Duplicate from LabelStudio/LabelStudio

Co-authored-by: Chris Hoge <hogepodge@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,127 @@
+FROM heartexlabs/label-studio:hf-latest
+
+################################################################################
+#
+# How to Disable Public Account Creation
+# --------------------------------------
+# By default this space allows for the unrestricted creation of new accounts
+# will full access to all projects and data. This is great for trying out
+# Label Studio and collaborating on projects, but you may want to restrict
+# access to your space to only authorized users. Uncomment the following line
+# to disable public account creation for this space.
+#
+# ENV LABEL_STUDIO_DISABLE_SIGNUP_WITHOUT_LINK=true
+#
+# Set secrets in your space to create an inital user, and log in with your
+# provided username and password. Do not set these in your Dockerfile, as they
+# globally visible on a public space.
+#
+# LABEL_STUDIO_USERNAME
+# LABEL_STUDIO_PASSWORD
+#
+# You will need to provide new users with an invitation link to join the space.
+#
+################################################################################
+
+################################################################################
+#
+# How to Enable Persistent Storage for Label Studio in Hugging Face Spaces
+# ------------------------------------------------------------------------
+#
+# By default this space stores all project configuration and data annotations
+# in local storage with sqlite. If the space is reset, all configuration and
+# annotation data in the space will be lost. You can enable configuration
+# persistence through one of two methods:
+#
+# 1) Enabling Hugging Face Persistent Storage for saving project and annotation
+#    settings, as well as local task storage.
+# 2) Connecting an external Postgres database for saving project and annotation
+#    settings, and cloud by connecting cloud storage for tasks.
+#
+################################################################################
+
+################################################################################
+#
+# How to Enable Hugging Face Persistent Storage for Label Studio
+# --------------------------------------------------------------
+#
+# In the Hugging Face Label Studio Space settings, select the appropriate
+# Persistent Storage tier. Note that Persistent Storage is a paid add-on.
+# By default, persistent storage is mounted to /data. In your Space settings,
+# set the following variables:
+#
+# LABEL_STUDIO_BASE_DATA_DIR=/data
+# ENV STORAGE_PERSISTENCE=1
+#
+# Your space will restart. NOTE: if you have existing settings and data,
+# they will be lost in this first restart. Data and setting will only be
+# preserved on subsequent restarts of the space.
+#
+################################################################################
+
+################################################################################
+#
+# How to Enable Configuration Persistence with Postgres
+# -----------------------------------------------------
+#
+# Set the following secret variables to match your own hosted instance of
+# Postgres. We strongly recommend setting these as secrets to prevent leaking
+# information about your database service to the public in your spaces
+# definition.
+#
+# ENV DJANGO_DB=default
+# ENV POSTGRE_NAME=<postgres_name>
+# ENV POSTGRE_PORT=<db_port>
+# ENV POSTGRE_USER=<postgres_user>
+# ENV POSTGRE_PASSWORD=<password>
+# ENV POSTGRE_PORT=<db_port>
+# ENV POSTGRE_HOST=<db_host>
+#
+# Uncomment the following line or set the following Space variable to remove
+# the warning about ephemeral storage
+#
+# ENV STORAGE_PERSISTENCE=1
+#
+# Note that you will need to connect cloud storage to host data items that you
+# want to annotate, as local storage will not be preserved across a space reset.
+#
+#
+# How to Enable Cloud Storage
+# ---------------------------
+# By default the only data storage enabled for this space is local. In the case
+# of a space reset, all data will be lost. To enable permanent storage, you
+# must enable a cloud storage connector. We also strongly recommend enabling
+# configuration persistence to preserve project data, annotations, and user
+# settings. Choose the appropriate cloud connector and configure the secrets
+# for it.
+#
+# Amazon S3
+# =========
+# STORAGE_TYPE=s3
+# STORAGE_AWS_ACCESS_KEY_ID="<YOUR_ACCESS_KEY_ID>"
+# STORAGE_AWS_SECRET_ACCESS_KEY="<YOUR_SECRET_ACCESS_KEY>"
+# STORAGE_AWS_BUCKET_NAME="<YOUR_BUCKET_NAME>"
+# STORAGE_AWS_REGION_NAME="<YOUR_BUCKET_REGION>"
+# STORAGE_AWS_FOLDER=""
+#
+# Google Cloud Storage
+# ====================
+#
+# STORAGE_TYPE=gcs
+# STORAGE_GCS_BUCKET_NAME="<YOUR_BUCKET_NAME>"
+# STORAGE_GCS_PROJECT_ID="<YOUR_PROJECT_ID>"
+# STORAGE_GCS_FOLDER=""
+# GOOGLE_APPLICATION_CREDENTIALS="/opt/heartex/secrets/key.json"
+#
+# Azure Blob Storage
+# ==================
+#
+# STORAGE_TYPE=azure
+# STORAGE_AZURE_ACCOUNT_NAME="<YOUR_STORAGE_ACCOUNT>"
+# STORAGE_AZURE_ACCOUNT_KEY="<YOUR_STORAGE_KEY>"
+# STORAGE_AZURE_CONTAINER_NAME="<YOUR_CONTAINER_NAME>"
+# STORAGE_AZURE_FOLDER=""
+#
+################################################################################
+
+CMD exec label-studio --host=$SPACE_HOST

README.md

@@ -0,0 +1,168 @@
+---
+title: LabelStudio
+emoji: 🟧
+colorFrom: yellow
+colorTo: purple
+sdk: docker
+tags:
+- label-studio
+fullwidth: true
+license: apache-2.0
+app_port: 8080
+---
+<img src="https://user-images.githubusercontent.com/12534576/192582340-4c9e4401-1fe6-4dbb-95bb-fdbba5493f61.png"/>
+
+[Website](https://hubs.ly/Q01CNgsd0) • [Docs](https://hubs.ly/Q01CN9Yq0) • [12K+ GitHub ⭐️!](https://hubs.ly/Q01CNbPQ0) • [Slack Community](https://hubs.ly/Q01CNb9H0)
+
+## What is Label Studio?
+
+Label Studio is an open source data labeling platform. It lets you label audio,
+text, images, videos, and time series data with a simple, straightforward, and
+highly-configurable user interface. Label Studio can prepare new data or
+improve existing training data to get more accurate ML models.
+
+
+## Label Studio in Hugging Face Spaces
+
+The Label Studio community is thrilled to offer Label Studio as a Hugging Face
+Spaces application. You can try the data-annotation interface, connect popular
+machine learning models, and share the application with collaborators. You can
+start immediately by creating an account or replicate the space and work in
+your own environment.
+
+## Creating a Use Account and Logging In
+
+Begin by creating a new account in the Label Studio space, then log in with your
+credentials.
+
+**By default, these spaces permit anyone to create a new login
+account, allowing them to view and modify project configuration, data sets, and
+annotations. Without any modifications, treat this space like a demo environment.**
+
+## Creating a Labeling Project
+
+After logging in, Label Studio will present you with a project view. Here you
+can create a new project with prompts to upload data and set up a custom
+configuration interface.
+
+**Note that in the default configuration, storage is local and temporary. Any
+projects, annotations, and configurations will be lost if the space is restarted.**
+
+## Next Steps and Additional Resources
+
+To help with getting started, the Label Studio community curated a list of
+resources including tutorials and documentation.
+
+- 🚀 [Zero to One with Label Studio Tutorial](https://labelstud.io/blog/introduction-to-label-studio-in-hugging-face-spaces/)
+- 📈 [Try Label Studio Enterprise](https://hubs.ly/Q01CMLll0)
+- 🤗 [Tutorial: Using Label Studio with Hugging Face Datasets Hub](https://danielvanstrien.xyz/huggingface/huggingface-datasets/annotation/full%20stack%20deep%20learning%20notes/2022/09/07/label-studio-annotations-hub.html)
+- 💡 [Label Studio Docs](https://hubs.ly/Q01CN9Yq0)
+
+ 
+![Gif of Label Studio annotating different types of data](https://raw.githubusercontent.com/heartexlabs/label-studio/master/images/annotation_examples.gif)
+
+### Making your Label Studio Hugging Face Space production-ready
+
+By default this space allows for the unrestricted creation of new accounts
+will full access to all projects and data. This is great for trying out
+Label Studio and collaborating on projects, but you may want to restrict
+access to your space to only authorized users. Add the following environment
+variable to your spaces Dockerfile to disable public account creation for
+this space.
+
+    ENV LABEL_STUDIO_DISABLE_SIGNUP_WITHOUT_LINK=true
+
+Set secrets in your space to create an inital user, and log in with your
+provided username and password. Do not set these in your Dockerfile, as they
+globally visible on a public space.
+
+    LABEL_STUDIO_USERNAME
+    LABEL_STUDIO_PASSWORD
+
+You will need to provide new users with an invitation link to join the space,
+which can be found in the Organizations interface of Label Studio.
+
+By default this space stores all project configuration and data annotations
+in local storage with Sqlite. If the space is reset, all configuration and
+annotation data in the space will be lost. You can enable configuration
+persistence in one of two ways:
+
+1. Enabling Persistent Storage in your Space settings and configuring Label
+   Studio to write its database and task storage there.
+
+2. Connecting an external Postgres database and cloud storage to your space,
+   guaranteeing that all project and annotation settings are preserved.
+
+### Enabling Hugging Face Persistent Storage
+
+In the Hugging Face Label Studio Space settings, select the appropriate
+Persistent Storage tier. Note that Persistent Storage is a paid add-on.
+By default, persistent storage is mounted to /data. In your Space settings,
+set the following variables:
+
+    LABEL_STUDIO_BASE_DATA_DIR=/data
+    ENV STORAGE_PERSISTENCE=1
+
+Your space will restart. NOTE: if you have existing settings and data,
+they will be lost in this first restart. Data and setting will only be
+preserved on subsequent restarts of the space.
+
+### Enabling Postgres Database and Cloud Storage
+
+Set the following secret variables to match your own hosted instance of
+Postgres. We strongly recommend setting these as secrets to prevent leaking
+information about your database service to the public in your spaces
+definition.
+
+    DJANGO_DB=default
+    POSTGRE_NAME=<postgres_name>
+    POSTGRE_PORT=<db_port>
+    POSTGRE_USER=<postgres_user>
+    POSTGRE_PASSWORD=<password>
+    POSTGRE_PORT=<db_port>
+    POSTGRE_HOST=<db_host>
+
+Add the following environment variable to remove the warning about ephemeral
+storage.
+
+    ENV STORAGE_PERSISTENCE=1
+
+Note that you will need to connect cloud storage to host data items that you
+want to annotate, as local storage will not be preserved across a space reset.
+
+By default the only data storage enabled for this space is local. In the case
+of a space reset, all data will be lost. To enable permanent storage, you
+must enable a cloud storage connector. We also strongly recommend enabling
+configuration persistence to preserve project data, annotations, and user
+settings. Choose the appropriate cloud connector and configure the secrets
+for it.
+
+#### Amazon S3
+    STORAGE_TYPE=s3
+    STORAGE_AWS_ACCESS_KEY_ID="<YOUR_ACCESS_KEY_ID>"
+    STORAGE_AWS_SECRET_ACCESS_KEY="<YOUR_SECRET_ACCESS_KEY>"
+    STORAGE_AWS_BUCKET_NAME="<YOUR_BUCKET_NAME>"
+    STORAGE_AWS_REGION_NAME="<YOUR_BUCKET_REGION>"
+    STORAGE_AWS_FOLDER=""
+
+#### Google Cloud Storage
+
+    STORAGE_TYPE=gcs
+    STORAGE_GCS_BUCKET_NAME="<YOUR_BUCKET_NAME>"
+    STORAGE_GCS_PROJECT_ID="<YOUR_PROJECT_ID>"
+    STORAGE_GCS_FOLDER=""
+    GOOGLE_APPLICATION_CREDENTIALS="/opt/heartex/secrets/key.json"
+
+Azure Blob Storage
+==================
+
+    STORAGE_TYPE=azure
+    STORAGE_AZURE_ACCOUNT_NAME="<YOUR_STORAGE_ACCOUNT>"
+    STORAGE_AZURE_ACCOUNT_KEY="<YOUR_STORAGE_KEY>"
+    STORAGE_AZURE_CONTAINER_NAME="<YOUR_CONTAINER_NAME>"
+    STORAGE_AZURE_FOLDER=""
+
+
+## Questions? Concerns? Want to get involved?
+
+Email the community team at [community@labelstud.io](mailto:community@labelstud.io)