[BUG] When file_type is set to all_files, only pdfminer is used

[e7217]

Describe the bug
Hello,

It seems that when the parser module is configured with file_type: all_files, only pdfminer is applied. I have tried using langchain_parser/upstagedocumentparse and llamaparser, and both appear to use pdfminer exclusively. Even when I set the output_format to html, it seems like pdfminer is still being used. Am I mistaken about something?

Below is the YAML file I configured:

- module_type: langchain_parse
  parse_method: upstagedocumentparse
  split: page
  file_type: all_files
  output_format: html

or

- module_type: llamaparse
  result_type: markdown
  file_type: all_files
  language: ko

And here is the result:

I would appreciate your help. Thank you.

[e7217]

I found the way to set all_files.
To use it, we should set all_files in start_parsing() to True

parser.start_parsing(parse_config, all_files=True)

what is correct way to set all files between as follows?

• start_parsing(... , all_files=True)
• set file_type to all_files in parser yaml

Additionally, to apply various parse configurations, should I modify the configuration file each time or create a new configuration for each module?

[bwook00]

First, sorry for the late comment (I was on vacation this week🫣)

You're right, you need to do start_parsing(... , all_files=True) to use file_type as all_files!
I forgot and didn't write it in Docs,, sorry for the confusion!

I designed it so that if you don't put all_files=True, it will parse with pdfminer, which is the default parse method for PDF.

I'll add it to Docs right away.

Finally, sorry for the confusion and Thanks for your hard contribution!!!