mirror of
https://github.com/zylon-ai/private-gpt.git
synced 2025-12-22 20:12:55 +01:00
While ingesting, some files led to a crash due to encoding error. Even though utf-8 some characters still messed it up.
This commit is contained in:
parent
757a8c79fd
commit
6af9fb8b42
1 changed files with 8 additions and 2 deletions
|
|
@ -89,10 +89,16 @@ class IngestionHelper:
|
|||
)
|
||||
# Read as a plain text
|
||||
string_reader = StringIterableReader()
|
||||
return string_reader.load_data([file_data.read_text()])
|
||||
return string_reader.load_data([file_data.read_text(errors='replace')])
|
||||
|
||||
logger.debug("Specific reader found for extension=%s", extension)
|
||||
return reader_cls().load_data(file_data)
|
||||
try:
|
||||
res = reader_cls().load_data(file_data)
|
||||
except:
|
||||
string_reader = StringIterableReader()
|
||||
res = string_reader.load_data([file_data.read_text(errors='replace')])
|
||||
pass
|
||||
return res
|
||||
|
||||
@staticmethod
|
||||
def _exclude_metadata(documents: list[Document]) -> None:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue