diff --git a/embedchain/config/InitConfig.py b/embedchain/config/InitConfig.py index 5fa9b032..9bcaeb90 100644 --- a/embedchain/config/InitConfig.py +++ b/embedchain/config/InitConfig.py @@ -33,4 +33,4 @@ class InitConfig(BaseConfig): def _set_embedding_function(self, ef): self.ef = ef - return + return diff --git a/embedchain/utils.py b/embedchain/utils.py index b6337147..d7a89301 100644 --- a/embedchain/utils.py +++ b/embedchain/utils.py @@ -13,21 +13,20 @@ def clean_string(text): """ # Replacement of newline characters: text = text.replace('\n', ' ') - + # Stripping and reducing multiple spaces to single: cleaned_text = re.sub(r'\s+', ' ', text.strip()) - + # Removing backslashes: cleaned_text = cleaned_text.replace('\\', '') - + # Replacing hash characters: cleaned_text = cleaned_text.replace('#', ' ') - + # Eliminating consecutive non-alphanumeric characters: # This regex identifies consecutive non-alphanumeric characters (i.e., not a word character [a-zA-Z0-9_] and not a whitespace) in the string # and replaces each group of such characters with a single occurrence of that character. # For example, "!!! hello !!!" would become "! hello !". cleaned_text = re.sub(r'([^\w\s])\1*', r'\1', cleaned_text) - - return cleaned_text + return cleaned_text