Docs: update to LLM quickstart (evidentlyai#1181)

docs/book/get-started/quickstart-llm.md

@@ -8,7 +8,7 @@ You can run this example in Colab or any Python environment.
 
 Install the Evidently Python library. 
 
-```
+```python
 !pip install evidently[llm]
 ```
 
@@ -19,93 +19,94 @@ import pandas as pd
 from sklearn import datasets
 from evidently.report import Report
 from evidently.metric_preset import TextEvals
-
-import nltk
-nltk.download('words')
-nltk.download('wordnet')
-nltk.download('omw-1.4')
-nltk.download('vader_lexicon')
+from evidently.descriptors import *
 ```
 
-**Optional**. Import components to send evaluation results to Evidently Cloud:
+**Optional**. Import the components to send evaluation results to Evidently Cloud:
 
 ```python
 from evidently.ui.workspace.cloud import CloudWorkspace
 ```
 
 # 2. Import the toy dataset 
 
-Import a toy dataset with e-commerce reviews. It contains a column with "Review_Text" that you'll analyze.
+Import a toy dataset with e-commerce reviews. It contains a column with "Review_Text". You will take 100 rows to analyze.
 
 ```python
-reviews_data = datasets.fetch_openml(name='Womens-E-Commerce-Clothing-Reviews', version=2, as_frame='auto')
+reviews_data = datasets.fetch_openml(
+    name='Womens-E-Commerce-Clothing-Reviews', 
+    version=2, as_frame='auto')
 reviews = reviews_data.frame[:100]
 ```
 
-# 3. Run the evals
+# 3. Run your first eval
 
-Run an evaluation Preset to check basic text descriptive text properties:
-* text sentiment (scale -1 to 1)
-* text length (number of symbols)
-* number of sentences in a text 
-* percentage of out-of-vocabulary words (scale 0 to 100)
-* percentage of non-letter characters (scale 0 to 100)
+Run a few basic evaluations for all texts in the "Review_Text" column: 
+* text sentiment (measured on a scale from -1 for negative to 1 for positive)
+* text length (returns an absolute number of symbols)
 
 ```python
 text_evals_report = Report(metrics=[
-    TextEvals(column_name="Review_Text")
-    ]
-)
+    TextEvals(column_name="Review_Text", descriptors=[
+        Sentiment(),
+        TextLength(),
+        ]
+    ),
+])
 
 text_evals_report.run(reference_data=None, current_data=reviews)
 ```
 
-There are more evals to choose from. You can also create custom ones, including LLM-as-a-judge.
+There are 20+ built-in evals to choose from. You can also create custom ones, including LLM-as-a-judge. We call the result of each such evaluation a `descriptor`. 
 
 View a Report in Python:
 
 ```
 text_evals_report
 ```
 
-You will see a summary distribution of results for each evaluation.
+You will see the summary results: the distribution of length and sentiment for all evaluated texts.  
 
 # 4. Send results to Evidently Cloud 
 
-To record and monitor evaluations over time, send them to Evidently Cloud. You'll need an API key.
-* Sign up for an [Evidently Cloud account](https://app.evidently.cloud/signup), and create your Organization.
-* Click on the **Teams** icon on the left menu. Create a Team - for example, "Personal". Copy and save the team ID. ([Team page](https://app.evidently.cloud/teams)).
-* Click the **Key** icon in the left menu to go. Generate and save the token. ([Token page](https://app.evidently.cloud/token)).
-
-Connect to Evidently Cloud using your token.
+To record and monitor evaluations over time, send them to Evidently Cloud. 
+* **Sign up**. Create an [Evidently Cloud account](https://app.evidently.cloud/signup) and your Organization.
+* **Add a Team**. Click **Teams** in the left menu. Create a Team, copy and save the Team ID. ([Team page](https://app.evidently.cloud/teams)).
+* **Get your API token**. Click the **Key** icon in the left menu to go. Generate and save the token. ([Token page](https://app.evidently.cloud/token)).
+* **Connect to Evidently Cloud**. Pass your API key to connect from your Python environment. 
 
 ```python
-ws = CloudWorkspace(token="YOUR_TOKEN_HERE", url="https://app.evidently.cloud")
+ws = CloudWorkspace(token="YOUR_API_TOKEN", url="https://app.evidently.cloud")
 ```
-
-Create a Project inside your Team. Pass the `team_id`:
+* **Create a Project**. Create a new Project inside your Team, adding your title and description:
 
 ```python
 project = ws.create_project("My test project", team_id="YOUR_TEAM_ID")
 project.description = "My project description"
 project.save()
 ```
 
-Send the Report to the Cloud: 
+* **Upload the Report to the Project**. Send the evaluation results: 
 
 ```python
 ws.add_report(project.id, text_evals_report)
 ```
 
-Go to the Evidently Cloud. Open your Project and head to the "Reports" in the left menu. ([Cloud home](https://app.evidently.cloud/)).
+* **View the Report**. Go to the Evidently Cloud. Open your Project and head to the "Reports" in the left menu. ([Cloud home](https://app.evidently.cloud/)).
 
 ![](../.gitbook/assets/cloud/toy_text_report_preview.gif)
 
-In the future, you can log ongoing evaluation results to build monitoring panels and send alerts.
+# 5. Get a dashboard 
+
+Go to the "Dashboard" tab and enter the "Edit" mode. Add a new tab, and select the "Descriptors" template.
+
+You'll see a set of panels that show Sentiment and Text Length with a single data point. As you log ongoing evaluation results, you can track trends and set up alerts. 
+
+![](../.gitbook/assets/cloud/add_descriptor_tab.gif)
 
 # Want to see more?
 
-Check out a more in-depth tutorial to learn key workflows. It covers using LLM-as-a-judge, running conditional test suites, monitoring results over time and more.
+Check out a more in-depth tutorial to learn key workflows. It covers using LLM-as-a-judge, running conditional test suites, monitoring results over time, and more.
 
 {% content-ref url="tutorial-llm.md" %}
 [Evidently LLM Tutorial](tutorial-llm.md). 

docs/book/monitoring/design_dashboard_api.md

@@ -434,7 +434,7 @@ project.dashboard.add_panel(
 
 **Aggregated by Status**. To show the total number of failed Tests (status filter), with daily level aggregation.
 
-```
+```python
 project.dashboard.add_panel(
     DashboardPanelTestSuite(
         title="All tests: aggregated",
@@ -452,7 +452,7 @@ project.dashboard.add_panel(
 
 **Filtered by Test ID**. To show all results for a specified list of Tests (on constant columns, missing values, empty rows) with daily-level aggregation.
 
-```
+```python
 project.dashboard.add_panel(
         DashboardPanelTestSuite(
             title="Data quality tests",