Method from_path

src/semble/index/index.py:125–162

Create and index a SembleIndex from a directory. :param path: Root directory to index. :param content: Content types to index, e.g. ContentType.CODE or [ContentType.CODE, ContentType.DOCS]. :param include_text_files: Deprecated. Pass a content sequence directly instead.

(
        cls,
        path: str | Path,
        content: ContentType | Sequence[ContentType] = _DEFAULT_CONTENT,
        include_text_files: bool | None = None,
        model_path: str | None = None,
    )

    @classmethod
    def from_path(
        cls,
        path: str | Path,
        content: ContentType | Sequence[ContentType] = _DEFAULT_CONTENT,
        include_text_files: bool | None = None,
        model_path: str | None = None,
    ) -> SembleIndex:
        """Create and index a SembleIndex from a directory.

        :param path: Root directory to index.
        :param content: Content types to index, e.g. ContentType.CODE or [ContentType.CODE, ContentType.DOCS].
        :param include_text_files: Deprecated. Pass a content sequence directly instead.
        :param model_path: Path to the model to use. If None, the default model will be used.
        :return: An indexed SembleIndex. Chunk file paths are relative to ``path``.
        :raises FileNotFoundError: If `path` does not exist.
        :raises NotADirectoryError: If `path` exists but is not a directory.
        """
        path = Path(path)
        if not path.exists():
            raise FileNotFoundError(f"Path does not exist: {path}")
        if not path.is_dir():
            raise NotADirectoryError(f"Path is not a directory: {path}")

        normalized = _apply_include_text_files(content, include_text_files)
        cache_path = get_validated_cache(str(path), model_path, normalized)
        if cache_path:
            return cls.load_from_disk(cache_path)
        model, model_path = load_model(model_path)

        path = path.resolve()
        bm25, vicinity, chunks = create_index_from_path(
            path,
            model=model,
            content=normalized,
            display_root=path,
        )

        return SembleIndex(model, bm25, vicinity, chunks, model_path, root=path, content=normalized)

    @classmethod
    def from_git(