Extract Structured JSON Data from Unstructured Data using Databricks Mosaic AI > Using the Extract Structured JSON Data from Unstructured Data using Databricks Mosaic AI recipe > Step 4. Publish and run the guide
  

Step 4. Publish and run the guide

You can enter field names based on the context of an uploaded file to extract data.
  1. 1Open the Extract Fields with Context guide.
  2. 2On the Start tab of the Start step, ensure that the Run As field is set to Current User.
  3. 3Save and publish the guide.
  4. 4On the Actions menu, click Run. Alternatively, you can copy the execution URL from the Properties Details dialog box to run the guide.
  5. 5On the Instructions page, select the context file that you want to upload from your machine.
  6. 6In the Enter field names to extract data field, enter comma separated field names to extract data based on the file contents.
  7. 7Click Continue.
  8. You will receive a response from the LLM.
  9. 8You can extract new data with the same context or upload a new file to start a new conversation.
  10. 9Click Continue.
  11. You will receive a response from the LLM.
Note: If the uploaded file is empty or the field names are not related to the file context, an error occurs.
You can also use the embed code to embed the guide into an HTML document of a third-party application.