Users can now harness the power of machine learning in the Connectors framework with the introduction of our AI Data Cleaning transform. This new transform takes user-provided examples of input/output transformations to create and apply a model for transforming data.
Using only 3 examples, our AI Data Cleaning algorithm can automate specific data manipulations at scale, without needing a user to write custom functions. This added flexibility is extremely helpful for users who may otherwise have difficulty with or be unable to write the necessary logic they need to easily transform their data.
For instance, with AI Data Cleaning, users could train a model with only 3 samples of input/output pairs (see examples below) to extract a price value from variable text strings (e.g., promotional messages). The model is then applied at scale to a column of your ingested data to transform the inputs into the desired outputs.
| Ex. | Input (Text) | Output (Price) |
|---|---|---|
| 1 | Limited time only! The price is only $883 or $ 41.91/mo. for 6 mo. | USD 883 |
| 2 | New product! Costing only $368 or $ 43.52 / mo. for 24 mo. | USD 368 |
| 3 | Limited time only! Now $481 or $ 68.38 / mo for 24 mo. | USD 481 |
Note: This feature is currently available as a Preview Feature. Click here to learn more about Yext’s Preview Feature program, and to see which Preview Features are currently available.
To leverage this feature, users will need to enable the Winter ‘22 Release: AI Data Cleaning Transform (Preview) feature within their account.
For more details on how to use this transform, visit our AI Data Cleaning Transform reference doc.