Project Canvas Datasets

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.

1. Hover over the menu icon and select Projects

2. Select the project for which you want to create DataApps and click the DataApps icon from the project level navigation.

datapps123

1. Click the plus icon and select Custom DataApp. This opens the Configuration page.

2. Specify this information:

DataApp Name: The name of the Dataapp.

DataApp description: The description of the Dataapp.

Environment: By default, the environment selected during project creation is applied. However, you have the flexibility to choose a different environment for running your DataApps.

1. Click Choose Image to browse and select the image that is visible on the DataApp cards.

2. Select an input from the Inputs section. Possible options:

   • Project Canvas Datasets – Select datasets available within the project, including those uploaded by the user.

   • Custom Uploaded Datasets – Use datasets that the user has manually uploaded.

   • SQL Sources – Fetch and use data directly from SQL databases.

   • Documents & PDFs – Utilize datasets uploaded in PDF, DOC, or DOCX formats.

   • Prediction Service – Use a prediction service as input for the DataApp.

   • Scheduler – Use a scheduler as input. A scheduler must be created beforehand to select this option.

   • Model DataApp – Use a machine learning model as the input source.

Here we are selecting Project Canvas Datasets as an input option.

1. Select a model that you want to use in the Custom DataApp. Possible values:

   • OpenAI GPT-4 Turbo

   • OpenAI GPT-4o (by default this is selected)

   • Azure OpenAI GPT-4o

   • Anthropic Claude 3.5 Sonnet (beta)

2. Toggle ON the Show Model Response Code option to return the same response for the identical queries despite asking multiple times.

3. Select Access Control to manage access to chats and charts generated within the DataApp. The available options are:

• Team Access: Allows all users within the tenant to view chats and charts in the DataApp.

• Individual Access: Restricts visibility of chats and charts to users who created them. For example, if User A creates Chat A and Chart C, only User A can view these.

1. 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.

2. 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.

3. Toggle ON the Show Model Response Code option to view the code generated by the model in response to the queries.

4. Enable Allow Column Hyperlinks to create hyperlinks between columns in related tables.

createaskaidataapp18

1. Add starter prompts to help users get started with predefined queries. To add prompts, see Adding starter prompts in DataApps.

2. Click Create. The DataApp card is created.

3. Click on the DataApp card to launch the AskAI DataApp. The AskAI chat window appears.

createaskaidataapp1

1. 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. Alternatively, click the Select from Artifacts tab to choose a document from the Artifacts folder. You can also use the search box to quickly locate the document you need.

createaskaidataapp11

1. 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. Once the output is generated, you can:

• Copy the answer using the Copy Answer option.

• View the generated code by selecting the View Code option.

• Get an explanation for each line of code by using the Explain option, which becomes visible only after clicking View Code.

askaidataappoutput

If you have generated a chart using the Ask AI, then you can view the + DataApp option.

askaidataappoutput1

1. 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.

1. Click the User Charts tab to view this chart.