langchain_community.utilities.opaqueprompts
.sanitize¶
- langchain_community.utilities.opaqueprompts.sanitize(input: Union[str, Dict[str, str]]) Dict[str, Union[str, Dict[str, str]]] [source]¶
Sanitize input string or dict of strings by replacing sensitive data with placeholders.
It returns the sanitized input string or dict of strings and the secure context as a dict following the format: {
“sanitized_input”: <sanitized input string or dict of strings>, “secure_context”: <secure context>
}
The secure context is a bytes object that is needed to de-sanitize the response from the LLM.
- Parameters
input – Input string or dict of strings.
- Returns
Sanitized input string or dict of strings and the secure context as a dict following the format: {
”sanitized_input”: <sanitized input string or dict of strings>, “secure_context”: <secure context>
}
The secure_context needs to be passed to the desanitize function.
- Raises
ValueError – If the input is not a string or dict of strings.
ImportError – If the opaqueprompts Python package is not installed.