Consume Mistral AI OData Feeds in SAP Lumira

You can use the CData API Server to create data visualizations based on Mistral AI data in SAP Lumira. The API Server enables connectivity to live data: dashboards and reports can be refreshed on demand. This article shows how to create a chart that is always up to date.

Set Up the API Server

If you have not already done so, download the CData API Server. Once you have installed the API Server, follow the steps below to begin producing secure Mistral AI OData services:

Connect to Mistral AI

To work with Mistral AI data from SAP Lumira, we start by creating and configuring a Mistral AI connection. Follow the steps below to configure the API Server to connect to Mistral AI data:

1. First, navigate to the Connections page.
2. Click Add Connection and then search for and select the Mistral AI connection.
3. Enter the necessary authentication properties to connect to 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;
   

   
4. After configuring the connection, click Save & Test to confirm a successful connection.

Configure API Server Users

Next, create a user to access your Mistral AI data through the API Server. You can add and configure users on the Users page. Follow the steps below to configure and create a user:

1. On the Users page, click Add User to open the Add User dialog.
2. Next, set the Role, Username, and Privileges properties and then click Add User.
3. An Authtoken is then generated for the user. You can find the Authtoken and other information for each user on the Users page:

Creating API Endpoints for Mistral AI

Having created a user, you are ready to create API endpoints for the Mistral AI tables:

1. First, navigate to the API page and then click Add Table .
2. Select the connection you wish to access and click Next.
3. With the connection selected, create endpoints by selecting each table and then clicking Confirm.

Gather the OData Url

Having configured a connection to Mistral AI data, created a user, and added resources to the API Server, you now have an easily accessible REST API based on the OData protocol for those resources. From the API page in API Server, you can view and copy the API Endpoints for the API:

Connect to Mistral AI from SAP Lumira

Follow the steps below to retrieve Mistral AI data into SAP Lumira. You can execute an SQL query or use the UI.

1. In SAP Lumira, click File -> New -> Query with SQL. The Add New Dataset dialog is displayed.
2. Expand the Generic section and click the Generic OData 2.0 Connector option.
3. In the Service Root URI box, enter the OData endpoint of the API Server. This URL will resemble the following:

   https://your-server:8080/api.rsc
   

4. In the User Name and Password boxes, enter the username and authtoken of an API user. These credentials will be used in HTTP Basic authentication.

5. Select entities in the tree or enter an SQL query. This article imports Mistral AI AudioTranscriptions entities.

   

6. When you click Connect, SAP Lumira will generate the corresponding OData request and load the results into memory. You can then use any of the data processing tools available in SAP Lumira, such as filters, aggregates, and summary functions.

   

Create Data Visualizations

After you have imported the data, you can create data visualizations in the Visualize room. Follow the steps below to create a basic chart.

1. In the Measures and Dimensions pane, drag measures and dimensions onto the x-axis and y-axis fields in the Visualization Tools pane. SAP Lumira automatically detects dimensions and measures from the metadata service of the API Server.

   By default, the SUM function is applied to all measures. Click the gear icon next to a measure to change the default summary.

2. In the Visualization Tools pane, select the chart type.
3. In the Chart Canvas pane, apply filters, sort by measures, add rankings, and update the chart with the current Mistral AI data.