Scheduler

Creating Custom DataApp using Scheduler as an input

Use this procedure to create a custom DataApp using job an an input. Note that these DataApps are model-independent, so no project model is required to create this type of custom DataApp.

Note: Ensure that at least one job has been created and run successfully, with datasets in a built state. Without a successful job run, the datasets will not be available for selection or for executing prompts.

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.

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

4. Select an input as Scheduler. Based on the selected input, the fields change.

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

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

   • OpenAI GPT-4 Turbo

   • Azure OpenAI GPT-4o

   • Anthropic Claude 3.5 Sonnet (beta)

3. Select the job on which you want to create the DataApp from the list of jobs created in the project.

4. Toggle ON the Enable Response Caching option to return the same response for the identical queries despite asking multiple times.

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

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

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

4. Click Create. The DataApp card is created.

datasetinputjob

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

2. Click Select Dataset to Start in the prompt box drop-down and select the dataset you want. All the datasets you are viewing in the drop-down are the input and output datasets generated after the latest job run.

datasetinputjob1

Once you select the dataset, this loads the data onto the chat window.

1. Enter your query in the query box and use a slash (/) to select 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.

You can also choose from prompt suggestions tailored to the selected dataset.

Note:

• If you select prompt suggestions, AskAI will provide five relevant prompts. You can either copy a suggestion into the query box or run it directly using the Run button.

• If you have an existing AskAI chat created to query input and output datasets or other job-generated outputs, the chat will continue to reference datasets from the previous job run. To query the latest scheduler inputs and outputs, you will need to create a new chat each time.

1. Click the Scheduler Charts tab to add charts generated after the schedule run in this tab.

2. Click Add Charts from Scheduler to add charts. You can choose the charts you want to add to the DataApp if there are multiple charts generated.

jobscharts

1. Click Add Chart To DataApp next to the chart you want to add. However, if you no longer want this chart in the Job Charts tab, you can use Remove From DataApp to remove it.

Note: Charts are displayed only if the data pipeline generates chart outputs. Furthermore, once a chart output is created after running a query, it cannot be edited like other DataApp input types—for example, modifying the title or changing colors.