Is the SEPARATOR_LENGTH_IN_MARKDOWN_FORMAT necessary? If yes, how to decide it?

> Please provide us with the following information:
> ---------------------------------------------------------------

### This issue is for a: (mark with an `x`)
```
- [ ] bug report -> please search issues before submitting
- [ ] feature request
- [x] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)
```

### Minimal steps to reproduce
>

### Any log messages given by the failure
>

### Expected/desired behavior
>

### OS and Version?
> Windows

### Versions
> 11

### Mention any other details that might be useful
Thanks for providing a [notebook](https://github.com/Azure-Samples/document-intelligence-code-samples/blob/main/Python(v4.0)/Retrieval_Augmented_Generation_(RAG)_samples/sample_identify_and_merge_cross_page_tables.ipynb) for merging tables across pages
For vertical table, is the SEPARATOR_LENGTH_IN_MARKDOWN_FORMAT necessary? as when there is no paragraph in between, there are only page header/footer/number between two tables, the two tables can be merged if they have the same number of columns.
If it is necessary, how can it be decided? It is “2” in the notebook but due to the inclusion of markdown for page header/footer/number and page break when calculating the offset, there are more than 2 characters between two tables. So 2 is too small.
> ---------------------------------------------------------------
> Thanks! We'll be in touch soon.

Open the linked sample_identify_and_merge_cross_page_tables.ipynb and locate SEPARATOR_LENGTH_IN_MARKDOWN_FORMAT. Trace how markdown for page headers, footers, numbers, and page breaks contributes to the offset between vertical tables, then compare the notebook's value of 2 with the described cases. Done means the necessity and decision rule are documented or the issue is answered with evidence from the sample.

Escrita pelo modelo de indexação a partir do texto da issue.