Parsing table with empty columns not optimal. result_type='text'
produces better table formatting.
#150
Labels
bug
Something isn't working
result_type='text'
produces better table formatting.
#150
Hello, I have been trying to parse my document (purchase orders and invoices) containing table by leveraging on
parsing_instructions
to handle awkward tables. However, I still cannot seem to achieve good parsing result after rewriting my prompts many times.result_type='markdown'
is the preferred result type because it allows more control over the output. Is there any 'special' prompts the parser needs so that it behaves as instructed?In one of my latest prompts to the parser, I have written the following instructions for table extraction. I also wrote formatting instructions to handle a few edge cases:
As I cannot share company document publicly, here is a screenshot of a portion of the table where the parser struggles on.
If
result_type='markdown'
, I get the following result. The columns shifted.If
result_type='text'
, I get the following result. No columns where shifted.The text was updated successfully, but these errors were encountered: