Usually you’ll load this once per process as nlp and pass the instance around your application. The Language class is created when you call spacy.load and contains the shared vocabulary and language data, optional binary weights, e.g. provided by a trained pipeline, and the processing pipeline containing components like the tagger or parser that are called on a document in order. You can also add your own processing pipeline components that take a Doc object, modify it and return it.

Language.__init__ method

Initialize a Language object. Note that the meta is only used for meta information in Language.meta and not to configure the nlp object or to override the config. To initialize from a config, use Language.from_config instead.

Language.from_config classmethodv3.0

Create a Language object from a loaded config. Will set up the tokenizer and language data, add pipeline components based on the pipeline and add pipeline components based on the definitions specified in the config. If no config is provided, the default config of the given language is used. This is also how spaCy loads a model under the hood based on its config.cfg.

Language.component classmethodv3.0

Register a custom pipeline component under a given name. This allows initializing the component by name using Language.add_pipe and referring to it in config files. This classmethod and decorator is intended for simple stateless functions that take a Doc and return it. For more complex stateful components that allow settings and need access to the shared nlp object, use the Language.factory decorator. For more details and examples, see the usage documentation.

Language.factory classmethod

Register a custom pipeline component factory under a given name. This allows initializing the component by name using Language.add_pipe and referring to it in config files. The registered factory function needs to take at least two named arguments which spaCy fills in automatically: nlp for the current nlp object and name for the component instance name. This can be useful to distinguish multiple instances of the same component and allows trainable components to add custom losses using the component instance name. The default_config defines the default values of the remaining factory arguments. It’s merged into the nlp.config. For more details and examples, see the usage documentation.

Language.__call__ method

Apply the pipeline to some text. The text can span multiple sentences, and can contain arbitrary whitespace. Alignment into the original string is preserved.

Instead of text, a Doc can be passed as input, in which case tokenization is skipped, but the rest of the pipeline is run.

Language.pipe method

Process texts as a stream, and yield Doc objects in order. This is usually more efficient than processing texts one-by-one.

Instead of text, a Doc object can be passed as input. In this case tokenization is skipped but the rest of the pipeline is run.

Language.set_error_handler methodv3.0

Define a callback that will be invoked when an error is thrown during processing of one or more documents. Specifically, this function will call set_error_handler on all the pipeline components that define that function. The error handler will be invoked with the original component’s name, the component itself, the list of documents that was being processed, and the original error.

Language.initialize methodv3.0

Initialize the pipeline for training and return an Optimizer. Under the hood, it uses the settings defined in the [initialize] config block to set up the vocabulary, load in vectors and tok2vec weights and pass optional arguments to the initialize methods implemented by pipeline components or the tokenizer. This method is typically called automatically when you run spacy train. See the usage guide on the config lifecycle and initialization for details.

get_examples should be a function that returns an iterable of Example objects. The data examples can either be the full training data or a representative sample. They are used to initialize the models of trainable pipeline components and are passed each component’s initialize method, if available. Initialization includes validating the network, inferring missing shapes and setting up the label scheme based on the data.

If no get_examples function is provided when calling nlp.initialize, the pipeline components will be initialized with generic data. In this case, it is crucial that the output dimension of each component has already been defined either in the config, or by calling pipe.add_label for each possible output label (e.g. for the tagger or textcat).

Language.resume_training methodexperimentalv3.0

Continue training a trained pipeline. Create and return an optimizer, and initialize “rehearsal” for any pipeline component that has a rehearse method. Rehearsal is used to prevent models from “forgetting” their initialized “knowledge”. To perform rehearsal, collect samples of text you want the models to retain performance on, and call nlp.rehearse with a batch of Example objects.

Language.update method

Update the models in the pipeline.

Language.rehearse methodexperimentalv3.0

Perform a “rehearsal” update from a batch of data. Rehearsal updates teach the current model to make predictions similar to an initial model, to try to address the “catastrophic forgetting” problem. This feature is experimental.

Language.evaluate method

Evaluate a pipeline’s components.

Language.use_params contextmanagermethod

Replace weights of models in the pipeline with those provided in the params dictionary. Can be used as a context manager, in which case, models go back to their original weights after the block.

Language.add_pipe method

Add a component to the processing pipeline. Expects a name that maps to a component factory registered using @Language.component or @Language.factory. Components should be callables that take a Doc object, modify it and return it. Only one of before, after, first or last can be set. Default behavior is last=True.

Language.create_pipe method

Create a pipeline component from a factory.

Language.has_factory classmethodv3.0

Check whether a factory name is registered on the Language class or subclass. Will check for language-specific factories registered on the subclass, as well as general-purpose factories registered on the Language base class, available to all subclasses.

Language.has_pipe method

Check whether a component is present in the pipeline. Equivalent to name in nlp.pipe_names.

Language.get_pipe method

Get a pipeline component for a given component name.

Language.replace_pipe method

Replace a component in the pipeline and return the new component.

Language.rename_pipe method

Rename a component in the pipeline. Useful to create custom names for pre-defined and pre-loaded components. To change the default name of a component added to the pipeline, you can also use the name argument on add_pipe.

Language.remove_pipe method

Remove a component from the pipeline. Returns the removed component name and component function.

Language.disable_pipe methodv3.0

Temporarily disable a pipeline component so it’s not run as part of the pipeline. Disabled components are listed in nlp.disabled and included in nlp.components, but not in nlp.pipeline, so they’re not run when you process a Doc with the nlp object. If the component is already disabled, this method does nothing.

Language.enable_pipe methodv3.0

Enable a previously disabled component (e.g. via Language.disable_pipes) so it’s run as part of the pipeline, nlp.pipeline. If the component is already enabled, this method does nothing.

Language.select_pipes contextmanagermethodv3.0

Disable one or more pipeline components. If used as a context manager, the pipeline will be restored to the initial state at the end of the block. Otherwise, a DisabledPipes object is returned, that has a .restore() method you can use to undo your changes. You can specify either disable (as a list or string), or enable. In the latter case, all components not in the enable list will be disabled. Under the hood, this method calls into disable_pipe and enable_pipe.

Language.get_factory_meta classmethodv3.0

Get the factory meta information for a given pipeline component name. Expects the name of the component factory. The factory meta is an instance of the FactoryMeta dataclass and contains the information about the component and its default provided by the @Language.component or @Language.factory decorator.

Language.get_pipe_meta methodv3.0

Get the factory meta information for a given pipeline component name. Expects the name of the component instance in the pipeline. The factory meta is an instance of the FactoryMeta dataclass and contains the information about the component and its default provided by the @Language.component or @Language.factory decorator.

Language.analyze_pipes methodv3.0

Analyze the current pipeline components and show a summary of the attributes they assign and require, and the scores they set. The data is based on the information provided in the @Language.component and @Language.factory decorator. If requirements aren’t met, e.g. if a component specifies a required property that is not set by a previous component, a warning is shown.

Structured

Pretty

Language.replace_listeners methodv3.0

Find listener layers (connecting to a shared token-to-vector embedding component) of a given pipeline component model and replace them with a standalone copy of the token-to-vector layer. The listener layer allows other components to connect to a shared token-to-vector embedding component like Tok2Vec or Transformer. Replacing listeners can be useful when training a pipeline with components sourced from an existing pipeline: if multiple components (e.g. tagger, parser, NER) listen to the same token-to-vector component, but some of them are frozen and not updated, their performance may degrade significantly as the token-to-vector component is updated with new data. To prevent this, listeners can be replaced with a standalone token-to-vector layer that is owned by the component and doesn’t change if the component isn’t updated.

This method is typically not called directly and only executed under the hood when loading a config with sourced components that define replace_listeners.

Language.memory_zone contextmanagerv3.8

Begin a block where all resources allocated during the block will be freed at the end of it. If a resources was created within the memory zone block, accessing it outside the block is invalid. Behavior of this invalid access is undefined. Memory zones should not be nested. The memory zone is helpful for services that need to process large volumes of text with a defined memory budget.

Language.meta property

Meta data for the Language class, including name, version, data sources, license, author information and more. If a trained pipeline is loaded, this contains meta data of the pipeline. The Language.meta is also what’s serialized as the meta.json when you save an nlp object to disk. See the meta data format for more details.

Language.config propertyv3.0

Export a trainable config.cfg for the current nlp object. Includes the current pipeline, all configs used to create the currently active pipeline components, as well as the default training config that can be used with spacy train. Language.config returns a Thinc Config object, which is a subclass of the built-in dict. It supports the additional methods to_disk (serialize the config to a file) and to_str (output the config as a string).

Language.to_disk method

Save the current state to a directory. Under the hood, this method delegates to the to_disk methods of the individual pipeline components, if available. This means that if a trained pipeline is loaded, all components and their weights will be saved to disk.

Language.from_disk method

Loads state from a directory, including all data that was saved with the Language object. Modifies the object in place and returns it.

Language.to_bytes method

Serialize the current state to a binary string.

Language.from_bytes method

Load state from a binary string. Note that this method is commonly used via the subclasses like English or German to make language-specific functionality like the lexical attribute getters available to the loaded object.

Note that if you want to serialize and reload a whole pipeline, using this alone won’t work, you also need to handle the config. See “Serializing the pipeline” for details.

Attributes

Class attributes

Defaults

The following attributes can be set on the Language.Defaults class to customize the default language data:

Serialization fields

During serialization, spaCy will export several data fields used to restore different aspects of the object. If needed, you can exclude them from serialization by passing in the string names via the exclude argument.

FactoryMeta dataclassv3.0

The FactoryMeta contains the information about the component and its default provided by the @Language.component or @Language.factory decorator. It’s created whenever a component is defined and stored on the Language class for each component instance and factory instance.