
+COPY . $HOME/app
 
 RUN chmod +x start_server.sh
 
-COPY --chown=user login.html /home/user/miniconda/lib/python3.9/site-packages/jupyter_server/templates/login.html
+COPY login.html /usr/local/lib/python3.12/site-packages/jupyter_server/templates/login.html
 
 ENV PYTHONUNBUFFERED=1 \
 	GRADIO_ALLOW_FLAGGING=never \

README.md

@@ -10,7 +10,7 @@ tags:
 - jupyterlab
 - spark
 - datasets
-suggested_storage: small
+rootless: true
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

data/hf-mount.ipynb

@@ -0,0 +1,49 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1d612ca3",
+   "metadata": {},
+   "source": [
+    "# Mount Hugging Face Buckets and repos as local filesystems\n",
+    "\n",
+    "<img width=\"640\" alt=\"image\" src=\"https://github.com/user-attachments/assets/d68eac8c-4e28-4d2d-93b2-b049da846397\" />\n",
+    "\n",
+    "Mount Hugging Face Buckets and repos as local filesystems using [hf-mount](https://github.com/huggingface/hf-mount).\n",
+    "\n",
+    "No download, no copy, no waiting."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "196bc954",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!hf-mount start bucket myuser/my-bucket /data/my-bucket"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

data/spark.ipynb

@@ -30,7 +30,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Load a dataset\n",
     "df = spark.read.format(\"huggingface\").load(\"fka/awesome-chatgpt-prompts\")\n",
+    "# Or load data from a storage bucket:\n",
+    "# df = spark.read.format(\"huggingface\").option(\"data_dir\", \"OpenOrca\").load(\"buckets/lhoestq/datasets\")\n",
     "df.show()"
    ]
   }

on_startup.sh

@@ -3,3 +3,7 @@
 # For example, to clone transformers and install it in dev mode:
 # git clone https://github.com/huggingface/transformers.git
 # cd transformers && pip install -e ".[dev]"
+
+# Install hf-mount
+INSTALL_DIR=/usr/local/bin
+curl -fsSL https://raw.githubusercontent.com/huggingface/hf-mount/main/install.sh | sh