Skip to main content
Use this section to troubleshoot issues encountered when calling the Split API (/v1/split).

​
Common Status Codes

​
Status 400: Bad Request

This status code indicates invalid request parameters or client-side errors. Review the specific error message to identify the issue.

​
Error: Failed to download document from URL

This error occurs when the API cannot download the Markdown file from the provided markdown_url. Error message:
What to do:
  • Verify the URL is accessible and returns valid content.
  • Check network connectivity and URL permissions.
  • Confirm the server hosting the file does not require authentication or block external requests. If it does, download the file and send it with the markdown parameter instead.

​
Status 413: Content Too Large

This error occurs when the request body exceeds 4 MiB. A Markdown file at markdown_url larger than 4 MiB returns a 422 error instead. What to do:
  • Split the Markdown into smaller batches of pages and send each batch in its own request.

​
Status 422: Unprocessable Entity

This status code indicates input validation failures. Review the error message and adjust your request parameters.

​
Error: No Markdown provided

This error occurs when your request does not include the markdown parameter or markdown_url parameter, or when the values are empty. Error message:
What to do: Add one of these parameters to your request:
  • Use the markdown parameter to upload a Markdown file or provide inline Markdown content, OR
  • Use the markdown_url parameter to provide a URL to a Markdown file.

​
Error: Multiple markdown files detected

This error occurs when multiple Markdown files are included in the request. Error message:
What to do: Send only one Markdown file per request.

​
Error: Invalid file provided

This error occurs when the file you send is not UTF-8 encoded text, such as a PDF, DOCX, or image file. An empty file returns the message File is empty. Error message:
What to do:
  • If you have a PDF, DOCX, or other document format, use the Parse API to convert your document to Markdown first, then pass the markdown field of the parse response to the split endpoint.
  • Ensure your file contains UTF-8 encoded Markdown content.

​
Error: Input too large

This error occurs when the Markdown contains more than 400 pages. Error message:
What to do:
  • Split the Markdown into batches of 400 pages or fewer and send each batch in its own request.

​
Error: split_class must contain at most 19 split classification names

This error occurs when you provide more than 19 Split Types in the split_class parameter. Error message:
What to do:
  • Reduce the number of Split Types to 19 or fewer.
  • Consider combining similar Split Types or removing less important ones.
  • For more information, see Split Types.

​
Error: Unknown model version

This error occurs when the model parameter names a version that does not exist. The error message lists the available versions. What to do:
  • Omit model to use the latest version, or pass one of the versions the error message lists.

​
Status 500: Internal Server Error

This error indicates an unexpected server error occurred during split classification. Error message:
What to do:
  • Retry the request.
  • Verify your Split Rules are properly formatted with valid Split Type names, descriptions, and identifiers.
  • Check that your Markdown content is valid and properly formatted.
  • If the error persists, contact support@landing.ai.

​
Status 504: Gateway Timeout

This error occurs when split classification does not finish within the 475-second limit for synchronous requests. Error message:
What to do:
  • Reduce the size of your Markdown document.
  • If processing a very large document, send its pages in smaller batches.
  • If the error persists, contact support@landing.ai.

​
Best Practices for Avoiding Errors

  • Use parsed Markdown: Always pass Markdown content that has been generated by the Parse API. The split endpoint expects structured Markdown with the specific format produced by the Parse API, including the <!-- PAGE BREAK --> markers between pages.
  • Define clear Split Rules: Provide detailed descriptions for each Split Type to help the model accurately classify your document sections. For guidance, see Split Rules.
  • Use appropriate identifiers: Only specify identifiers when your document contains multiple instances of the same Split Type that need to be separated. For guidance, see Identifiers.

​
When Are Credits Consumed?

Credits are consumed only when the Split API returns a 200 status code. All other responses, including errors, do not consume credits.