Connect to Perplexity Data in RapidMiner

This article shows how you can easily integrate the CData JDBC driver for Perplexity into your processes in RapidMiner. This article uses the CData JDBC Driver for Perplexity to transfer Perplexity data to a process in RapidMiner.

Connect to Perplexity in RapidMiner as a JDBC Data Source

You can follow the procedure below to establish a JDBC connection to Perplexity:

1. Add a new database driver for Perplexity: Click Connections -> Manage Database Drivers.
2. In the resulting wizard, click the Add button and enter a name for the connection.
3. Enter the prefix for the JDBC URL:

   jdbc:api:
   

4. Enter the path to the cdata.jdbc.api.jar file, located in the lib subfolder of the installation directory.
5. Enter the driver class:

   cdata.jdbc.api.APIDriver
   

   
6. Create a new Perplexity connection: Click Connections -> Manage Database Connections.
7. Enter a name for your connection.
8. For Database System, select the Perplexity driver you configured previously.
9. Enter your connection string in the Host box.

   Start by setting the Profile connection property to the location of the Perplexity Profile on disk (e.g. C:\profiles\Perplexity.apip). Next, set the ProfileSettings connection property to the connection string for Perplexity (see below).

   Perplexity API Profile Settings

   Visit the Perplexity API dashboard at https://www.perplexity.ai/settings/api to generate an API key.

   Built-in Connection String Designer

   For assistance in constructing the JDBC URL, use the connection string designer built into the Perplexity JDBC Driver. Either double-click the JAR file or execute the jar file from the command-line.

   java -jar cdata.jdbc.api.jar
   

   Fill in the connection properties and copy the connection string to the clipboard.

   

   A typical connection string is below:

   Profile=C:\profiles\Perplexity.apip;ProfileSettings='APIKey=your_api_key';
   

10. Enter your username and password if necessary.

You can now use your Perplexity connection with the various RapidMiner operators in your process. To retrieve Perplexity data, drag the Retrieve operator from the Operators view. With the Retrieve operator selected, you can then define which table to retrieve in the Parameters view by clicking the folder icon next to the "repository entry." In the resulting Repository Browser, you can expand your connection node to select the desired example set.

Finally, wire the output to the Retrieve process to a result, and run the process to see the Perplexity data.