This page covers on how to manage and use dataapps.
DataApps
DataApps are interactive visualizations built using React, designed for four main problem types within Rapid Model Recipes: Binary Classification, Regression, Multi-Class Classification, and Binary Experimental.
You can create two types of DataApps: Model DataApps and Custom DataApps.
Model DataApps: These are dependent on a trained model and can only be created if a project includes one. They focus on visualizing the performance and predictions of the specific model in your project.
Custom DataApps: These are not tied to a specific model and support a variety of inputs, making them flexible for different data sources. Custom DataApps can be built using:
Project Canvas Datasets: Use all datasets available on the project canvas, including any user-uploaded datasets. This option also allows you to use AskAI to explore these datasets interactively.
Uploaded Datasets: You can apply AskAI to analyze any datasets you upload, providing a straightforward way to explore your data without needing a model.
SQL Sources: Connect directly to MySQL databases through pre-configured connectors, allowing you to fetch and analyze data directly from these sources using AskAI.
Documents and PDFs: Allows you to upload documents in formats like PDF, DOC, and DOCX directly into the DataApp. Once uploaded, the Ask AI feature allows users to query the document contents, enabling quick extraction of insights, information analysis, and text-based responses.
On the other hand, the DataApps can also be built by writing Python code on Juypter Notebook. If the DataApps are built from Notebook, business users can consume those once are deployed by data scientists. The data scientist will first create an app template on the Juypter Notebook and uses this app template to deploy the dataapp passing a project ID, scenario, artifact, or model. Business users can only view and delete the dataapps published onto the UI from the Notebook, but cannot create, modify the app templates. All the app templates created in a tenant are saved in the Data app module.
If you want to generate a chart, you can either create a custom template on the Notebook or use an existing system template. Examples of system templates you can use to generate the chart after building the machine learning flows are - Correlation Matrix, EDA data drift, Pivot Table viewer, Visual Analytics, Pandas Profiler, and so on. Using a system or custom template, you can generate the charts only with the default Streamlit version. Contrary to this, dataapps support all Streamlit versions.
The app template is similar to system templates, but app templates can only be used to generate dataapps(charts).
Accessing and Creating a Model DataApp at a project level
Use this procedure to create a model DataApp in a project. After you run the data pipeline for any of these four problem types such as binary classification, regression, multi-class classification, or binary experimental problems, the DataApp button gets enabled.
Click the menu icon and select Projects
Select the project for which you want to create DataApps and click the DataApps icon from the project level navigation.
Click the plus icon. This takes you to Select Configuration page.
Click the Get Started Now button in the Model DataApp card. This option is only enabled when there is a model in the project. This opens the Model Configuration form.
Specify this information:
- DataApp Name:
The name of the DataApp.
- DataApp Description:
The description of the DataApp.
- Recipe Name:
The recipe for which you want to create a DataApp.
- Choose Image:
Click to upload an image to display on the DataApp card that you see on the DataApps page.
Click Create.
You can see the DataApp card created in this project.
Viewing dataapps in a tenant
Use this procedure to view the dataapps created on the UI or published by Notebook users from Notebook.
Click the menu icon and select DataApps. This displays the dataapps dashboard where you can see all the DataApps for different projects in this tenant.
Note
The DataApps will become inactive after a certain period set by the admin. If you want to use DataApps, you must relaunch.
Click Relaunch on the DataApp card that you want to launch again.
Click on the Dataapp. The screen displays the following tabs:
Feature importance - Assigning scores to input features based on how helpful they are in predicting a target variable. These scores are ranked to help users understand which features have a significant impact on model prediction.
Model performance - This evaluates the performance of the model.
What-If analysis - Help data scientists to get insights into what a model predicts for given input values. This allows them to experiment with various combinations of values for key features and observe the resulting predictions.
You can use the sliders to change the values or use drop-down to select values and click Predict What-If Outcome to review what the model predicts for the given input values.
Prediction - You can perform predictions on the uploaded dataset. For more information, see Performing predictions on the uploaded dataset.
Performing predictions on the uploaded dataset
Use this procedure to do the predictions on the new dataset and generate charts using Ask AI.
Click Browse to upload the dataset and obtain predictions generated by the model.
Click Upload File From Local. Once you upload the file, click Close to upload.
Click Generate Prediction. Once the prediction is done on the dataset, you can download the prediction results, using the Download option.
Note
You can use the Log option to view the detailed records of the execution activity and identify issues.
Click Ask AI button.
Important
Apart from generating charts, you can also perform data transformation operations on the dataset by prompting for the Ask AI.
Click +DataApp to add this chart to the dataapp. The Update Name box appears where you can provide the custom name for the chart and click Save.
Click the User Charts tab to view this chart.
Ask AI - You can use the Ask AI feature similar to what you see in AI-assisted recipe to provide text prompt in the chat window and generate the chart outputs on the dataset used for model building. This allows you to generate visualizations and carry out different data pre-processing operations on the selected dataset.
You can add as many chats as you want and switch between the chat windows from the Chat list on the left. The difference between the chat window used for prediction output dataset and dataset used for model building can be see in its chat name on the left.
Perform the following actions clicking the caret icon:
Copy the dataapps URL to share with the other business users, using the Copy option.
Open the dataapps on a new tab, using the Open in New Tab option.
Configure the shutdown time of the DataApp, using the Config option.
View logs of DataApps to debug issues, using the Logs option.
Delete the DataApp that is no longer required, using the Delete option.
Creating Custom DataApp using project Canvas datasets as input
Use this procedure to create a custom DataApp. Note that these DataApps are model-independent, so no project model is required to create them.
Click the menu icon and select Projects
Select the project for which you want to create DataApps and click the DataApps icon from the project level navigation.
Click the plus icon. This shows the select configuration form.
Click Get Started Now under the Custom DataApp card to create a custom Dataapp. This opens the Custom Configuration form.
Specify this information:
- DataApp Name:
The name of the Dataapp.
- DataApp description:
The description of the Dataapp.
Click Choose Image to browse and select the image that is visible on the DataApp cards.
Select an input from the Inputs section. Possible options:
Project Canvas Datasets - Use the datasets available in the project and uploaded by the user.
Custom Uploaded Datasets - Use the datasets that are uploaded by the user.
SQL Sources - Use the data that is fetched from the SQL databases.
Documents and PDFs - Use the datasets uploaded in pdf, doc, or docx formats.
Here we are selecting Project Canvas Datasets as an input option.
Select a model that you want to use in the Custom DataApp. Possible values:
Open AI GPT-4 Turbo
Open AI GPT-4o
Azure OpenAI GPT-4o
Toggle ON the Enable Response Caching option to return the same response for the identical queries despite asking multiple times.
Select the Security options. Possible values:
Sample Data : The sample of 5 rows of data is shared with the LLM for context.
Only Metadata: Only the column names in the dataset are shared with the LLM for context.
Enter Model controls in the text box to provide specific context to the AI guide. This helps in aligning the AI-generated responses more closely with the user’s particular use case
Click Create.
Click on the DataApp card to launch the AskAI DataApp. The AskAI chat window appears.
Select the Dataset on which you want to create the DataApp. You can view all the datasets that are on the canvas in the drop-down.
Note
You can also view the +Upload New Datasets option in the datasets drop-down, from where you can upload a new dataset on which you want to run the query using AskAI.
Enter the query in the query box. You can use slash to choose the type of output you want the AI to generate, such as text, dataset, or chart.
If you have generated a chart using the Ask AI, then you can view the + DataApp option.
Click + DataApp to add this chart to the dataapp. Clicking this opens the Update Name box where you can provide the custom name for the chart and click Save.
Once a chart is added, you can easily track the total number of charts added under the User Charts tab. An indicator on this tab displays the number of charts.
Click the User Charts tab to view this chart.
Creating Custom DataApp using Datasets as an input
Use this procedure to create a custom DataApp using Datasets an an input. Note that these DataApps are model-independent, so no project model is required to create them.
Click the menu icon and select Projects
Select the project for which you want to create DataApps and click the DataApps icon from the project level navigation.
Note
You can also view the +Upload New Datasets option in the datasets drop-down, from where you can upload a new dataset on which you want to run the query using AskAI.
Click the plus icon. This shows the select configuration form.
Click Get Started Now under the Custom DataApp card to create a custom Dataapp. This opens the Custom Configuration form.
Specify this information:
- DataApp Name:
The name of the Dataapp.
- DataApp description:
The description of the Dataapp.
Click Choose Image to browse and select the image that is visible on the DataApp cards.
Select an input as Uploaded datasets.
Select a model that you want to use in the Custom DataApp. Possible values:
Open AI GPT-4 Turbo
Open AI GPT-4o
Azure OpenAI GPT-4o
Toggle ON the Enable Response Caching option to return the same response for the identical queries despite asking multiple times.
Select the Security options. Possible values:
Sample Data : The sample of 5 rows of data is shared with the LLM for context.
Only Metadata: Only the column names in the dataset are shared with the LLM for context.
Enter Model controls in the text box to provide specific context to the AI guide. This helps in aligning the AI-generated responses more closely with the user’s particular use case
Click Create. The DataApp card is created.
Click on the DataApp card to launch the AskAI DataApp. The AskAI chat window appears.
Click Select Dataset to Start in the prompt box drop-down and select +Upload New Datasets. This opens the Upload Dataset(s) window.
Click Upload Files From Local to upload the file and then click Upload. Once done, click Done.
Enter the query in the query box. You can use slash to choose the type of output you want the AI to generate, such as text, dataset, or chart.
If you have generated a chart using the Ask AI, then you can view the + DataApp option.
Click + DataApp to add this chart to the dataapp. Clicking this opens the Update Name box where you can provide the custom name for the chart and click Save.
Once a chart is added, you can easily track the total number of charts added under the User Charts tab. An indicator on this tab displays the number of charts.
Click the User Charts tab to view this chart.
Note
You can upload and run queries on as many datasets as you want. To upload a new dataset, click the plus button next to Charts on the left side.
Creating Custom DataApp using SQL sources as an input
Use this procedure to create a custom DataApp using SQL sources an an input. Note that these DataApps are model-independent, so no project model is required to create them.
Click the menu icon and select Projects
Select the project for which you want to create DataApps and click the DataApps icon from the project level navigation.
Note
You can also view the +Upload New Datasets option in the datasets drop-down, from where you can upload a new dataset on which you want to run the query using AskAI.
Click the plus icon. This shows the select configuration form.
Click Get Started Now under the Custom DataApp card to create a custom Dataapp. This opens the Custom Configuration form.
Specify this information:
- DataApp Name:
The name of the Dataapp.
- DataApp description:
The description of the Dataapp.
Click Choose Image to browse and select the image that is visible on the DataApp cards.
Select an input as SQL Sources.
Select a model that you want to use in the Custom DataApp. Possible values:
Open AI GPT-4 Turbo
Open AI GPT-4o
Azure OpenAI GPT-4o
Toggle ON the Enable Response Caching option to return the same response for the identical queries despite asking multiple times.
Select the Security options. Possible values:
Sample Data : The sample of 5 rows of data is shared with the LLM for context.
Only Metadata: Only the column names in the dataset are shared with the LLM for context.
Enter Model controls in the text box to provide specific context to the AI guide. This helps in aligning the AI-generated responses more closely with the user’s particular use case
Click Create. The DataApp card is created.
Click on the DataApp card to launch the AskAI DataApp. The AskAI chat window appears.
Click Select Data Connector drop-down in the prompt box. This opens the Select Data Connector window.
Select the connector from which you can to fetch the data.
Note
You need to first configure the connectors on the Connectors page to view here in the connectors list.
Click Next. This opens the Select Table from Connector window.
Select the table from the list and click Connect. You can view the data fetched from the table on the chat window.
Enter the query in the query box. You can use slash to choose the type of output you want the AI to generate, such as text, dataset, or chart.
If you have generated a chart using the Ask AI, then you can view the + DataApp option.
Click + DataApp to add this chart to the dataapp. Clicking this opens the Update Name box where you can provide the custom name for the chart and click Save.
Once a chart is added, you can easily track the total number of charts added under the User Charts tab. An indicator on this tab displays the number of charts.
Click the User Charts tab to view this chart.
Note
You can upload and run queries on as many datasets as you want. To upload a new dataset, click the plus button next to Charts on the left side.
Creating Custom DataApp using Documents and PDFs as an input
Use this procedure to create a custom DataApp using documents and PDFs an an input. Note that these DataApps are model-independent, so no project model is required to create them.
Click the menu icon and select Projects
Select the project for which you want to create DataApps and click the DataApps icon from the project level navigation.
Click the plus icon. This shows the select configuration form.
Click Get Started Now under the Custom DataApp card to create a custom Dataapp. This opens the Custom Configuration form.
Specify this information:
- DataApp Name:
The name of the Dataapp.
- DataApp description:
The description of the Dataapp.
Click Choose Image to browse and select the image that is visible on the DataApp cards.
Select an input as Documents and PDFs.
Toggle ON the Enable Response Caching option to return the same response for the identical queries despite asking multiple times.
Enter Model controls in the text box to provide specific context to the AI guide. This helps in aligning the AI-generated responses more closely with the user’s particular use case
Select a model that you want to use in the Custom DataApp. Possible values:
Open AI GPT-4 Turbo
Open AI GPT-4o
Click Create. The DataApp card is created.
Click on the DataApp card to launch the AskAI DataApp. The AskAI chat window appears.
Click Upload Documents to upload the documents in the formats, such as pdf, doc, docx, text, and Markdown. This allows you to browse and upload the document from the local system. Once the document is uploaded, you can start asking the questions to the AskAI
Enter the query in the query box. The generated output will be in the text format.
Dataapps dashboard
Dataapps dashboard has all the dataapps in the form of cards. These datapps are either created in projects or published from the Notebook. Each card gives various details such as project name, description of the project, recipe used, the person who created the dataapp, last shutdown by, and the date and time at which the dataapp was created. You can also launch the app and relaunch when the app is idle.
Use the search box to search for Dataapp templates by name.
The list view provides the Data app details in the table form. You can view the same details that you see in the tile view of Dataapps such as DataApp name, Created on, Created by, Description and Project.
Use the table settings icon to rearrange the columns in the order you want and view or hide the columns by selecting and clearing the check boxes next to the columns.
The card view provides all the data app cards on the dashboard. Click on each card to view the DataApp associated with the project.
Use the filter option to filer the dataapps by project and view only the dataapps associated with the filtered project on the dataapps dashboard. You cannot view this option in project-level DataApps.
Select or clear the projects whose dataapps you want to view or hide.
Click Apply.
Editing a DataApp
Use this procedure to delete a DataApp.
To edit a DataApp:
Click the menu icon and select DataAapps. This shows the DataApps created under this tenant and in different projects.
Click on the ellipses icon on a DataApp that you want to edit and select the Edit option. This opens the side panel window to make changes to DataApp details.
Modify the details and Click Save to update the changes.
Deleting a DataApp
Use this procedure to delete a DataApp.
To delete a DataApp:
From the left navigation menu, select DataAapps. The DataApps dashboard is displayed.
Click the ellipses icon on the DataApps dashboard.
Click Delete. The dialog box appears prompting you to delete or discard
Click Yes, Delete to delete the DataApp permanently.
Viewing DataApp logs
Use the history of DataApp logs to debug the issues in DataApp.
To view DataApp logs:
From the left navigation menu, select DataAapps. The DataApps dashboard is displayed.
Click the ellipses icon on the DataApps dashboard.
Click Logs. The dialog box appears prompting you to delete or discard.
You can now view the DataApp logs.
Configuring DataApp Shutdown Time
Use this procedure to configure the shutdown time for DataApp. You can also check resource consumption while DataApp is running.
To view DataApp logs:
From the left navigation menu, select DataAapps. The DataApps dashboard is displayed.
Click the ellipses icon on the DataApps dashboard.
Click Configs.
The Configuration & Consumption side-panel appears.
Select the time period (in hours) after which the DataApp should automatically shut down if it remains inactive.
Select Evergreen check box to keep the DataApp Running always.
Clear this check box to specify the time after which the DataApp must shut down if there is no activity. You can set the time in hours.
Click Save.