Language Processing Pipelines

When you call nlp on a text, spaCy first tokenizes the text to produce a Doc object. The Doc is then processed in several different steps – this is also referred to as the processing pipeline. The pipeline used by the default models consists of a tagger, a parser and an entity recognizer. Each pipeline component returns the processed Doc, which is then passed on to the next component.

The processing pipeline
tokenizerTokenizerDocSegment text into tokens.
taggerTaggerDoc[i].tagAssign part-of-speech tags.
parserDependencyParserDoc[i].head, Doc[i].dep, Doc.sents, Doc.noun_chunksAssign dependency labels.
nerEntityRecognizerDoc.ents, Doc[i].ent_iob, Doc[i].ent_typeDetect and label named entities.
textcatTextCategorizerDoc.catsAssign document labels.
custom,, Span._.xxxAssign custom attributes, methods or properties.

The processing pipeline always depends on the statistical model and its capabilities. For example, a pipeline can only include an entity recognizer component if the model includes data to make predictions of entity labels. This is why each model will specify the pipeline to use in its meta data, as a simple list containing the component names:

"pipeline": ["tagger", "parser", "ner"]

In spaCy v2.x, the statistical components like the tagger or parser are independent and don’t share any data between themselves. For example, the named entity recognizer doesn’t use any features set by the tagger and parser, and so on. This means that you can swap them, or remove single components from the pipeline without affecting the others.

However, custom components may depend on annotations set by other components. For example, a custom lemmatizer may need the part-of-speech tags assigned, so it’ll only work if it’s added after the tagger. The parser will respect pre-defined sentence boundaries, so if a previous component in the pipeline sets them, its dependency predictions may be different. Similarly, it matters if you add the EntityRuler before or after the statistical entity recognizer: if it’s added before, the entity recognizer will take the existing entities into account when making predictions. The EntityLinker, which resolves named entities to knowledge base IDs, should be preceded by a pipeline component that recognizes entities such as the EntityRecognizer.

The tokenizer is a “special” component and isn’t part of the regular pipeline. It also doesn’t show up in nlp.pipe_names. The reason is that there can only really be one tokenizer, and while all other pipeline components take a Doc and return it, the tokenizer takes a string of text and turns it into a Doc. You can still customize the tokenizer, though. nlp.tokenizer is writable, so you can either create your own Tokenizer class from scratch, or even replace it with an entirely custom function.

Processing text

When you call nlp on a text, spaCy will tokenize it and then call each component on the Doc, in order. It then returns the processed Doc that you can work with.

doc = nlp("This is a text")

When processing large volumes of text, the statistical models are usually more efficient if you let them work on batches of texts. spaCy’s nlp.pipe method takes an iterable of texts and yields processed Doc objects. The batching is done internally.

texts = ["This is a text", "These are lots of texts", "..."]
- docs = [nlp(text) for text in texts]
+ docs = list(nlp.pipe(texts))

In this example, we’re using nlp.pipe to process a (potentially very large) iterable of texts as a stream. Because we’re only accessing the named entities in doc.ents (set by the ner component), we’ll disable all other statistical components (the tagger and parser) during processing. nlp.pipe yields Doc objects, so we can iterate over them and access the named entity predictions:

import spacy

texts = [
    "Net income was $9.4 million compared to the prior year of $2.7 million.",
    "Revenue exceeded twelve billion dollars, with a loss of $1b.",

nlp = spacy.load("en_core_web_sm")
for doc in nlp.pipe(texts, disable=["tagger", "parser"]):
    # Do something with the doc here
    print([(ent.text, ent.label_) for ent in doc.ents])

How pipelines work

spaCy makes it very easy to create your own pipelines consisting of reusable components – this includes spaCy’s default tagger, parser and entity recognizer, but also your own custom processing functions. A pipeline component can be added to an already existing nlp object, specified when initializing a Language class, or defined within a model package.

When you load a model, spaCy first consults the model’s meta.json. The meta typically includes the model details, the ID of a language class, and an optional list of pipeline components. spaCy then does the following:

  1. Load the language class and data for the given ID via get_lang_class and initialize it. The Language class contains the shared vocabulary, tokenization rules and the language-specific annotation scheme.
  2. Iterate over the pipeline names and create each component using create_pipe, which looks them up in Language.factories.
  3. Add each pipeline component to the pipeline in order, using add_pipe.
  4. Make the model data available to the Language class by calling from_disk with the path to the model data directory.

So when you call this…

nlp = spacy.load("en_core_web_sm")

… the model’s meta.json tells spaCy to use the language "en" and the pipeline ["tagger", "parser", "ner"]. spaCy will then initialize spacy.lang.en.English, and create each pipeline component and add it to the processing pipeline. It’ll then load in the model’s data from its data directory and return the modified Language class for you to use as the nlp object.

Fundamentally, a spaCy model consists of three components: the weights, i.e. binary data loaded in from a directory, a pipeline of functions called in order, and language data like the tokenization rules and annotation scheme. All of this is specific to each model, and defined in the model’s meta.json – for example, a Spanish NER model requires different weights, language data and pipeline components than an English parsing and tagging model. This is also why the pipeline state is always held by the Language class. spacy.load puts this all together and returns an instance of Language with a pipeline set and access to the binary data:

spacy.load under the hood

lang = "en" pipeline = ["tagger", "parser", "ner"] data_path = "path/to/en_core_web_sm/en_core_web_sm-2.0.0" cls = spacy.util.get_lang_class(lang) # 1. Get Language instance, e.g. English() nlp = cls() # 2. Initialize it for name in pipeline: component = nlp.create_pipe(name) # 3. Create the pipeline components nlp.add_pipe(component) # 4. Add the component to the pipeline nlp.from_disk(model_data_path) # 5. Load in the binary data

When you call nlp on a text, spaCy will tokenize it and then call each component on the Doc, in order. Since the model data is loaded, the components can access it to assign annotations to the Doc object, and subsequently to the Token and Span which are only views of the Doc, and don’t own any data themselves. All components return the modified document, which is then processed by the component next in the pipeline.

The pipeline under the hood

doc = nlp.make_doc("This is a sentence") # create a Doc from raw text for name, proc in nlp.pipeline: # iterate over components in order doc = proc(doc) # apply each component

The current processing pipeline is available as nlp.pipeline, which returns a list of (name, component) tuples, or nlp.pipe_names, which only returns a list of human-readable component names.

# [('tagger', <spacy.pipeline.Tagger>), ('parser', <spacy.pipeline.DependencyParser>), ('ner', <spacy.pipeline.EntityRecognizer>)]
# ['tagger', 'parser', 'ner']

Built-in pipeline components

spaCy ships with several built-in pipeline components that are also available in the Language.factories. This means that you can initialize them by calling nlp.create_pipe with their string names and require them in the pipeline settings in your model’s meta.json.

String nameComponentDescription
taggerTaggerAssign part-of-speech-tags.
parserDependencyParserAssign dependency labels.
nerEntityRecognizerAssign named entities.
entity_linkerEntityLinkerAssign knowledge base IDs to named entities. Should be added after the entity recognizer.
textcatTextCategorizerAssign text categories.
entity_rulerEntityRulerAssign named entities based on pattern rules.
sentencizerSentencizerAdd rule-based sentence segmentation without the dependency parse.
merge_noun_chunksmerge_noun_chunksMerge all noun chunks into a single token. Should be added after the tagger and parser.
merge_entitiesmerge_entitiesMerge all entities into a single token. Should be added after the entity recognizer.
merge_subtokensmerge_subtokensMerge subtokens predicted by the parser into single tokens. Should be added after the parser.

Disabling and modifying pipeline components

If you don’t need a particular component of the pipeline – for example, the tagger or the parser, you can disable loading it. This can sometimes make a big difference and improve loading speed. Disabled component names can be provided to spacy.load, Language.from_disk or the nlp object itself as a list:

Disable loading

nlp = spacy.load("en_core_web_sm", disable=["tagger", "parser"]) nlp = English().from_disk("/model", disable=["ner"])

In some cases, you do want to load all pipeline components and their weights, because you need them at different points in your application. However, if you only need a Doc object with named entities, there’s no need to run all pipeline components on it – that can potentially make processing much slower. Instead, you can use the disable keyword argument on nlp.pipe to temporarily disable the components during processing:

Disable for processing

for doc in nlp.pipe(texts, disable=["tagger", "parser"]): # Do something with the doc here

If you need to execute more code with components disabled – e.g. to reset the weights or update only some components during training – you can use the nlp.disable_pipes contextmanager. At the end of the with block, the disabled pipeline components will be restored automatically. Alternatively, disable_pipes returns an object that lets you call its restore() method to restore the disabled components when needed. This can be useful if you want to prevent unnecessary code indentation of large blocks.

Disable for block

# 1. Use as a contextmanager with nlp.disable_pipes("tagger", "parser"): doc = nlp("I won't be tagged and parsed") doc = nlp("I will be tagged and parsed") # 2. Restore manually disabled = nlp.disable_pipes("ner") doc = nlp("I won't have named entities") disabled.restore()

Finally, you can also use the remove_pipe method to remove pipeline components from an existing pipeline, the rename_pipe method to rename them, or the replace_pipe method to replace them with a custom component entirely (more details on this in the section on custom components.

nlp.rename_pipe("ner", "entityrecognizer")
nlp.replace_pipe("tagger", my_custom_tagger)

Creating custom pipeline components

A component receives a Doc object and can modify it – for example, by using the current weights to make a prediction and set some annotation on the document. By adding a component to the pipeline, you’ll get access to the Doc at any point during processing – instead of only being able to modify it afterwards.

docDocThe Doc object processed by the previous component.

Custom components can be added to the pipeline using the add_pipe method. Optionally, you can either specify a component to add it before or after, tell spaCy to add it first or last in the pipeline, or define a custom name. If no name is set and no name attribute is present on your component, the function name is used.

lastboolIf set to True, component is added last in the pipeline (default).
firstboolIf set to True, component is added first in the pipeline.
beforeunicodeString name of component to add the new component before.
afterunicodeString name of component to add the new component after.

Example: A simple pipeline component

The following component receives the Doc in the pipeline and prints some information about it: the number of tokens, the part-of-speech tags of the tokens and a conditional message based on the document length.

import spacy

def my_component(doc):
    print("After tokenization, this doc has {} tokens.".format(len(doc)))
    print("The part-of-speech tags are:", [token.pos_ for token in doc])
    if len(doc) < 10:
        print("This is a pretty short document.")
    return doc

nlp = spacy.load("en_core_web_sm")
nlp.add_pipe(my_component, name="print_info", last=True)
print(nlp.pipe_names)  # ['tagger', 'parser', 'ner', 'print_info']
doc = nlp("This is a sentence.")

Of course, you can also wrap your component as a class to allow initializing it with custom settings and hold state within the component. This is useful for stateful components, especially ones which depend on shared data. In the following example, the custom component EntityMatcher can be initialized with nlp object, a terminology list and an entity label. Using the PhraseMatcher, it then matches the terms in the Doc and adds them to the existing entities.

import spacy
from spacy.matcher import PhraseMatcher
from spacy.tokens import Span

class EntityMatcher(object):
    name = "entity_matcher"

    def __init__(self, nlp, terms, label):
        patterns = [nlp.make_doc(text) for text in terms]
        self.matcher = PhraseMatcher(nlp.vocab)
        self.matcher.add(label, None, *patterns)

    def __call__(self, doc):
        matches = self.matcher(doc)
        for match_id, start, end in matches:
            span = Span(doc, start, end, label=match_id)
            doc.ents = list(doc.ents) + [span]
        return doc

nlp = spacy.load("en_core_web_sm")
terms = ("cat", "dog", "tree kangaroo", "giant sea spider")
entity_matcher = EntityMatcher(nlp, terms, "ANIMAL")

nlp.add_pipe(entity_matcher, after="ner")

print(nlp.pipe_names)  # The components in the pipeline

doc = nlp("This is a text about Barack Obama and a tree kangaroo")
print([(ent.text, ent.label_) for ent in doc.ents])

Example: Custom sentence segmentation logic

Let’s say you want to implement custom logic to improve spaCy’s sentence boundary detection. Currently, sentence segmentation is based on the dependency parse, which doesn’t always produce ideal results. The custom logic should therefore be applied after tokenization, but before the dependency parsing – this way, the parser can also take advantage of the sentence boundaries.

import spacy

def custom_sentencizer(doc):
    for i, token in enumerate(doc[:-2]):
        # Define sentence start if pipe + titlecase token
        if token.text == "|" and doc[i+1].is_title:
            doc[i+1].is_sent_start = True
            # Explicitly set sentence start to False otherwise, to tell
            # the parser to leave those tokens alone
            doc[i+1].is_sent_start = False
    return doc

nlp = spacy.load("en_core_web_sm")
nlp.add_pipe(custom_sentencizer, before="parser")  # Insert before the parser
doc = nlp("This is. A sentence. | This is. Another sentence.")
for sent in doc.sents:

Example: Pipeline component for entity matching and tagging with custom attributes

This example shows how to create a spaCy extension that takes a terminology list (in this case, single- and multi-word company names), matches the occurrences in a document, labels them as ORG entities, merges the tokens and sets custom is_tech_org and has_tech_org attributes. For efficient matching, the example uses the PhraseMatcher which accepts Doc objects as match patterns and works well for large terminology lists. It also ensures your patterns will always match, even when you customize spaCy’s tokenization rules. When you call nlp on a text, the custom pipeline component is applied to the Doc.

Can't fetch code example from GitHub :( Please use the link below to view the example. If you've come across a broken link, we always appreciate a pull request to the repository, or a report on the issue tracker. Thanks!

Wrapping this functionality in a pipeline component allows you to reuse the module with different settings, and have all pre-processing taken care of when you call nlp on your text and receive a Doc object.

Adding factories

When spaCy loads a model via its meta.json, it will iterate over the "pipeline" setting, look up every component name in the internal factories and call nlp.create_pipe to initialize the individual components, like the tagger, parser or entity recognizer. If your model uses custom components, this won’t work – so you’ll have to tell spaCy where to find your component. You can do this by writing to the Language.factories:

from spacy.language import Language
Language.factories["entity_matcher"] = lambda nlp, **cfg: EntityMatcher(nlp, **cfg)

You can also ship the above code and your custom component in your packaged model’s, so it’s executed when you load your model. The **cfg config parameters are passed all the way down from spacy.load, so you can load the model and its components with custom settings:

nlp = spacy.load("your_custom_model", terms=["tree kangaroo"], label="ANIMAL")

Extension attributes v2.0

As of v2.0, spaCy allows you to set any custom attributes and methods on the Doc, Span and Token, which become available as Doc._, Span._ and Token._ – for example, Token._.my_attr. This lets you store additional information relevant to your application, add new features and functionality to spaCy, and implement your own models trained with other machine learning libraries. It also lets you take advantage of spaCy’s data structures and the Doc object as the “single source of truth”.

Writing to a ._ attribute instead of to the Doc directly keeps a clearer separation and makes it easier to ensure backwards compatibility. For example, if you’ve implemented your own .coref property and spaCy claims it one day, it’ll break your code. Similarly, just by looking at the code, you’ll immediately know what’s built-in and what’s custom – for example, doc.sentiment is spaCy, while doc._.sent_score isn’t.

Extension definitions – the defaults, methods, getters and setters you pass in to set_extension – are stored in class attributes on the Underscore class. If you write to an extension attribute, e.g. doc._.hello = True, the data is stored within the Doc.user_data dictionary. To keep the underscore data separate from your other dictionary entries, the string "._." is placed before the name, in a tuple.

There are three main types of extensions, which can be defined using the Doc.set_extension, Span.set_extension and Token.set_extension methods.

  1. Attribute extensions. Set a default value for an attribute, which can be overwritten manually at any time. Attribute extensions work like “normal” variables and are the quickest way to store arbitrary information on a Doc, Span or Token.

     Doc.set_extension("hello", default=True)
     assert doc._.hello
     doc._.hello = False
  2. Property extensions. Define a getter and an optional setter function. If no setter is provided, the extension is immutable. Since the getter and setter functions are only called when you retrieve the attribute, you can also access values of previously added attribute extensions. For example, a Doc getter can average over Token attributes. For Span extensions, you’ll almost always want to use a property – otherwise, you’d have to write to every possible Span in the Doc to set up the values correctly.

    Doc.set_extension("hello", getter=get_hello_value, setter=set_hello_value)
    assert doc._.hello
    doc._.hello = "Hi!"
  3. Method extensions. Assign a function that becomes available as an object method. Method extensions are always immutable. For more details and implementation ideas, see these examples.

    Doc.set_extension("hello", method=lambda doc, name: "Hi {}!".format(name))
    assert doc._.hello("Bob") == "Hi Bob!"

Before you can access a custom extension, you need to register it using the set_extension method on the object you want to add it to, e.g. the Doc. Keep in mind that extensions are always added globally and not just on a particular instance. If an attribute of the same name already exists, or if you’re trying to access an attribute that hasn’t been registered, spaCy will raise an AttributeError.


from spacy.tokens import Doc, Span, Token fruits = ["apple", "pear", "banana", "orange", "strawberry"] is_fruit_getter = lambda token: token.text in fruits has_fruit_getter = lambda obj: any([t.text in fruits for t in obj]) Token.set_extension("is_fruit", getter=is_fruit_getter) Doc.set_extension("has_fruit", getter=has_fruit_getter) Span.set_extension("has_fruit", getter=has_fruit_getter)

Once you’ve registered your custom attribute, you can also use the built-in set, get and has methods to modify and retrieve the attributes. This is especially useful it you want to pass in a string instead of calling doc._.my_attr.

Example: Pipeline component for GPE entities and country meta data via a REST API

This example shows the implementation of a pipeline component that fetches country meta data via the REST Countries API, sets entity annotations for countries, merges entities into one token and sets custom attributes on the Doc, Span and Token – for example, the capital, latitude/longitude coordinates and even the country flag.

Can't fetch code example from GitHub :( Please use the link below to view the example. If you've come across a broken link, we always appreciate a pull request to the repository, or a report on the issue tracker. Thanks!

In this case, all data can be fetched on initialization in one request. However, if you’re working with text that contains incomplete country names, spelling mistakes or foreign-language versions, you could also implement a like_country-style getter function that makes a request to the search API endpoint and returns the best-matching result.

User hooks

While it’s generally recommended to use the Doc._, Span._ and Token._ proxies to add your own custom attributes, spaCy offers a few exceptions to allow customizing the built-in methods like Doc.similarity or Doc.vector with your own hooks, which can rely on statistical models you train yourself. For instance, you can provide your own on-the-fly sentence segmentation algorithm or document similarity method.

Hooks let you customize some of the behaviors of the Doc, Span or Token objects by adding a component to the pipeline. For instance, to customize the Doc.similarity method, you can add a component that sets a custom function to doc.user_hooks['similarity']. The built-in Doc.similarity method will check the user_hooks dict, and delegate to your function if you’ve set one. Similar results can be achieved by setting functions to Doc.user_span_hooks and Doc.user_token_hooks.

user_hooksDoc.vector, Doc.has_vector, Doc.vector_norm, Doc.sents
user_token_hooksToken.similarity, Token.vector, Token.has_vector, Token.vector_norm, Token.conjuncts
user_span_hooksSpan.similarity, Span.vector, Span.has_vector, Span.vector_norm, Span.root

Add custom similarity hooks

class SimilarityModel(object): def __init__(self, model): self._model = model def __call__(self, doc): doc.user_hooks["similarity"] = self.similarity doc.user_span_hooks["similarity"] = self.similarity doc.user_token_hooks["similarity"] = self.similarity def similarity(self, obj1, obj2): y = self._model([obj1.vector, obj2.vector]) return float(y[0])

Developing plugins and wrappers

We’re very excited about all the new possibilities for community extensions and plugins in spaCy v2.0, and we can’t wait to see what you build with it! To get you started, here are a few tips, tricks and best practices. See here for examples of other spaCy extensions.

Usage ideas

  • Adding new features and hooking in models. For example, a sentiment analysis model, or your preferred solution for lemmatization or sentiment analysis. spaCy’s built-in tagger, parser and entity recognizer respect annotations that were already set on the Doc in a previous step of the pipeline.
  • Integrating other libraries and APIs. For example, your pipeline component can write additional information and data directly to the Doc or Token as custom attributes, while making sure no information is lost in the process. This can be output generated by other libraries and models, or an external service with a REST API.
  • Debugging and logging. For example, a component which stores and/or exports relevant information about the current state of the processed document, and insert it at any point of your pipeline.

Best practices

Extensions can claim their own ._ namespace and exist as standalone packages. If you’re developing a tool or library and want to make it easy for others to use it with spaCy and add it to their pipeline, all you have to do is expose a function that takes a Doc, modifies it and returns it.

  • Make sure to choose a descriptive and specific name for your pipeline component class, and set it as its name attribute. Avoid names that are too common or likely to clash with built-in or a user’s other custom components. While it’s fine to call your package "spacy_my_extension", avoid component names including "spacy", since this can easily lead to confusion.

    + name = "myapp_lemmatizer"
    - name = "lemmatizer"
  • When writing to Doc, Token or Span objects, use getter functions wherever possible, and avoid setting values explicitly. Tokens and spans don’t own any data themselves, and they’re implemented as C extension classes – so you can’t usually add new attributes to them like you could with most pure Python objects.

    + is_fruit = lambda token: token.text in ("apple", "orange")
    + Token.set_extension("is_fruit", getter=is_fruit)
    - token._.set_extension("is_fruit", default=False)
    - if token.text in ('"apple", "orange"):
    -     token._.set("is_fruit", True)
  • Always add your custom attributes to the global Doc, Token or Span objects, not a particular instance of them. Add the attributes as early as possible, e.g. in your extension’s __init__ method or in the global scope of your module. This means that in the case of namespace collisions, the user will see an error immediately, not just when they run their pipeline.

    + from spacy.tokens import Doc
    + def __init__(attr="my_attr"):
    +     Doc.set_extension(attr, getter=self.get_doc_attr)
    - def __call__(doc):
    -     doc.set_extension("my_attr", getter=self.get_doc_attr)
  • If your extension is setting properties on the Doc, Token or Span, include an option to let the user to change those attribute names. This makes it easier to avoid namespace collisions and accommodate users with different naming preferences. We recommend adding an attrs argument to the __init__ method of your class so you can write the names to class attributes and reuse them across your component.

    + Doc.set_extension(self.doc_attr, default="some value")
    - Doc.set_extension("my_doc_attr", default="some value")
  • Ideally, extensions should be standalone packages with spaCy and optionally, other packages specified as a dependency. They can freely assign to their own ._ namespace, but should stick to that. If your extension’s only job is to provide a better .similarity implementation, and your docs state this explicitly, there’s no problem with writing to the user_hooks and overwriting spaCy’s built-in method. However, a third-party extension should never silently overwrite built-ins, or attributes set by other extensions.

  • If you’re looking to publish a model that depends on a custom pipeline component, you can either require it in the model package’s dependencies, or – if the component is specific and lightweight – choose to ship it with your model package and add it to the Language instance returned by the model’s load() method. For examples of this, check out the implementations of spaCy’s load_model_from_init_pyload_model_from_path utility functions.

    + nlp.add_pipe(my_custom_component)
    +     return nlp.from_disk(model_path)
  • Once you’re ready to share your extension with others, make sure to add docs and installation instructions (you can always link to this page for more info). Make it easy for others to install and use your extension, for example by uploading it to PyPi. If you’re sharing your code on GitHub, don’t forget to tag it with spacy and spacy-extension to help people find it. If you post it on Twitter, feel free to tag @spacy_io so we can check it out.

Wrapping other models and libraries

Let’s say you have a custom entity recognizer that takes a list of strings and returns their BILUO tags. Given an input like ["A", "text", "about", "Facebook"], it will predict and return ["O", "O", "O", "U-ORG"]. To integrate it into your spaCy pipeline and make it add those entities to the doc.ents, you can wrap it in a custom pipeline component function and pass it the token texts from the Doc object received by the component.

The gold.spans_from_biluo_tags is very helpful here, because it takes a Doc object and token-based BILUO tags and returns a sequence of Span objects in the Doc with added labels. So all your wrapper has to do is compute the entity spans and overwrite the doc.ents.

import your_custom_entity_recognizerfrom import offsets_from_biluo_tags

def custom_ner_wrapper(doc):
    words = [token.text for token in doc]
    custom_entities = your_custom_entity_recognizer(words)    doc.ents = spans_from_biluo_tags(doc, custom_entities)    return doc

The custom_ner_wrapper can then be added to the pipeline of a blank model using nlp.add_pipe. You can also replace the existing entity recognizer of a pretrained model with nlp.replace_pipe.

Here’s another example of a custom model, your_custom_model, that takes a list of tokens and returns lists of fine-grained part-of-speech tags, coarse-grained part-of-speech tags, dependency labels and head token indices. Here, we can use the Doc.from_array to create a new Doc object using those values. To create a numpy array we need integers, so we can look up the string labels in the StringStore. The doc.vocab.strings.add method comes in handy here, because it returns the integer ID of the string and makes sure it’s added to the vocab. This is especially important if the custom model uses a different label scheme than spaCy’s default models.

import your_custom_modelfrom spacy.symbols import POS, TAG, DEP, HEAD
from spacy.tokens import Doc
import numpy

def custom_model_wrapper(doc):
    words = [token.text for token in doc]
    spaces = [token.whitespace for token in doc]
    pos, tags, deps, heads = your_custom_model(words)    # Convert the strings to integers and add them to the string store
    pos = [doc.vocab.strings.add(label) for label in pos]
    tags = [doc.vocab.strings.add(label) for label in tags]
    deps = [doc.vocab.strings.add(label) for label in deps]
    # Create a new Doc from a numpy array
    attrs = [POS, TAG, DEP, HEAD]    arr = numpy.array(list(zip(pos, tags, deps, heads)), dtype="uint64")    new_doc = Doc(doc.vocab, words=words, spaces=spaces).from_array(attrs, arr)    return new_doc