Gpt repo

初始化文件。

GPTRepoReader

Bases: BaseReader

GPTRepoReader.

以适合提示的格式读取github仓库。

Source code in llama_index/readers/gpt_repo/base.py

class GPTRepoReader(BaseReader):
    """GPTRepoReader.

    以适合提示的格式读取github仓库。"""

    def __init__(self, concatenate: bool = False) -> None:
        """初始化。"""
        self.concatenate = concatenate

    def load_data(
        self,
        repo_path: str,
        preamble_str: Optional[str] = None,
        extensions: Optional[List[str]] = None,
        encoding: Optional[str] = "utf-8",
    ) -> List[Document]:
        """从输入目录加载数据。

Args:
    pages (List[str]): 要读取的页面列表。
"""
        ignore_file_path = os.path.join(repo_path, ".gptignore")

        if os.path.exists(ignore_file_path):
            ignore_list = get_ignore_list(ignore_file_path)
        else:
            ignore_list = []

        output_text = ""
        if preamble_str:
            output_text += f"{preamble_str}\n"
        elif self.concatenate:
            output_text += (
                "The following text is a Git repository with code. "
                "The structure of the text are sections that begin with ----, "
                "followed by a single line containing the file path and file "
                "name, followed by a variable amount of lines containing the "
                "file contents. The text representing the Git repository ends "
                "when the symbols --END-- are encountered. Any further text beyond "
                "--END-- are meant to be interpreted as instructions using the "
                "aforementioned Git repository as context.\n"
            )
        else:
            # self.concatenate is False
            output_text += (
                "The following text is a file in a Git repository. "
                "The structure of the text are sections that begin with ----, "
                "followed by a single line containing the file path and file "
                "name, followed by a variable amount of lines containing the "
                "file contents. The text representing the file ends "
                "when the symbols --END-- are encountered. Any further text beyond "
                "--END-- are meant to be interpreted as instructions using the "
                "aforementioned file as context.\n"
            )
        text_list = process_repository(
            repo_path,
            ignore_list,
            concatenate=self.concatenate,
            extensions=extensions,
            encoding=encoding,
        )
        docs = []
        for text in text_list:
            doc_text = output_text + text + "\n--END--\n"
            docs.append(Document(text=doc_text))

        return docs

load_data

load_data(
    repo_path: str,
    preamble_str: Optional[str] = None,
    extensions: Optional[List[str]] = None,
    encoding: Optional[str] = "utf-8",
) -> List[Document]

从输入目录加载数据。

Parameters:

Name	Type	Description	Default
pages	List[str]	要读取的页面列表。	required

Source code in llama_index/readers/gpt_repo/base.py

    def load_data(
        self,
        repo_path: str,
        preamble_str: Optional[str] = None,
        extensions: Optional[List[str]] = None,
        encoding: Optional[str] = "utf-8",
    ) -> List[Document]:
        """从输入目录加载数据。

Args:
    pages (List[str]): 要读取的页面列表。
"""
        ignore_file_path = os.path.join(repo_path, ".gptignore")

        if os.path.exists(ignore_file_path):
            ignore_list = get_ignore_list(ignore_file_path)
        else:
            ignore_list = []

        output_text = ""
        if preamble_str:
            output_text += f"{preamble_str}\n"
        elif self.concatenate:
            output_text += (
                "The following text is a Git repository with code. "
                "The structure of the text are sections that begin with ----, "
                "followed by a single line containing the file path and file "
                "name, followed by a variable amount of lines containing the "
                "file contents. The text representing the Git repository ends "
                "when the symbols --END-- are encountered. Any further text beyond "
                "--END-- are meant to be interpreted as instructions using the "
                "aforementioned Git repository as context.\n"
            )
        else:
            # self.concatenate is False
            output_text += (
                "The following text is a file in a Git repository. "
                "The structure of the text are sections that begin with ----, "
                "followed by a single line containing the file path and file "
                "name, followed by a variable amount of lines containing the "
                "file contents. The text representing the file ends "
                "when the symbols --END-- are encountered. Any further text beyond "
                "--END-- are meant to be interpreted as instructions using the "
                "aforementioned file as context.\n"
            )
        text_list = process_repository(
            repo_path,
            ignore_list,
            concatenate=self.concatenate,
            extensions=extensions,
            encoding=encoding,
        )
        docs = []
        for text in text_list:
            doc_text = output_text + text + "\n--END--\n"
            docs.append(Document(text=doc_text))

        return docs