Fix/issue 28 (#29) hello world Datalab

* rephrase text

* remove individual authors

* make subtitle more visible

* fix notebook text

* Update CodeSnippet.tsx

* change notebook filename

* Update TermsOfUseModal.tsx

* Update CodeSnippet.tsx

src/components/CodeSnippet.tsx

@@ -1,7 +1,6 @@
 import { useState, useRef, useEffect } from "react"
 import ReactCodeMirror, { EditorView } from "@uiw/react-codemirror"
 import type { ReactCodeMirrorRef } from "@uiw/react-codemirror"
-import { duotoneDark } from "@uiw/codemirror-theme-duotone"
 import { python } from "@codemirror/lang-python"
 import { Copy, CheckCircle } from "iconoir-react"
 import { createTheme } from "@uiw/codemirror-themes"
@@ -18,7 +17,7 @@ export interface CodeSnippetProps {
 const myTheme = createTheme({
   theme: "light",
   settings: {
-    background: "#fff9f2",
+    background: "#fff9f250",
     backgroundImage: "",
     foreground: "#75baff",
     caret: "#5d00ff",

src/components/GettingStarted.tsx

@@ -44,7 +44,7 @@ const GettingStarted = ({ className = "" }) => {
             <div className="badge bg-dark me-2 py-1 px-2 font-weight-extrabold text-primary">
               {startNumAfterOptionalSteps}
             </div>{" "}
-            Consult our terms of use
+            Accept our Terms of Use
           </Link>
         </li>
         <li>

src/components/TermsOfUseModal.tsx

@@ -1,4 +1,4 @@
-import { useEffect, useRef, useState, type ChangeEvent } from "react"
+import { useEffect, useState, type ChangeEvent } from "react"
 import AcceptTermsOfUse from "./AcceptTermsOfUse"
 import Page from "./Page"
 import { Col, Container, Row } from "react-bootstrap"

src/components/Wall.tsx

@@ -73,7 +73,7 @@ const Wall = ({
               <b>{numberOfAuthors}</b> authors.
             </p>
           </Col>
-          <Col md={4}>
+          <Col md={6} lg={6} xxl={5}>
             <h3>
               Join us in this early stage of development and help us to improve
               the platform.

src/content/notebooks/detect-news-agency-with-impresso-model.mdx

@@ -8,39 +8,40 @@ date: 2024-09-18T10:11:47Z
 googleColabUrl: https://colab.research.google.com/github/impresso/impresso-datalab-notebooks/blob/main/2-entity/NE_02_newsagencies.ipynb
 authors:
   - impresso-team
-seealso:
-  - setup
 ---
 
 {/* cell:0 cell_type:markdown */}
-Delivering swift and reliable news since the 1830s and 1840s, news agencies have played a pivotal role both nationally and internationally. However, understanding their precise impact on shaping news content has remained somewhat elusive. Our goal is to illuminate this aspect by identifying news agencies within historical newspaper articles. Using data from newspapers in Switzerland and Luxembourg as part of the impresso project, we've trained our pipeline to recognize these entities. 
+Delivering swift and reliable news since the 1830s and 1840s, news agencies have played a pivotal role both nationally and internationally. However, understanding their precise impact on shaping news content has remained somewhat elusive. Our goal is to illuminate this aspect by identifying news agencies within historical newspaper articles. Using data from newspapers in Switzerland and Luxembourg as part of the impresso project, we've trained our pipeline to recognize these entities.
 
 If you're here, you likely seek to detect news agency entities in your own text. This notebook will guide you through the process of setting up a workflow to identify specific newspaper or agency mentions within your text.
 
 {/* cell:1 cell_type:markdown */}
-Install necessary libraries (if not already installed) and 
+Install necessary libraries (if not already installed) and
 download the necessary NLTK data.
 
 {/* cell:2 cell_type:code */}
+
 ```python
 !pip install python-dotenv
 !pip install transformers
 !pip install torch
 ```
 
 {/* cell:3 cell_type:markdown */}
-*Note: This notebook requires `HF_TOKEN` to be set in the environment variables. You can get your token by signing up on the [Hugging Face website](https://huggingface.co/join) and read more in the [official documentation](https://huggingface.co/docs/huggingface_hub/v0.20.2/en/quick-start#environment-variable). We use [dotenv](https://pypi.org/project/python-dotenv/) library to load the HF_TOKEN value from a local .env file*
+_Note: This notebook requires `HF_TOKEN` to be set in the environment variables. You can get your token by signing up on the [Hugging Face website](https://huggingface.co/join) and read more in the [official documentation](https://huggingface.co/docs/huggingface_hub/v0.20.2/en/quick-start#environment-variable). We use [dotenv](https://pypi.org/project/python-dotenv/) library to load the HF_TOKEN value from a local .env file_
 
 {/* cell:4 cell_type:code */}
+
 ```python
 from dotenv import load_dotenv
 load_dotenv()  # take environment variables from .env.
 ```
 
 {/* cell:5 cell_type:markdown */}
-Now the fun part, this function will download the requried model and gives you the keys to successfullly detect news agencies in your text. 
+Now the fun part, this function will download the requried model and gives you the keys to successfullly detect news agencies in your text.
 
 {/* cell:6 cell_type:code */}
+
 ```python
 from transformers import is_torch_available
 from transformers import pipeline
@@ -56,6 +57,7 @@ nlp = pipeline("newsagency-ner", model="impresso-project/bert-newsagency-ner-fr"
 Run the example below to see how it works.
 
 {/* cell:8 cell_type:code */}
+
 ```python
 # Example
 text = "Mon nom est François et j'habite à Paris. (Reuter)"

src/content/notebooks/generic-entity-api.mdx

@@ -2,7 +2,7 @@
 githubUrl: https://github.com/impresso/impresso-datalab-notebooks/blob/main/2-entity/generic-entity-api.ipynb
 authors:
   - impresso-team
-  - EmanuelaBoros
+#   - EmanuelaBoros
 title: Detect Entities and Link them to Wikipedia and Wikidata in a Text through
   the Impresso API
 sha: 54802fcabc0e32a4a05a1b4f2761a54b9807b0c5
@@ -14,10 +14,13 @@ googleColabUrl: https://colab.research.google.com/github/impresso/impresso-datal
 Named entities such as organizations, locations, persons, and temporal expressions play a crucial role in the comprehension and analysis of both historical and contemporary texts. The HIPE-2022 project focuses on named entity recognition and classification (NERC) and entity linking (EL) in multilingual historical documents.
 
 ### About HIPE-2022
+
 HIPE-2022 involves processing diverse datasets from historical newspapers and classical commentaries, spanning approximately 200 years and multiple languages. The primary goal is to confront systems with challenges related to multilinguality, domain-specific entities, and varying annotation tag sets.
 
 ### Datasets
+
 The HIPE-2022 datasets are based on six primary datasets, but this model was only trained on **hipe2020** in French and German.
+
 - **ajmc**: Classical commentaries in German, French, and English.
 - **hipe2020**: Historical newspapers in German, French, and English.
 - **letemps**: Historical newspapers in French.
@@ -26,6 +29,7 @@ The HIPE-2022 datasets are based on six primary datasets, but this model was onl
 - **sonar**: Historical newspapers in German.
 
 ### Annotation Types and Levels
+
 HIPE-2022 employs an IOB tagging scheme (inside-outside-beginning format) for entity annotations. The annotation levels include:
 
 1. **TOKEN**: The annotated token.
@@ -37,6 +41,7 @@ HIPE-2022 employs an IOB tagging scheme (inside-outside-beginning format) for en
 7. **NE-NESTED**: Coarse type of the nested entity.
 
 ### Getting Started
+
 This notebook will guide you through setting up a workflow to identify named entities within your text using the HIPE-2022 trained pipeline. By leveraging this pipeline, you can detect mentions of people, places, organizations, and temporal expressions, enhancing your analysis and understanding of historical and contemporary documents.
 
 ---
@@ -45,23 +50,25 @@ This updated description provides a clear overview of the HIPE-2022 project's go
 *Note: This notebook *might* require `HF_TOKEN` to be set in the environment variables. You can get your token by signing up on the [Hugging Face website](https://huggingface.co/join) and read more in the [official documentation](https://huggingface.co/docs/huggingface_hub/v0.20.2/en/quick-start#environment-variable)*
 
 {/* cell:1 cell_type:markdown */}
-Install necessary libraries (if not already installed) and 
+Install necessary libraries (if not already installed) and
 download the necessary NLTK data.
 
 {/* cell:2 cell_type:code */}
+
 ```python
 !pip install transformers
 !pip install nltk
 !pip install torch
 ```
 
 {/* cell:3 cell_type:code */}
+
 ```python
 def print_nicely(results, text):
     # Print the timestamp and system ID
     print(f"Timestamp: {results.get('ts')}")
     print(f"System ID: {results.get('sys_id')}")
-    
+
     entities = results.get('nes', [])
     if entities:
         print(f"\n{'Entity':<20} {'Type':<15} {'Confidence NER':<15} {'Confidence NEL':<15} {'Start':<5} {'End':<5} {'Wikidata ID':<10} {'Wikipedia Page':<20}")
@@ -72,7 +79,7 @@ def print_nicely(results, text):
             wkd_id = entity.get('wkd_id', 'N/A')
             wkpedia_pagename = entity.get('wkpedia_pagename', 'N/A')
             print(f"{entity['surface']:<20} {entity['type']:<15} {confidence_ner:<15} {confidence_nel:<15} {entity['lOffset']:<5} {entity['rOffset']:<5} {wkd_id:<10} {wkpedia_pagename:<20}")
-        
+
         print("*" * 100)
         print('Testing offsets:')
         print("*" * 100)
@@ -84,7 +91,7 @@ def print_nicely(results, text):
             wkd_id = entity.get('wkd_id', 'N/A')
             wkpedia_pagename = entity.get('wkpedia_pagename', 'N/A')
             print(f"{text[entity['lOffset']:entity['rOffset']]:<20} {entity['type']:<15} {confidence_ner:<15} {confidence_nel:<15} {entity['lOffset']:<5} {entity['rOffset']:<5} {wkd_id:<10} {wkpedia_pagename:<20}")
-            
+
         print("*" * 100)
         print('Testing offsets in the returned text:')
         print("*" * 100)
@@ -96,14 +103,15 @@ def print_nicely(results, text):
             wkd_id = entity.get('wkd_id', 'N/A')
             wkpedia_pagename = entity.get('wkpedia_pagename', 'N/A')
             print(f"{results['text'][entity['lOffset']:entity['rOffset']]:<20} {entity['type']:<15} {confidence_ner:<15} {confidence_nel:<15} {entity['lOffset']:<5} {entity['rOffset']:<5} {wkd_id:<10} {wkpedia_pagename:<20}")
-            
+
 
 ```
 
 {/* cell:4 cell_type:markdown */}
-Now the fun part, this function will download the requried model and gives you the keys to successfullly detect entities in your text. 
+Now the fun part, this function will download the requried model and gives you the keys to successfullly detect entities in your text.
 
 {/* cell:5 cell_type:code */}
+
 ```python
 from utils import get_linked_entities
 import requests
@@ -117,41 +125,49 @@ for sentence in sentences:
 ```
 
 {/* cell:6 cell_type:code */}
+
 ```python
 
 ```
 
 {/* cell:7 cell_type:code */}
+
 ```python
 
 ```
 
 {/* cell:8 cell_type:code */}
+
 ```python
 
 ```
 
 {/* cell:9 cell_type:code */}
+
 ```python
 
 ```
 
 {/* cell:10 cell_type:code */}
+
 ```python
 
 ```
 
 {/* cell:11 cell_type:code */}
+
 ```python
 
 ```
 
 {/* cell:12 cell_type:code */}
+
 ```python
 
 ```
 
 {/* cell:13 cell_type:code */}
+
 ```python
 
 ```

src/content/notebooks/impresso-py-collections.mdx

@@ -1,67 +1,79 @@
 ---
 githubUrl: https://github.com/impresso/impresso-py/blob/main/examples/notebooks/collections.ipynb
 authors:
-  - RomanKalyakin
+  # - RomanKalyakin
+  - impresso-team
 title: Search collections
 sha: fbebc19629cfc008a085283e61c0669de326add9
 date: 2024-09-18T15:04:39Z
 googleColabUrl: https://colab.research.google.com/github/impresso/impresso-py/blob/main/examples/notebooks/collections.ipynb
 ---
 
 {/* cell:0 cell_type:code */}
+
 ```python
 from impresso import connect
 
 impresso = connect()
 ```
 
 {/* cell:1 cell_type:code */}
+
 ```python
 result = impresso.collections.find()
 result
 ```
 
 {/* cell:2 cell_type:markdown */}
+
 # Get collection
 
 Get metadata of a colection by its ID.
 
 {/* cell:3 cell_type:code */}
+
 ```python
 result = impresso.collections.get("local-roka-tOrwrOG3")
 result
 ```
 
 {/* cell:4 cell_type:markdown */}
+
 ## Get collection items
 
 Get items from a collection by its ID.
 
 {/* cell:5 cell_type:code */}
+
 ```python
 colection_id = result.raw["uid"]
 items = impresso.collections.items(colection_id)
 items
 ```
 
 {/* cell:6 cell_type:markdown */}
+
 ## Remove items from collection
 
 {/* cell:7 cell_type:code */}
+
 ```python
 item_id = items.pydantic.data[0].uid
 item_id
 ```
 
 {/* cell:8 cell_type:code */}
+
 ```python
 impresso.collections.remove_items(colection_id, [item_id])
 ```
 
 {/* cell:9 cell_type:markdown */}
+
 ## Add items to collection
 
 {/* cell:10 cell_type:code */}
+
 ```python
 impresso.collections.add_items(colection_id, [item_id])
 ```