updates

Author: alelavml3

md-docs/user_guide/task.md

@@ -5,19 +5,34 @@ A Task represents an ordinary artificial intelligence task like regression, clas
 
 A Task is associated with a [Model] and a [Data schema] that describes all the information about the data in the Task.
 
+A Task is associated with a unique identifier that will be used by SDK to operate on it.
+The identifier can be retrieved from the Task homepage or by looking at the url.
+
+A Task has a *status* that summarizes the health of its AI model.
+The status depends on the monitoring module and changes from Ok, Warning or Drift when the Monitoring modules detects drifts on monitored quantities.
+
+Moreover, in the Task homepage is present the section named "Data events" which shows the most recent detection events generated by the monitoring module.
+It is possible to click on *view* to see more details or discard the notification (the event will remain available for future analysis on the [Detection] page).
+
+## Attributes
+
 A Task is described by a set of attributes specified during its creation.
-Some attributes are common for every Task while, others vary according to its type.
+Some attributes are common for every Task, while others vary according to its type.
 Generic attributes are:
 
 | Attribute | Description |
 |--|--|
 | Name | Name of the Task, unique for the Project. |
-| Tags | Optional customizable list of tags. It is used to better describe the Task and to improve search. |
+| Tags | Optional customizable list of tags. They are used to better describe the Task and to improve search. |
 | Task type | Artificial intelligence type of Task. Possible values are:<br><ul><li>[Regression](task.md#regression)</li><li>[Binary classification](task.md#classification)</li><li>[Multiclass classification](task.md#classification)</li><li>[Multilabel classification](task.md#classification)</li><li>[Retrieval Augmented Generation](task.md#retrieval-augmented-generation)</li><li>[Object Detection](task.md#object-detection)</li></ul>|
-| Data structure | Type of input data the Task uses. Possible values are:<br><ul><li>Tabular</li><li>Image</li><li>Text: when data structure is Text, attribute *Text Language* is required.</li><li>Embeddings: input data are arrays that could represent embedding either image or text data. This data structure is used when raw data are not shared with ML cube Platform.</li></ul> |
+| Data structure | Type of input data the Task uses. Possible values are:<br><ul><li>Tabular: standard table based data used in contexts like regression or classification.</li><li>Image: images in their different formats and channels.</li><li>Text: textual data expressed as strings. When data structure is Text, attribute *Text Language* is required.</li><li>Embeddings: input data are arrays that could represent embedding either image or text data. This data structure is used when raw data are not shared with ML cube Platform.</li></ul> |
 |Optional target| Boolean value that specifies if the ground truth is always available or not. In some Tasks, the actual value is not present until explicit labeling is done. In this cases, the Task is marked as with optional target so that ML cube Platform works accordingly. |
 | Cost info | Optional information about costs that depend on Task Type. |
 
+
+!!! warning
+    Some Task's attributes are immutable: type, data structure and optional target flag cannot be modified after the creation of the Task.
+
 Most of ML cube Platform operations are done at Task level: monitoring, retraining, analytics and other features are specific to AI models and data that belong to a Task.
 Indeed, each task type has a set of ML cube Platform modules:
 
@@ -30,9 +45,12 @@ Indeed, each task type has a set of ML cube Platform modules:
 | RAG Evaluation | :material-close: | :material-close: | :material-check: | :material-close: |
 | LLM Security | :material-close: | :material-close: | :material-check: | :material-close: |
 
+!!! Tip
+    On the left side of the web app page is present the Task menù with links to the above mentioned modules and Task settings.
+
 ## Task Type
 
-ML cube Platform support several task types providing specific features for each of them.
+ML cube Platform supports several task types providing specific features for each of them.
 Not all task types are compatible with data structures, in the table below are shown which data structure is supported by which task type:
 
 |Task type| Tabular | Image | Text | Embedding|
@@ -117,10 +135,23 @@ Moreover, in this Task, the Target is a text as well and the input is composed o
 
 RAG tasks has additional attribute *context separator* which is string used to separate different retrieved contexts into chunks. Context data is sent as a single string, however, in RAG settings multiple documents can be retrieved. In this case, context separator is used to distinguish them. It is optional since a single context can be provided.
 
+!!! example
+    Context separator: <CONTEXT>
+    
+    Context data: The capital of Italy is Rome.<CONTEXT>Rome is the capital of Italy.<CONTEXT>Rome was the capital of Roman Empire.
+
+    Contexts:
+
+        - The capital of Italy is Rome.
+        - Rome is the capital of Italy.
+        - Rome was the capital of Roman Empire.
+
+
 ### Object Detection
 
 Object Detection task processes images and provides as output a list of bounding boxes with associated label indicating the type of identified entity.
 Therefore, target is a list of four elements tuples indicating the vertex of the box and a string label for the entity type.
 
 [Model]: model.md
-[Data schema]: data_schema.md
+[Data schema]: data_schema.md
+[Detection]: detection.md