Merge branch 'develop' into docs/final-docs-1.x-revision

# Conflicts:
#	README.md

.pre-commit-config.yaml

@@ -20,7 +20,7 @@ repos:
             # - --remove-header
 
 -   repo: https://github.com/psf/black
-    rev: 22.8.0
+    rev: 22.10.0
     hooks:
     -   id: black
         additional_dependencies: ['click==8.0.4']

README.md

@@ -6,33 +6,36 @@
   <br>
 </h1>
 <p align="center">
-<a  href="https://pypi.org/project/rubrix/">
+<a  href="https://pypi.org/project/argilla/">
 <img  alt="CI"  src="https://img.shields.io/pypi/v/rubrix.svg?style=flat-square&logo=pypi&logoColor=white">
 </a>
 <!--a  href="https://anaconda.org/conda-forge/rubrix">
 <img  alt="CI"  src="https://img.shields.io/conda/vn/conda-forge/rubrix?logo=anaconda&style=flat&color=orange">
 </!a-->
 <img  alt="Codecov" src="https://img.shields.io/codecov/c/github/recognai/rubrix">
-<a href="https://pepy.tech/project/rubrix">
-<img  alt="CI"  src="https://static.pepy.tech/personalized-badge/rubrix?period=month&units=international_system&left_color=grey&right_color=blue&left_text=pypi%20downloads/month">
+<a href="https://pepy.tech/project/argilla">
+<img  alt="CI"  src="https://static.pepy.tech/personalized-badge/argilla?period=month&units=international_system&left_color=grey&right_color=blue&left_text=pypi%20downloads/month">
 </a>
 </p>
 
 <h2 align="center">Open-source framework for data-centric NLP</h2>
 <p align="center">Data Labeling + Data Curation + Inference Store</p>
 <p align="center">Designed for MLOps & Feedback Loops</p>
 
-<iframe width="100%" height="450" src="https://www.youtube.com/embed/jP3anvp7Rto" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
-
+https://user-images.githubusercontent.com/1107111/197567844-4370487d-fe44-441e-9a92-48e529713a15.mp4
 
 <br>
 
 <p align="center">
 <a  href="https://join.slack.com/t/rubrixworkspace/shared_invite/zt-whigkyjn-a3IUJLD7gDbTZ0rKlvcJ5g">
 <img src="https://img.shields.io/badge/JOIN US ON SLACK-4A154B?style=for-the-badge&logo=slack&logoColor=white" />
 </a>
+<a href="https://linkedin.com/company/argilla-io">
 <img src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
+</a>
+<a  href="https://twitter.com/argilla_io">
 <img src="https://img.shields.io/badge/Twitter-1DA1F2?style=for-the-badge&logo=twitter&logoColor=white" />
+</a>
 </p>
 
 <br>
@@ -52,25 +55,25 @@
 
 ### Advanced NLP labeling
 
-- Programmatic labeling using Weak Supervision. Built-in label models (Snorkel, Flyingsquid)
-- Bulk-labeling and search-driven annotation
-- Iterate on training data with any pre-trained model or library
+- Programmatic labeling using [weak supervision](https://docs.argilla.io/en/latest/guides/techniques/weak_supervision.html). Built-in label models (Snorkel, Flyingsquid)
+- [Bulk-labeling](https://docs.argilla.io/en/latest/reference/webapp/features.html#bulk-annotate) and [search-driven annotation](https://docs.argilla.io/en/latest/guides/features/queries.html)
+- Iterate on training data with any [pre-trained model](https://docs.argilla.io/en/latest/tutorials/libraries/huggingface.html) or [library](https://docs.argilla.io/en/latest/tutorials/libraries/libraries.html)
 - Efficiently review and refine annotations in the UI and with Python
-- Use Argilla built-in metrics and methods for finding label and data errors (e.g., cleanlab)
-- Simple integration with active learning workflows
+- Use Argilla built-in metrics and methods for [finding label and data errors (e.g., cleanlab)](https://docs.argilla.io/en/latest/tutorials/notebooks/monitoring-textclassification-cleanlab-explainability.html)
+- Simple integration with [active learning workflows](https://docs.argilla.io/en/latest/tutorials/techniques/active_learning.html)
 
 ### Monitoring
 
 - Close the gap between production data and data collection activities
-- Auto-monitoring for major NLP libraries and pipelines (spaCy, Hugging Face, FlairNLP)
-- ASGI middleware for HTTP endpoints
-- Argilla Metrics to understand data and model issues, like entity consistency for NER models
+- [Auto-monitoring](https://docs.argilla.io/en/latest/guides/steps/3_deploying.html) for [major NLP libraries and pipelines](https://docs.argilla.io/en/latest/tutorials/libraries/libraries.html) (spaCy, Hugging Face, FlairNLP)
+- [ASGI middleware](https://docs.argilla.io/en/latest/tutorials/notebooks/deploying-texttokenclassification-fastapi.html) for HTTP endpoints
+- Argilla Metrics to understand data and model issues, [like entity consistency for NER models](https://docs.argilla.io/en/latest/guides/steps/4_monitoring.html)
 - Integrated with Kibana for custom dashboards
 
 ### Team workspaces
 
 - Bring different users and roles into the NLP data and model lifecycles
-- Organize data collection, review and monitoring into different workspaces
+- Organize data collection, review and monitoring into different [workspaces](https://docs.argilla.io/en/latest/getting_started/installation/user_management.html#workspace)
 - Manage workspace access for different users
 
 ## Quickstart
@@ -92,7 +95,7 @@ The simplest way is to use`Docker` by running:
 docker run -d --name es-for-argilla -p 9200:9200 -p 9300:9300 -e "ES_JAVA_OPTS=-Xms512m -Xmx512m" -e "discovery.type=single-node" docker.elastic.co/elasticsearch/elasticsearch-oss:7.10.2
 
 ```
-> :information_source: **Check [the docs](https://rubrix.readthedocs.io/en/stable/getting_started/setup%26installation.html) for further options and configurations for Elasticsearch.**
+> :information_source: **Check [the docs](https://docs.argilla.io/en/latest/getting_started/quickstart.html) for further options and configurations for Elasticsearch.**
 
 Finally you can **launch the server**:
 
@@ -181,7 +184,6 @@ Argilla is useful if you want to:
 ### What do I need to start using Argilla?
 You need to have a running instance of Elasticsearch and install the Argilla Python library.
 The library is used to read and write data into Argilla.
-To get started we highly recommend using Jupyter Notebooks so you might want to install Jupyter Lab or use Jupiter support for VS Code for example.
 
 ### How can I "upload" data into Argilla?
 Currently, the only way to upload data into Argilla is by using the Python library.
@@ -213,10 +215,10 @@ The training datasets created with Argilla are model agnostic.
 
 You can choose one of many amazing frameworks to train your model, like [transformers](https://huggingface.co/docs/transformers/), [spaCy](https://spacy.io/), [flair](https://github.com/flairNLP/flair) or [sklearn](https://scikit-learn.org).
 
-Check out our [cookbook](https://rubrix.readthedocs.io/en/stable/guides/cookbook.html) and our [tutorials](https://rubrix.readthedocs.io/en/stable) on how Argilla integrates with these frameworks.
+Check out our [deep dives](https://docs.argilla.io/en/latest/guides/guides.html) and our [tutorials](https://docs.argilla.io/en/latest/tutorials/tutorials.html) on how Argilla integrates with these frameworks.
 
 
-If you want to train a Hugging Face transformer or spaCy NER model, we provide a neat shortcut to [prepare your dataset for training](https://rubrix.readthedocs.io/en/stable/reference/python/python_client.html#rubrix.client.datasets.DatasetForTextClassification.prepare_for_training).
+If you want to train a Hugging Face transformer or spaCy NER model, we provide a neat shortcut to [prepare your dataset for training](https://docs.argilla.io/en/latest/guides/features/datasets.html#Prepare-dataset-for-training).
 ### Can Argilla share the Elasticsearch Instance/cluster?
 Yes, you can use the same Elasticsearch instance/cluster for Argilla and other applications.
 You only need to perform some configuration, check the Advanced installation guide in the docs.
@@ -233,8 +235,8 @@ curl -X PUT "localhost:9200/_cluster/settings?pretty" -H 'Content-Type: applicat
 
 ```
 ## Contributors
-<a  href="https://github.com/recognai/rubrix/graphs/contributors">
+<a  href="https://github.com/argilla-io/argilla/graphs/contributors">
 
-<img  src="https://contrib.rocks/image?repo=recognai/rubrix" />
+<img  src="https://contrib.rocks/image?repo=argilla-io/argilla" />
 
 </a>

docker-compose.yaml

@@ -2,7 +2,7 @@ version: "3"
 
 services:
   argilla:
-    image: argilla-io/argilla-server:latest
+    image: argilla/argilla-server:latest
     restart: unless-stopped
     ports:
       - "6900:80"
@@ -48,4 +48,4 @@ networks:
     driver: bridge
 
 volumes:
-  elasticdata:
+  elasticdata:

frontend/components/commons/datasets-list/DatasetsEmpty.vue

@@ -29,12 +29,18 @@ export default {
 
   methods: {
     generateCodeSnippet() {
-      return `import argilla as rg
+      return `# install datasets library with pip install datasets
+import argilla as rg
+from datasets import load_dataset
 
-rg.log(
-  y rg.TextClassificationRecord(text="my first cool example"),
-  name='example-dataset'
-)`;
+# load dataset from the hub
+dataset = load_dataset("argilla/gutenberg_spacy-ner", split="train")
+
+# read in dataset, assuming its a dataset for token classification
+dataset_rg = rg.read_datasets(dataset, task="TokenClassification")
+
+# log the dataset
+rg.log(dataset_rg, "gutenberg_spacy-ner")`;
     },
   },
 };

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "argilla",
-  "version": "1.0.0",
+  "version": "1.1.0-dev0",
   "private": true,
   "eslintIgnore": [
     "node_modules/**/*",
@@ -40,7 +40,7 @@
     "vue-moment": "^4.1.0",
     "vue-svgicon": "^3.2.9",
     "vue-vega": "^1.0.0-alpha.13",
-    "vue-virtual-scroller": "^1.0.10"
+    "vue-virtual-scroller": "~1.0.10"
   },
   "devDependencies": {
     "@babel/core": "7.17.2",

src/argilla/_version.py

@@ -13,4 +13,4 @@
 #  limitations under the License.
 
 # coding: utf-8
-version = "1.0.0"
+version = "1.1.0-dev0"