langchain_community.utilities.opaqueprompts

from typing import Dict, Union


[docs]def sanitize(
    input: Union[str, Dict[str, str]],
) -> Dict[str, Union[str, Dict[str, str]]]:
    """对输入字符串或字符串字典进行清理，将敏感数据替换为占位符。

它返回清理后的输入字符串或字符串字典，以及作为字典的安全上下文，格式如下：
{
    "sanitized_input": <清理后的输入字符串或字符串字典>,
    "secure_context": <安全上下文>
}

安全上下文是一个字节对象，需要用于从LLM的响应中去除清理。

参数：
    input: 输入字符串或字符串字典。

返回：
    清理后的输入字符串或字符串字典，以及作为字典的安全上下文，格式如下：
    {
        "sanitized_input": <清理后的输入字符串或字符串字典>,
        "secure_context": <安全上下文>
    }

    需要将`secure_context`传递给`desanitize`函数。

抛出：
    ValueError: 如果输入不是字符串或字符串字典。
    ImportError: 如果未安装`opaqueprompts` Python包。
"""
    try:
        import opaqueprompts as op
    except ImportError:
        raise ImportError(
            "Could not import the `opaqueprompts` Python package, "
            "please install it with `pip install opaqueprompts`."
        )

    if isinstance(input, str):
        # the input could be a string, so we sanitize the string
        sanitize_response: op.SanitizeResponse = op.sanitize([input])
        return {
            "sanitized_input": sanitize_response.sanitized_texts[0],
            "secure_context": sanitize_response.secure_context,
        }

    if isinstance(input, dict):
        # the input could be a dict[string, string], so we sanitize the values
        values = list()

        # get the values from the dict
        for key in input:
            values.append(input[key])

        # sanitize the values
        sanitize_values_response: op.SanitizeResponse = op.sanitize(values)

        # reconstruct the dict with the sanitized values
        sanitized_input_values = sanitize_values_response.sanitized_texts
        idx = 0
        sanitized_input = dict()
        for key in input:
            sanitized_input[key] = sanitized_input_values[idx]
            idx += 1

        return {
            "sanitized_input": sanitized_input,
            "secure_context": sanitize_values_response.secure_context,
        }

    raise ValueError(f"Unexpected input type {type(input)}")


[docs]def desanitize(sanitized_text: str, secure_context: bytes) -> str:
    """从经过处理的文本中恢复原始的敏感数据。

参数:
    sanitized_text: 经过处理的文本。
    secure_context: `sanitize` 函数返回的安全上下文。

返回:
    反处理后的文本。
"""
    try:
        import opaqueprompts as op
    except ImportError:
        raise ImportError(
            "Could not import the `opaqueprompts` Python package, "
            "please install it with `pip install opaqueprompts`."
        )
    desanitize_response: op.DesanitizeResponse = op.desanitize(
        sanitized_text, secure_context
    )
    return desanitize_response.desanitized_text
Source code for langchain_community.utilities.opaqueprompts
