跳到内容

Box

BoxReaderAIExtract #

基类: BoxReaderBase

一个使用 Box AI Extract 从 Box 文件加载数据的读取器类。

该类继承自 BaseReader 类，专门用于使用 Box AI Extract 处理 Box 文件中的数据。它利用提供的 BoxClient 对象与 Box API 交互，并根据指定的 AI 提示提取数据。

属性

名称 类型 描述
_box_client BoxClient

用于与 Box API 交互的已认证 Box 客户端对象。
源代码位于 llama-index-integrations/readers/llama-index-readers-box/llama_index/readers/box/BoxReaderAIExtraction/base.py 
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
class BoxReaderAIExtract(BoxReaderBase):
    """
    A reader class for loading data from Box files using Box AI Extract.

    This class inherits from the `BaseReader` class and specializes in
    processing data from Box files using Box AI Extract. It utilizes the
    provided BoxClient object to interact with the Box API and extracts
    data based on a specified AI prompt.

    Attributes:
        _box_client (BoxClient): An authenticated Box client object used
            for interacting with the Box API.

    """

    _box_client: BoxClient

    @classmethod
    def class_name(cls) -> str:
        return "BoxReaderAIExtract"

    def __init__(self, box_client: BoxClient):
        super().__init__(box_client=box_client)

    def load_data(
        self,
        ai_prompt: str,
        file_ids: Optional[List[str]] = None,
        folder_id: Optional[str] = None,
        is_recursive: bool = False,
    ) -> List[Document]:
        """
        Extracts data from Box files using Box AI and creates Document objects.

        This method utilizes the Box AI Extract functionality to extract data
        based on the provided AI prompt from the specified Box files. It then
        creates Document objects containing the extracted data along with
        file metadata.

        Args:
            ai_prompt (str): The AI prompt that specifies what data to extract
                from the files.
            file_ids (Optional[List[str]], optional): A list of Box file IDs
                to extract data from. If provided, folder_id is ignored.
                Defaults to None.
            folder_id (Optional[str], optional): The ID of the Box folder to
                extract data from. If provided, along with is_recursive set to
                True, retrieves data from sub-folders as well. Defaults to None.
            is_recursive (bool, optional): If True and folder_id is provided,
                extracts data from sub-folders within the specified folder.
                Defaults to False.

        Returns:
            List[Document]: A list of Document objects containing the extracted
                data and file metadata.

        """
        # check if the box client is authenticated
        box_check_connection(self._box_client)

        docs: List[Document] = []
        box_files: List[File] = []

        # get payload information
        if file_ids is not None:
            box_files.extend(
                get_box_files_details(box_client=self._box_client, file_ids=file_ids)
            )
        elif folder_id is not None:
            box_files.extend(
                get_box_folder_files_details(
                    box_client=self._box_client,
                    folder_id=folder_id,
                    is_recursive=is_recursive,
                )
            )

        box_files = get_files_ai_extract_data(
            box_client=self._box_client,
            box_files=box_files,
            ai_prompt=ai_prompt,
        )

        for file in box_files:
            doc = box_file_to_llama_document(file)
            doc.text = file.ai_response if file.ai_response else ""
            doc.metadata["ai_prompt"] = file.ai_prompt
            doc.metadata["ai_response"] = file.ai_response
            docs.append(doc)
        return docs

    def load_resource(self, box_file_id: str, ai_prompt: str) -> List[Document]:
        """
        Load data from a specific resource.

        Args:
            resource (str): The resource identifier.

        Returns:
            List[Document]: A list of documents loaded from the resource.

        """
        return self.load_data(file_ids=[box_file_id], ai_prompt=ai_prompt)

load_data #

load_data(ai_prompt: str, file_ids: Optional[List[str]] = None, folder_id: Optional[str] = None, is_recursive: bool = False) -> List[Document]

使用 Box AI 从 Box 文件中提取数据并创建 Document 对象。

此方法利用 Box AI Extract 功能，根据提供的 AI 提示从指定的 Box 文件中提取数据。然后，它创建包含提取数据及文件元数据的 Document 对象。

参数

名称 类型 描述 默认值
ai_prompt str

指定从文件中提取哪些数据的 AI 提示。

 必需
file_ids 可选[列表[字符串]]

要从中提取数据的 Box 文件 ID 列表。如果提供，folder_id 将被忽略。默认为 None。

 无
folder_id 可选[字符串]

要从中提取数据的 Box 文件夹 ID。如果提供，并且 is_recursive 设置为 True，则也会从子文件夹中检索数据。默认为 None。

 无
is_recursive bool

如果为 True 且 folder_id 提供，则从指定文件夹内的子文件夹中提取数据。默认为 False。

 False

返回值

类型 描述
列表[Document]

List[Document]: 包含提取数据和文件元数据的 Document 对象列表。
源代码位于 llama-index-integrations/readers/llama-index-readers-box/llama_index/readers/box/BoxReaderAIExtraction/base.py 
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
def load_data(
    self,
    ai_prompt: str,
    file_ids: Optional[List[str]] = None,
    folder_id: Optional[str] = None,
    is_recursive: bool = False,
) -> List[Document]:
    """
    Extracts data from Box files using Box AI and creates Document objects.

    This method utilizes the Box AI Extract functionality to extract data
    based on the provided AI prompt from the specified Box files. It then
    creates Document objects containing the extracted data along with
    file metadata.

    Args:
        ai_prompt (str): The AI prompt that specifies what data to extract
            from the files.
        file_ids (Optional[List[str]], optional): A list of Box file IDs
            to extract data from. If provided, folder_id is ignored.
            Defaults to None.
        folder_id (Optional[str], optional): The ID of the Box folder to
            extract data from. If provided, along with is_recursive set to
            True, retrieves data from sub-folders as well. Defaults to None.
        is_recursive (bool, optional): If True and folder_id is provided,
            extracts data from sub-folders within the specified folder.
            Defaults to False.

    Returns:
        List[Document]: A list of Document objects containing the extracted
            data and file metadata.

    """
    # check if the box client is authenticated
    box_check_connection(self._box_client)

    docs: List[Document] = []
    box_files: List[File] = []

    # get payload information
    if file_ids is not None:
        box_files.extend(
            get_box_files_details(box_client=self._box_client, file_ids=file_ids)
        )
    elif folder_id is not None:
        box_files.extend(
            get_box_folder_files_details(
                box_client=self._box_client,
                folder_id=folder_id,
                is_recursive=is_recursive,
            )
        )

    box_files = get_files_ai_extract_data(
        box_client=self._box_client,
        box_files=box_files,
        ai_prompt=ai_prompt,
    )

    for file in box_files:
        doc = box_file_to_llama_document(file)
        doc.text = file.ai_response if file.ai_response else ""
        doc.metadata["ai_prompt"] = file.ai_prompt
        doc.metadata["ai_response"] = file.ai_response
        docs.append(doc)
    return docs

load_resource #

load_resource(box_file_id: str, ai_prompt: str) -> List[Document]

从特定资源加载数据。

参数

名称 类型 描述 默认值
resource str

资源标识符。

 必需

返回值

类型 描述
列表[Document]

List[Document]: 从资源加载的文档列表。
源代码位于 llama-index-integrations/readers/llama-index-readers-box/llama_index/readers/box/BoxReaderAIExtraction/base.py 
115
116
117
118
119
120
121
122
123
124
125
126
def load_resource(self, box_file_id: str, ai_prompt: str) -> List[Document]:
    """
    Load data from a specific resource.

    Args:
        resource (str): The resource identifier.

    Returns:
        List[Document]: A list of documents loaded from the resource.

    """
    return self.load_data(file_ids=[box_file_id], ai_prompt=ai_prompt)