mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-24 15:36:50 +08:00
Fix errors (#11804)
### What problem does this PR solve? 1. typos 2. grammar errors. ### Type of change - [x] Refactoring Signed-off-by: Jin Hai <haijin.chn@gmail.com>
This commit is contained in:
@ -70,7 +70,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
|
||||
"""
|
||||
Supported file formats are docx, pdf, txt.
|
||||
Since a book is long and not all the parts are useful, if it's a PDF,
|
||||
please setup the page ranges for every book in order eliminate negative effects and save elapsed computing time.
|
||||
please set up the page ranges for every book in order eliminate negative effects and save elapsed computing time.
|
||||
"""
|
||||
parser_config = kwargs.get(
|
||||
"parser_config", {
|
||||
|
||||
@ -313,7 +313,7 @@ def mdQuestionLevel(s):
|
||||
def chunk(filename, binary=None, from_page=0, to_page=100000, lang="Chinese", callback=None, **kwargs):
|
||||
"""
|
||||
Excel and csv(txt) format files are supported.
|
||||
If the file is in excel format, there should be 2 column question and answer without header.
|
||||
If the file is in Excel format, there should be 2 column question and answer without header.
|
||||
And question column is ahead of answer column.
|
||||
And it's O.K if it has multiple sheets as long as the columns are rightly composed.
|
||||
|
||||
|
||||
@ -37,7 +37,7 @@ def beAdoc(d, q, a, eng, row_num=-1):
|
||||
def chunk(filename, binary=None, lang="Chinese", callback=None, **kwargs):
|
||||
"""
|
||||
Excel and csv(txt) format files are supported.
|
||||
If the file is in excel format, there should be 2 column content and tags without header.
|
||||
If the file is in Excel format, there should be 2 column content and tags without header.
|
||||
And content column is ahead of tags column.
|
||||
And it's O.K if it has multiple sheets as long as the columns are rightly composed.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user