Canvas overview
Canvas is a place where you can build data pipelines and machine learning models by importing datasets and adding recipes. Once you create a project, you are navigated to the Canvas, where you can create, test, and train models using various recipe types.
Types of Recipes
AI-Assisted Recipe – Enter a text prompt to generate a recipe in seconds using AI and integrate it into your pipeline.
Rapid Canvas Recipe – Automatically runs an end-to-end machine learning flow by simply uploading a dataset.
Code Recipe – Write custom code to transform data and generate outputs, including datasets, charts, text, or models. Designed specifically for data scientists.
Template Recipe – Provides predefined templates for common tasks such as data cleaning, data preparation, data analysis, feature engineering, model building, model prediction, and visualization.
The Canvas offers a flexible and efficient way to build and refine data pipelines.
You can perform the following tasks on the canvas to create flows:
Input the dataset or text file
Execute or run recipes (Template, AI-assisted, code, or rapid model)
Get the output dataset or a chart, text, or model
Getting familiar with these areas will help business users to build models more efficiently without writing any Python code or ML expertise. With a user-friendly interface, any user can get started with building machine learning models.
Building blocks and significance
The following are the building blocks you view while building the data pipeline.
Dataset
This icon represents a dataset. It is displayed when you import a dataset onto the canvas successfully, or when a dataset is generated after running a recipe.
Recipe
This icon represents a recipe. It executes various transforms related to data cleaning, preparation, analysis, feature engineering, model building, prediction and visualization.
Dashboard
This icon represents a dashboard. You can visualize the data presented in the form of charts and scatter plots.
Unbuilt recipe
This icon represents a recipe added to the flow but has no transformations added.
Running the recipe
This icon represents the recipe execution in progress.
Error
This icon represents a recipe error. It is displayed when the recipe is failed during its execution.
Model
This icon represents a model that is generated after running a recipe.
Artifact
This icon represents an artifact generated after running a recipe.
Empty dataset
This icon represents an empty output dataset. It is displayed when the recipe run is in progress.
Empty recipe
This icon represents a recipe added to the flow but is not executed.
Code recipe
This icon represents a code recipe that has been added to the data pipeline
Dag view options
Use these Dag view options to change the view of the data pipeline.
Zoom in
Use this option to enlarge the DAG.
Zoom out
Use this option to shrink the DAG.
Fit view
Use this option to fit the Dag into the size of the screen.
Auto arrange canvas nodes
Use this option to auto arrange canvas nodes. This formats the building blocks and lines in the flow to make it easier to read. It also ensures that the connectors do not overlap with another.
Curved connector
Use this option to use curved lines for aligning the building blocks.
Straight connector
Use this option to use straight lines for aligning the building blocks.
Save canvas nodes orientation
Use this option to save the order in which you arranged the building blocks on the canvas manually.
Expand all
Use this option to expand all the nodes in the data pipeline.
Collapse all
Use this option to collapse all the nodes in the data pipeline.
Snippet Generator
Use this option to generate AI snippet for each node on the canvas.
Shortcut options on canvas
Quick Actions on Canvas Components
You can perform quick actions on different components on the canvas, such as datasets, artifacts, recipes, models, and charts, using the shortcut options. You must right-click on each component to view these options.
Available Quick Actions
Source Dataset
Preview
Add AI-assisted recipe
Add Rapid Model recipe
Template recipe
API Connector recipe
AI Guide
Add File
Export
Delete
Collapse
Reload – Available for datasets imported through data connectors, allowing you to fetch the latest data as needed.
Recipe
Preview
Run recipe
Check logs
Delete recipe
Stop recipe (Visible only when the recipe run is in progress)
Collapse
Chart
Preview
Delete
Model
Preview
Create prediction service
AI Guide
AI-assisted recipe
Template recipe
API Connector recipe
Manual Prediction
Prediction scheduler
Delete
Artifact
Preview
AI-assisted recipe
Template recipe
API Connector recipe
Delete
Output Dataset
Preview
Add AI-assisted recipe
Add Rapid Model recipe
Template recipe
API Connector recipe
AI Guide
Add Destination
Export
Delete
Unbuilt Recipe
Preview
Run Recipe
Logs
Delete
Collapse
Unbuilt Output Dataset
Preview
+Add destination
Delete
Unbuilt Chart
Delete
Unbuilt Model
Preview
Prediction Service
Delete
Unbuilt Artifact
Preview
Delete
Unbuilt Source File
Preview
Add file
Delete
Reload – If the source file is uploaded from connectors, this option replaces "Add file."
Note: When you right-click anywhere on the canvas, a menu appears with the following options:
Dataset
Artifact
Model
Text File
Recipes (AI-Assisted, Rapid Model, Template, and Code Recipes)
Various options to create a machine learning flow on the canvas
Use these options to build machine learning flows.
How to access?
Dataset
The option to upload a dataset onto the canvas to do the predictions.
Artifact
The option to add artifacts onto the canvas.
Model
The option to add an existing model to the canvas.
Template
The option to add pre-defined templates to the canvas to perform data cleaning, data pre-processing, feature engineering and model building.
AI-assisted
The option to use AI to generate the recipes or templates you want by providing a text prompt.
Rapid Model
The option to build machine learning models automatically by uploading the dataset and selecting the problem type.
Code
The option to write Python code to generate datasets and run recipes.
Text
The option to add text files (supported formats - txt, html, json or markdown)
Other Options Available on the Canvas
Run
Run: Executes the recipes using the data currently available in the datasets on the canvas. This option remains disabled until recipes are added to the canvas.
Run with Fresh Data: Retrieves fresh data from data connectors and runs the data pipeline.
RapidCanvas AI Guide – Generates the steps required to develop a model for the selected use case.
Switch Scenarios– Click the drop-down to switch between scenarios within the project.
Search Entities – Search for a specific entity in the canvas using the search option.
Queuing the Recipes
When triggering multiple recipes on the canvas, subsequent recipes are queued if the first recipe run is in progress using the queuing recipe feature. For the first recipe, you can view the Run option. If you want to run a series of other recipes on the canvas, you can right-click on the desired recipe to see the Add to Queue option. Clicking this option will add the recipe to the queue.
Queuing a Recipe in the Data Pipeline
Select the project to navigate to the canvas view page.
Right-click on the first recipe node on the canvas and click the Run option. To queue another recipe, right-click and select Add to Queue.
Click the Recipe Queue icon beside the Run button. This displays the list of recipes queued to run in sequential order.
Review the recipes in the queue:
Recipe – Name of the recipe.
Scenario – Scenario in which the recipe is being run.
Status – Current status of the recipe. Possible values:
Running – Recipe run is in progress.
In Queue – Recipe is queued as the other recipe run is in progress.
Success – Recipe run completed successfully.
Error – An error occurred while running the recipe.
Run Triggered At – Time when the recipe run was triggered.
Actions:
Click the Delete icon to remove the recipe from the queue.
Click the Log icon to view recipe logs. If the recipe fails, check the logs to identify and fix the issue.
Additional Actions in the Recipe Queue
Click Clear All to remove all recipes from the queue.
Use the Reorder option next to each recipe to adjust the execution order.
AI Guide
The AI Guide feature is available for datasets, models, charts, and Rapid Canvas recipes.
Datasets and Models
To access the AI Guide for datasets or models, right-click on the respective dataset or model block. This redirects you to the AI Guide page, where a chat interface is initiated. You can interact with the AI specifically regarding the dataset or model you have selected and ask follow-up questions based on the response received.
Accessing AI Guide from a Dataset
Charts
For charts, the process is slightly different. First, click on the chart block on the canvas. This action opens the Charts page, where each chart has an AI Guide option. Clicking on the AI Guide for a particular chart allows you to chat with the AI, ask questions, and receive guidance related to the chart data.
Using the AI Guide
Once you access the AI Guide for a dataset, model, or chart, you can engage in an interactive chat with the AI. Users can ask questions related to the data within the selected component.
For datasets, you can inquire about missing values or specific data points.
For models, you can ask about performance metrics, training data details, or explanations on predictions.
For charts, you can request insights such as trends, outliers, or comparisons.
The Ask AI Guide provides dynamic prompt suggestions that adapt to your queries, ensuring relevant and insightful guidance.
See also
To learn more about the other tabs on canvas, read the following sections:
Last updated
