Import Real-Time Mistral AI Data via JDBC in ColdFusion to Build Applications

Adobe ColdFusion is a web and mobile application development platform. It uses its own scripting language, ColdFusion Markup Language (CFML), to create data-driven websites as well as generate remote services, such as REST.

When ColdFusion is paired with the CData API Driver for JDBC, you can link your ColdFusion web and mobile applications to operational Mistral AI data. This allows for your applications to be more robust and complete. This article details how to use the JDBC driver to create a table populated with Mistral AI data from within a ColdFusion markup file.

With built-in optimized data processing, the CData JDBC Driver offers unmatched performance for interacting with live Mistral AI data. When you issue complex SQL queries to Mistral AI, the driver pushes supported SQL operations, like filters and aggregations, directly to Mistral AI and utilizes the embedded SQL engine to process unsupported operations client-side (often SQL functions and JOIN operations). Its built-in dynamic metadata querying allows you to work with and analyze Mistral AI data using native data types.

Configuring the Connection to Mistral AI

You will need a JDBC connection string to establish a connection between Coldfusion and Mistral AI.

The MistralAI API uses API key authentication.

Using API Key Authentication

Your MistralAI API Key is required to create a connection to MistralAI. API Keys can be obtained from your MistralAI account at console.mistral.ai by navigating to the API Keys section. Once you have obtained the API key, set it in the ProfileSettings connection property.

Example Connection string

Profile=C:\profiles\MistralAI.apip;ProfileSettings='APIKey=my_api_key;';AuthScheme=APIKey;

Built-in Connection String Designer

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

java -jar cdata.jdbc.api.jar

Adding a Data Source and Creating a Table

After configuring the connection, follow the steps below to add the CData JDBC Driver to ColdFusion's lib directory, add a new data source, test the connection, create a ColdFusion markup file, and, finally, make a real-time connection with Mistral AI data and display it in a table written in the ColdFusion Markup Language, or CFML:

1. Copy the JDBC Driver for Mistral AI and lic file from "C:\Program Files\CData[product_name]\lib" to "C:\ColdFusion2021\cfusion\wwwroot\WEB-INF\lib".

               cdata.jdbc.api.jar
               cdata.jdbc.api.lic
           

   Note: If you do not copy the .lic file with the jar, you will see a licensing error that indicates you do not have a valid license installed. This is true for both the trial and full versions.

2. From the ColdFusion administrator interface, choose Data & Services.
3. Here, we can "Add New Data Source". The data source name can be any name, provided it conforms to the ColdFusion variable naming conventions. For our JDBC driver, choose "other", then click the "Add" button.
4. Next, populate the driver properties.
   • JDBC URL will need to be in the format: jdbc:api:|connectionString|.
   • A typical connection string looks like this:

     jdbc:api:Profile=C:\profiles\MistralAI.apip;ProfileSettings='APIKey=my_api_key;';AuthScheme=APIKey;

   • The Driver Class is: cdata.jdbc.api.APIDriver
   • The Driver Name is arbitrary and simply used to recognize the data source in the ColdFusion administration console.
   
5. Now, test the connection by clicking the check mark to the left of the CDataMistral AIJDBC data source you just created. When the data source reports an "OK" status, it is ready for use.
6. Next, create a new ColdFusion Markup file (.cfm) and place it in the wwwroot directory ("C:\ColdFusion2021\cfusion\wwwroot") for ColdFusion.

   The following code queries the data source:

               
           <cfquery name="Mistral AIQuery" dataSource="CDataMistral AIJDBC"> 
             SELECT * FROM AudioTranscriptions 
           </cfquery> 
       

   And a CFTable can be used to quickly output the table in HTML:

               
             <cftable  
             query = "Mistral AIQuery" 
             border = "1" 
             colHeaders 
             colSpacing = "2" 
             headerLines = "2" 
             HTMLTable 
             maxRows = "500" 
             startRow = "1"> 
   
             <cfcol header="<b></b>" align="Left" width=2 text=""/> 
   
             <cfcol header="<b></b>" align="Left" width=15 text=""/> 
   
             ...
   
           </cftable> 
       

   Full code, including the HTML portion is available below:

               
           <html> 
           <head><title>CData Software | Mistral AI AudioTranscriptions Table Demo </title></head> 
           <body> 
           <cfoutput>#ucase("Mistral AI AudioTranscriptions Table Demo")#</cfoutput> 
           <cfquery name="Mistral AIQuery" dataSource="CDataMistral AIJDBC"> 
   
             SELECT * FROM AudioTranscriptions 
   
           </cfquery> 
           <cftable  
             query = "Mistral AIQuery" 
             border = "1" 
             colHeaders 
             colSpacing = "2" 
             headerLines = "2" 
             HTMLTable 
             maxRows = "500" 
             startRow = "1"> 
             <cfcol header="<b></b>" align="Left" width=2 text=""/> 
   
             <cfcol header="<b></b>" align="Left" width=15 text=""/> 
   
             ...
   
           </cftable> 
           </body> 
   
           </html>  
       

7. Finally, run the code locally in a browser at the default port of 8500. It produces a table populated with Mistral AI data!

As a note, the CData JDBC Drivers also support parameterized queries using the cfqueryparam element. For example:

SELECT * FROM Account WHERE name =  

Get Started Today

Download a free, 30-day trial of the CData JDBC Driver for Mistral AI and start building Mistral AI-connected applications with Adobe ColdFusion. Reach out to our Support Team if you have any questions.