How can i migrate the LUIS data to CLU as LUIS is retiring on 31st march 2026 . So , before that i have to migrate all my data trained in LUIS. Suggest me steps and also i am unable to see the portal where i can fill the details like subscription etc.

Hi Himani Bohra

If you're using Language Understanding (LUIS), you can import your Language Understanding (LUIS) JSON file to the new Conversational language understanding feature:

1. Export the LUIS app
   • Export your LUIS application as JSON by using the LUIS authoring APIs or the LUIS portal.
   • LUIS Versions – Export REST API
2. Map LUIS data to the CLU schema
   • Update the exported JSON to align intents, entities, and utterances with the CLU project schema.
   • Conversational Language Understanding overview provides details on the CLU schema and supported features.
3. Create a CLU project and import data
   • Create a CLU project and import the prepared data by using Language Studio or the CLU authoring APIs.
   • CLU quickstart (REST API) provides instructions on creating a CLU project and importing data.
4. Train the model
   • Start a training job to build the CLU model from the imported data.
   • Train and evaluate a CLU model provides details on training and evaluating your CLU model.
5. Test the model
   • Send test utterances to the CLU prediction endpoint and verify intent and entity results.
   • Conversational Language Understanding overview provides details on querying your CLU model.

Reference - https://learn.microsoft.com/en-us/azure/ai-services/language-service/reference/migrate

Thank you.

To migrate your data from Language Understanding (LUIS) to Conversational Language Understanding (CLU), you can follow these steps:

1. Export Your LUIS Data: Start by exporting your LUIS app data. You can do this through the LUIS portal or using the LUIS API.
2. Prepare Your Data for CLU: After exporting, you may need to adjust your data format to match the requirements of CLU. This typically involves ensuring that intents and entities are correctly mapped.
3. Import into CLU: Use the CLU API to import your adjusted LUIS JSON file into the new CLU model. You can find specific guidelines on how to do this in the migration documentation.
4. Train Your CLU Model: Once your data is imported, you will need to train your CLU model to ensure it understands the intents and entities as expected.
5. Test and Validate: After training, test your CLU model to validate that it performs as intended. Make any necessary adjustments based on the results.

Regarding the portal for filling in details like subscription and language resource, ensure that you are accessing the correct Azure portal for managing your AI services. If you are unable to see the portal, check your Azure subscription status and permissions, as these can affect your access to certain resources.

For more detailed guidance, refer to the migration guide provided by Microsoft.

References:

• Migrating to Azure Language in Foundry Tools
• Natural language understanding