Method from_config

spacy/language.py:1763–1994

Create the nlp object from a loaded config. Will set up the tokenizer and language data, add pipeline components etc. If no config is provided, the default config of the given language is used. config (Dict[str, Any] / Config): The loaded config. vocab (Vocab): A Voc

(
        cls,
        config: Union[Dict[str, Any], Config] = {},
        *,
        vocab: Union[Vocab, bool] = True,
        disable: Union[str, Iterable[str]] = _DEFAULT_EMPTY_PIPES,
        enable: Union[str, Iterable[str]] = _DEFAULT_EMPTY_PIPES,
        exclude: Union[str, Iterable[str]] = _DEFAULT_EMPTY_PIPES,
        meta: Dict[str, Any] = SimpleFrozenDict(),
        auto_fill: bool = True,
        validate: bool = True,
    )

    @classmethod
    def from_config(
        cls,
        config: Union[Dict[str, Any], Config] = {},
        *,
        vocab: Union[Vocab, bool] = True,
        disable: Union[str, Iterable[str]] = _DEFAULT_EMPTY_PIPES,
        enable: Union[str, Iterable[str]] = _DEFAULT_EMPTY_PIPES,
        exclude: Union[str, Iterable[str]] = _DEFAULT_EMPTY_PIPES,
        meta: Dict[str, Any] = SimpleFrozenDict(),
        auto_fill: bool = True,
        validate: bool = True,
    ) -> "Language":
        """Create the nlp object from a loaded config. Will set up the tokenizer
        and language data, add pipeline components etc. If no config is provided,
        the default config of the given language is used.

        config (Dict[str, Any] / Config): The loaded config.
        vocab (Vocab): A Vocab object. If True, a vocab is created.
        disable (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to disable.
            Disabled pipes will be loaded but they won't be run unless you
            explicitly enable them by calling nlp.enable_pipe.
        enable (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to enable. All other
            pipes will be disabled (and can be enabled using `nlp.enable_pipe`).
        exclude (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to exclude.
            Excluded components won't be loaded.
        meta (Dict[str, Any]): Meta overrides for nlp.meta.
        auto_fill (bool): Automatically fill in missing values in config based
            on defaults and function argument annotations.
        validate (bool): Validate the component config and arguments against
            the types expected by the factory.
        RETURNS (Language): The initialized Language class.

        DOCS: https://spacy.io/api/language#from_config
        """
        if auto_fill:
            config = Config(
                cls.default_config, section_order=CONFIG_SECTION_ORDER
            ).merge(config)
        if "nlp" not in config:
            raise ValueError(Errors.E985.format(config=config))
        # fill in [nlp.vectors] if not present (as a narrower alternative to
        # auto-filling [nlp] from the default config)
        if "vectors" not in config["nlp"]:
            config["nlp"]["vectors"] = {"@vectors": "spacy.Vectors.v1"}
        config_lang = config["nlp"].get("lang")
        if config_lang is not None and config_lang != cls.lang:
            raise ValueError(
                Errors.E958.format(
                    bad_lang_code=config["nlp"]["lang"],
                    lang_code=cls.lang,
                    lang=util.get_object_name(cls),
                )
            )
        config["nlp"]["lang"] = cls.lang
        # This isn't very elegant, but we remove the [components] block here to prevent
        # it from getting resolved (causes problems because we expect to pass in
        # the nlp and name args for each component). If we're auto-filling, we're
        # using the nlp.config with all defaults.