Duplicate from giskardai/giskard

Co-authored-by: Weixuan Xiao <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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 +1,43 @@
+FROM docker.io/giskardai/giskard:2.11.0
+
+USER root
+RUN usermod -u 1000 giskard
+RUN chown -R giskard  \
+    /var/run/postgresql \
+    /var/lib/nginx  \
+    "${GSK_USER_HOME}"  \
+    "${GSK_DIST_PATH}"
+
+# Use HF persistent storage under /data if mounted
+ENV GISKARD_HF_DATA_DIR=/data/giskard/datadir
+RUN mkdir -p "${GISKARD_HF_DATA_DIR}" && chown -R giskard "${GISKARD_HF_DATA_DIR}"
+
+# Create or declare subdirs under GISKARD_HF_DATA_DIR
+ENV PGDATA=$GISKARD_HF_DATA_DIR/database
+RUN mkdir -p "${GISKARD_HF_DATA_DIR}/run" && chown -R giskard "${GISKARD_HF_DATA_DIR}/run"
+
+# Keep the original GSK_HOME for supervisord run files
+# We can still bring up supervisord in case of the persistent storage not working
+ENV GSK_RUN=$GSK_HOME
+RUN mkdir -p "${GSK_RUN}/run" && chown -R giskard "${GSK_RUN}/run"
+
+USER giskard
+
+# Only changed the original supervisord.conf to redirect logs to stdout
+COPY --chown=giskard supervisord.conf $GSK_DIST_PATH
+
+# Copy requirements for demo Space external worker
+COPY --chown=giskard requirements.txt /requirements.txt
+
+# Internal workr doesn't download resource, but takes them directly from projects, so no cache
+ENV GSK_CACHE_DIR=projects
+
+# Redirect to HF persistent storage for Python ($GSK_HOME) and Java ($GISKARD_HOME)
+ENV GSK_HOME=$GISKARD_HF_DATA_DIR \
+    GISKARD_HOME=$GISKARD_HF_DATA_DIR
+
+EXPOSE 7860
+
+# Use a script to create dir and change owner in HF persistent storage during runtime
+COPY --chown=giskard hf.sh "/giskard-bootstrap.sh"
+ENTRYPOINT ["bash", "/giskard-bootstrap.sh"]

README.md

@@ -0,0 +1,25 @@
+---
+title: Giskard Hub
+emoji: 🐢
+colorFrom: green
+colorTo: green
+sdk: docker
+app_port: 7860
+pinned: false
+duplicated_from: giskardai/giskard
+---
+Welcome to Giskard !
+You can modify this space to suit your needs.
+
+The goal for you is to upload your model so you can inspect and test it thanks to Giskard.
+
+In the Dockerfile you can change the PYTHON_VERSION to any python version between 3.7 and 3.10 !
+The default value is 3.7.13. If you don't have specific need we advise you to stay with this version because the build will be quicker.
+
+In the requirements.txt file you can add every python package your model needs. Be carefull, the package giskard is mandatory.
+
+Finally the main code will be in the project.py file. You can choose the name, description of your project.
+Then you can upload your model and dataset, by following the Giskard documentation https://docs.giskard.ai/start/guides/upload-your-model.
+
+As an exemple, we already built one model and dataset in the project.py file. Feel free to delete it.
+If you have any question, you can contact us on linkedin https://www.linkedin.com/in/alexcombessie/

hf.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+echo "Initializing datadir..."
+
+# Create dir if not existed in HF persistent storage
+if [ ! -d "${GSK_HOME}" ]
+then
+  # Create HOME
+  mkdir -p "${GSK_HOME}"
+  # Create frontend run dir
+  mkdir -p "${GSK_HOME}/run/nginx"
+fi
+
+if [ ! -z "${GISKARD_LICENSE}" ]
+then
+  # Use new license if env set
+  echo "${GISKARD_LICENSE}" > "${GISKARD_HOME}/license.lic"
+fi
+
+echo "Detecting demo Giskard Space..."
+
+if [ ! -z "${SPACE_ID}" ] && [ "${DEMO_SPACE_ID}" == "${SPACE_ID}" ]
+then
+  # Generate GISKARD_DEFAULT_API_KEY in demo space instead of set from Secrets
+  export GISKARD_DEFAULT_API_KEY=gsk-$(cat /dev/urandom | tr -dc '[:alpha:]' | fold -w ${1:-28} | head -n 1)
+fi
+
+echo "Starting supervisord..."
+
+exec supervisord -c "${GSK_DIST_PATH}/supervisord.conf"

requirements.txt

@@ -0,0 +1,3 @@
+transformers==4.33.2
+datasets==2.14.5  
+torch==2.0.1

supervisord.conf

@@ -0,0 +1,54 @@
+[supervisord]
+directory=%(ENV_GSK_RUN)s/run
+pidfile=%(ENV_GSK_RUN)s/run/supervisord.pid
+logfile=%(ENV_GSK_RUN)s/run/supervisord.log
+nodaemon=true
+
+[rpcinterface:supervisor]
+supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface
+
+
+[unix_http_server]
+file = %(ENV_GSK_RUN)s/run/svd.sock
+username = giskard
+password = giskard
+
+[supervisorctl]
+serverurl = unix://%(ENV_GSK_RUN)s/run/svd.sock
+username = giskard
+password = giskard
+
+
+[program:backend]
+stdout_logfile=/dev/fd/1
+stdout_logfile_maxbytes=0
+autorestart=true
+redirect_stderr=true
+startsecs=5
+command=bash -c 'sleep 3 && java -jar %(ENV_GSK_DIST_PATH)s/backend/giskard.jar'
+
+[program:db]
+stdout_logfile=/dev/fd/1
+stdout_logfile_maxbytes=0
+autorestart=true
+redirect_stderr=true
+stopsignal=INT
+startsecs=5
+command=/bin/bash %(ENV_GSK_DIST_PATH)s/start-db.sh
+
+[program:worker]
+stdout_logfile=/dev/fd/1
+stdout_logfile_maxbytes=0
+autorestart=true
+redirect_stderr=true
+startsecs=5
+command=bash -c 'python -m giskard.cli worker stop -s && python -m giskard.cli worker start -s --parallelism 2'
+
+[program:frontend]
+stdout_logfile=/dev/fd/1
+stdout_logfile_maxbytes=0
+autorestart=true
+redirect_stderr=true
+startsecs=5
+priority=0
+command=/bin/bash %(ENV_GSK_DIST_PATH)s/start-frontend.sh