Add jupyter service

.gitignore

@@ -1,3 +1,5 @@
 package.json
 package-lock.json
 node_modules/
+.ipynb_checkpoints/
+*.ipynb

README.md

@@ -41,11 +41,13 @@ graph TD
       mongodb[mongodb**] --> backend
       backend --> frontend[frontend**]
       backend --> searchapi
+      backend --> jupyter
    end
 
    proxy -.- backend
    proxy -.- frontend
    proxy -.- searchapi
+   proxy -.- jupyter
 ```
 
 We flag with `*` the services which have extra internal dependencies, which are not shared across the two backend versions, and with `**` the ones which have an explicit dependency on the `BE_VERSION` value. To view them, refer to the service README.

docker-compose.yaml

@@ -5,3 +5,4 @@ include:
   - ./services/frontend/docker-compose.yaml
   - ./services/searchapi/docker-compose.yaml
   - ./services/proxy/docker-compose.yaml
+  - ./services/jupyter/docker-compose.yaml

services/jupyter/README.md

@@ -0,0 +1,23 @@
+# Jupyter Notebook
+
+This Jupyter Notebook instance is preconfigured with an example notebook that shows the usage of [Pyscicat](https://github.com/scicatproject/pyscicat).
+
+## [Pyscicat Notebook](./config/notebooks/pyscicat.ipynb)
+This notebook demonstrates all the major actions Pyscicat is capable of: 
+ * logging into SciCat backend
+ * dataset creation
+ * datablock creation
+ * attachment upload
+
+## [.env file](./config/.env)
+It contains the environment variables for connecting to the backend service deployed by this project
+
+## [Thumbnail image](./config/notebooks/example_files/thumbnail.png)
+An example image that is used for the attachment upload demonstration
+
+## Default configuration
+This service is only dependant on the backend service, since it demonstrates communication with the latter through Pyscicat.
+
+The notebooks are mounted to the container from the [config/notebooks](config/notebooks/) directory. The changes to these notebooks should *not* be contributed back to this repository, unless this is intentional. In the case you want to upstream changes to these notebooks, be sure to clear all the results from them.
+
+The [main readme](../../README.md) covers all dependencies of this package.

services/jupyter/config/.env

@@ -0,0 +1,4 @@
+BE_BASE_URL="http://backend:3000/api/v3/"
+USERNAME="admin"
+PASSWORD="2jf70TPNZsS"
+NOTEBOOK_ARGS="--NotebookApp.token=''"

services/jupyter/config/notebooks/pyscicat.ipynb

@@ -0,0 +1,175 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# install pyscicat\n",
+    "!pip install 'pyscicat>=0.4.4'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# create scicat client\n",
+    "\n",
+    "from pyscicat.client import ScicatClient\n",
+    "import os\n",
+    "\n",
+    "base_url = os.environ.get('BE_BASE_URL')\n",
+    "username = os.environ.get('USERNAME')\n",
+    "password = os.environ.get('PASSWORD')\n",
+    "\n",
+    "client = ScicatClient(base_url=base_url, username=username, password=password)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# create (raw) dataset\n",
+    "\n",
+    "from pyscicat.model import Ownable, RawDataset\n",
+    "from datetime import datetime\n",
+    "\n",
+    "ownable = Ownable(\n",
+    "    ownerGroup=\"example_research_group\", # only obligatory element of this model\n",
+    "    accessGroups=['group1', 'group2'],\n",
+    "    instrumentGroup='instrument1'\n",
+    ")\n",
+    "\n",
+    "dataset = RawDataset(\n",
+    "    contactEmail=\"[email protected]\", # must be valid email in format\n",
+    "    creationTime=datetime(year=2024, month=4, day=12, hour=12, minute=35, second=30).isoformat(),\n",
+    "    datasetName=\"example_dataset\",\n",
+    "    description=\"You can insert a lengthy description here\",\n",
+    "    instrumentId=\"example.instrument.id\",\n",
+    "    isPublished=False,\n",
+    "    keywords=[\"important\", \"biology\", \"example\"],\n",
+    "    license=\"Public Domain\",\n",
+    "    numberOfFiles = 6,\n",
+    "    orcidOfOwner=\"0000-0001-5109-3700\",\n",
+    "    owner=\"Emmett Exemplum, PhD\",\n",
+    "    ownerEmail=\"example.exemplum@some_uni.ch\",\n",
+    "    size=589824, # in bytes!\n",
+    "    sourceFolder=\"/datasets/example_dataset\", # this will have to reflect the retrieval location for the archival system \n",
+    "    #sourceFolderHost=\"earth.net\", # same as above but the network host part (instead of filesystem)\n",
+    "    validationStatus=\"valid\",\n",
+    "    version=\"4.0.0\", # optional\n",
+    "    scientificMetadata={}, # optional\n",
+    "    principalInvestigator=\"Mr. Irvine Investigator\",\n",
+    "    creationLocation=\"University of Example, Exemplia\",\n",
+    "    #dataFormat=\"someformat\", # optional\n",
+    "    sampleId=\"example.sample.id\",\n",
+    "    **ownable.model_dump()\n",
+    ")\n",
+    "\n",
+    "# attempt to create dataset, *CAN* throw ScicatCommError\n",
+    "dataset_id = client.datasets_create(dataset)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "# Add datablock to dataset\n",
+    "\n",
+    "from pyscicat.model import DataFile, CreateDatasetOrigDatablockDto\n",
+    "from datetime import datetime\n",
+    "\n",
+    "# disable info level logging\n",
+    "import logging\n",
+    "logging.getLogger().setLevel(logging.FATAL)\n",
+    "\n",
+    "files = [\n",
+    "    \"file1.txt\",\n",
+    "    \"someimage.raw\",\n",
+    "    \"thumbnail/someimage.jpg\",\n",
+    "    \"thumbnail/FoilHoles.jpg\",\n",
+    "    \"transformations.json\",\n",
+    "    \"FoilHoles.raw\"\n",
+    "]\n",
+    "file_sizes = [\n",
+    "    100,\n",
+    "    204800,\n",
+    "    20480,\n",
+    "    20480,\n",
+    "    1000,\n",
+    "    342964\n",
+    "]\n",
+    "file_times = [\n",
+    "    datetime(year=2024, month=4, day=12, hour=12, minute=35, second=30),\n",
+    "    datetime(year=2024, month=2, day=4, hour=5, minute=56, second=39),\n",
+    "    datetime(year=2024, month=3, day=30, hour=19, minute=4, second=53),\n",
+    "    datetime(year=2024, month=4, day=2, hour=16, minute=25, second=37),\n",
+    "    datetime(year=2024, month=4, day=12, hour=8, minute=13, second=44),\n",
+    "    datetime(year=2024, month=2, day=4, hour=4, minute=24, second=17)\n",
+    "]\n",
+    "dataFileList = [\n",
+    "    DataFile(path=p, size=s, time=t.isoformat()) for (p, s, t) in zip(files, \n",
+    "                                                                      file_sizes, \n",
+    "                                                                      file_times)\n",
+    "]\n",
+    "\n",
+    "data_block = CreateDatasetOrigDatablockDto(\n",
+    "    size=576, version=1, dataFileList=dataFileList\n",
+    ")\n",
+    "\n",
+    "client.datasets_origdatablock_create(dataset_id, data_block);"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Upload attachment\n",
+    "\n",
+    "from pyscicat.client import encode_thumbnail\n",
+    "from pyscicat.model import Attachment\n",
+    "\n",
+    "attachment = Attachment(\n",
+    "    datasetId=dataset_id,\n",
+    "    thumbnail=encode_thumbnail(\"example_files/thumbnail.png\", \"png\"),\n",
+    "    caption=\"Example thumbnail image as attachment\",\n",
+    "    **ownable.model_dump()\n",
+    ")\n",
+    "\n",
+    "client.datasets_attachment_create(attachment);"
+   ]
+  }
+ ],
+ "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": "3.11.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

services/jupyter/docker-compose.yaml

@@ -0,0 +1,13 @@
+services:
+  jupyter:
+    image: quay.io/jupyter/base-notebook:x86_64-notebook-7.1.2
+    depends_on:
+      backend:
+        condition: service_healthy
+    labels:
+      - traefik.http.routers.jupyter.rule=Host(`jupyter.localhost`)
+      - traefik.http.services.jupyter.loadbalancer.server.port=8888
+    volumes:
+      - ./config/notebooks:/home/jovyan/notebooks
+    env_file:
+      - config/.env