fix: update spacy patch

edsnlp/patch_spacy.py

@@ -114,6 +114,7 @@ def __init__(
     max_length: int = 10**6,
     meta: Dict[str, Any] = {},
     create_tokenizer: Optional[Callable[["Language"], Callable[[str], Doc]]] = None,
+    create_vectors: Optional[Callable[["Vocab"], Any]] = None,
     batch_size: int = 1000,
     **kwargs,
 ) -> None:
@@ -158,21 +159,23 @@ def __init__(
     if vocab is True:
         vectors_name = meta.get("vectors", {}).get("name")
         vocab = create_vocab(self.lang, self.Defaults, vectors_name=vectors_name)
-    if (self.lang and vocab.lang) and (self.lang != vocab.lang):
-        raise ValueError(Errors.E150.format(nlp=self.lang, vocab=vocab.lang))
+        if not create_vectors and "@vectors" in self._config["nlp"]["vectors"]:
+            vectors_cfg = {"vectors": self._config["nlp"]["vectors"]}
+            create_vectors = registry.resolve(vectors_cfg)["vectors"]
+        vocab.vectors = create_vectors(vocab)
+    else:
+        if (self.lang and vocab.lang) and (self.lang != vocab.lang):
+            raise ValueError(Errors.E150.format(nlp=self.lang, vocab=vocab.lang))
     self.vocab: Vocab = vocab
     if self.lang is None:
         self.lang = self.vocab.lang
     self._components: List[Tuple[str, Callable[[Doc], Doc]]] = []
     self._disabled: Set[str] = set()
     self.max_length = max_length
     # Create the default tokenizer from the default config
-    create_tokenizer = (
-        create_tokenizer
-        or registry.resolve({"tokenizer": self._config["nlp"]["tokenizer"]})[
-            "tokenizer"
-        ]
-    )
+    if not create_tokenizer:
+        tokenizer_cfg = {"tokenizer": self._config["nlp"]["tokenizer"]}
+        create_tokenizer = registry.resolve(tokenizer_cfg)["tokenizer"]
     self.tokenizer = create_tokenizer(self)
     self.batch_size = batch_size
     self.default_error_handler = raise_error