The Ask Questions App allows you to query your text data at scale, through the app you can test out questions to see potential results, refine that question until you have the results you are looking for and then apply that question to all of your data
Third party API key required
|The Ask Questions app uses functionality from OpenAI, you will need your own OpenAI account to access this app (it is greyed out with a banner unless an OpenAI API key is added) and costs associated with the use of the Graft app will appear on your OpenAI account.|
- Select the App type you would like to create from the App Library template tab
- Mousing over the App tile will display a short description of the App and its applications
Select which of the methods you would like to create the App if you have your own data ready to go
Alternatively use the Graft Demo data source
For the Question and Answer
- Enter a name for your App entity
- Select a Primary Key (a field with a unique ID for each item of data)
- Select the Field the question will be made to.
Graft provides 10 samples of your data which can be navigated through using the and arrows. Add in your question in the question section and click on to generate an answer for the sample, you can refine your question to optimize your results as much as needed ahead of creating your App.
Once you are happy that your question is generating good results click on CREATE APP to start processing your data. A sample of 100 entries will initially be created.
The TRY IT tab allows you to review answers generated with your new app. The right hand panel shows the current configuration, the name of the entity which holds your app data, the field we are asking questions of and information about the current data set.
The Question asked will appear at the top of the Try it tab, in this example "does this review mention the staff and their service"
- Clicking on the SYNC DATA button will ingest and process all the items associated with the data source, until this is carried out you will see a yellow warning banner at the top of the search window
- Clicking on the icon will schedule daily ingestion and processing of your data source. If you would like to configure more frequent data processing you can enable a processing workflow.
- Clicking on the ANSWER ALL ROWS will ingest and process all the items associated with the data source.
Results in a comparison view with the input field on the left and answer on the right.
- Click on the and arrows to step through the available samples
This tab allows you to experiment with an API snippet which can then be copied and used in your own development environment
You will need an API key to start. If none are available Click on the Create an API key link and follow these instructions. If there are one or more API keys in the project you can switch between then using the API key drop down menu. Click on MANAGE KEYS to add or delete new keys.
The API snippet is controlled from the configuration bar on the right.
Changes made to the configuration are immediately shown in the code.
Use the Output format drop down to switch between CSV (default), TSV or JSONL (JSON Lines) formats
The Entity_columns drop down allows you to add or remove columns from the output
Entity_Predictors dropdown shows the current summary model. If you are using the underlying entity in multiple Apps the list of predictors will appear here. You can select/deselect as needed.
NOTE: One predictor MUST be selected for the API query to complete successfully
Each configuration item can be compressed by clicking on the icon
Once you have adjusted any query configuration parameters click on TEST REQUEST to run the API query.
This tab allows you to delete your app, see which field is being processed for the App and also enable the App for external API access.
App API limits
The number of Apps available for external access is limited by your tier. If no APIs are remaining you will need to disable any existing APIs (save the changes) and then enable the App API of interest or consider upgrading to a bigger tier.