From ab7be5fc5a40ddc02306ed5c96ed05b6c7692261 Mon Sep 17 00:00:00 2001
From: David Buchaca Prats <davidbuchaca@gmail.com>
Date: Thu, 3 Feb 2022 08:47:49 +0100
Subject: [PATCH 1/7] feat: allow empty to get kwargs

---
 docarray/array/mixins/empty.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/docarray/array/mixins/empty.py b/docarray/array/mixins/empty.py
index 9959562fdbb..92a95f96624 100644
--- a/docarray/array/mixins/empty.py
+++ b/docarray/array/mixins/empty.py
@@ -10,11 +10,11 @@ class EmptyMixin:
     """Helper functions for building arrays with empty Document."""
 
     @classmethod
-    def empty(cls: Type['T'], size: int = 0) -> 'T':
+    def empty(cls: Type['T'], size: int = 0, *args, **kwargs) -> 'T':
         """Create a :class:`DocumentArray`  object with :attr:`size` empty
         :class:`Document` objects.
 
         :param size: the number of empty Documents in this container
         :return: a :class:`DocumentArray` object
         """
-        return cls(Document() for _ in range(size))
+        return cls((Document() for _ in range(size)), *args, **kwargs)

From ac1c9fda81023e5d5e44d36f3cf06fdd2ee4da3b Mon Sep 17 00:00:00 2001
From: David Buchaca Prats <davidbuchaca@gmail.com>
Date: Thu, 3 Feb 2022 09:58:07 +0100
Subject: [PATCH 2/7] feat: fix black

---
 docarray/array/mixins/io/binary.py    | 27 +++++++++++++++++++++++----
 docarray/array/mixins/io/csv.py       |  2 ++
 docarray/array/mixins/io/dataframe.py |  2 +-
 docarray/array/mixins/io/from_gen.py  | 10 ++++++++++
 docarray/array/mixins/io/json.py      | 20 +++++++++++++++-----
 docarray/array/mixins/io/pushpull.py  |  4 +---
 docarray/array/mixins/match.py        |  1 -
 docarray/array/mixins/pydantic.py     |  5 ++---
 docarray/document/mixins/porting.py   | 19 +++++++++++++------
 docarray/document/mixins/protobuf.py  |  4 ++--
 docarray/document/mixins/pydantic.py  |  4 ++--
 11 files changed, 71 insertions(+), 27 deletions(-)

diff --git a/docarray/array/mixins/io/binary.py b/docarray/array/mixins/io/binary.py
index 3b7b772c1c6..6269e26150a 100644
--- a/docarray/array/mixins/io/binary.py
+++ b/docarray/array/mixins/io/binary.py
@@ -24,6 +24,8 @@ def load_binary(
         compress: Optional[str] = None,
         _show_progress: bool = False,
         streaming: bool = False,
+        *args,
+        **kwargs,
     ) -> Union['DocumentArray', Generator['Document', None, None]]:
         """Load array elements from a compressed binary file.
 
@@ -49,9 +51,13 @@ def load_binary(
                 protocol=protocol,
                 compress=compress,
                 _show_progress=_show_progress,
+                *args,
+                **kwargs,
             )
         else:
-            return cls._load_binary_all(file_ctx, protocol, compress, _show_progress)
+            return cls._load_binary_all(
+                file_ctx, protocol, compress, _show_progress, *args, **kwargs
+            )
 
     @classmethod
     def _load_binary_stream(
@@ -60,6 +66,8 @@ def _load_binary_stream(
         protocol=None,
         compress=None,
         _show_progress=False,
+        *args,
+        **kwargs,
     ) -> Generator['Document', None, None]:
         """Yield `Document` objects from a binary file
 
@@ -97,7 +105,9 @@ def _load_binary_stream(
                 )
 
     @classmethod
-    def _load_binary_all(cls, file_ctx, protocol, compress, show_progress):
+    def _load_binary_all(
+        cls, file_ctx, protocol, compress, show_progress, *args, **kwargs
+    ):
         """Read a `DocumentArray` object from a binary file
 
         :param protocol: protocol to use
@@ -166,9 +176,14 @@ def from_bytes(
         protocol: str = 'pickle-array',
         compress: Optional[str] = None,
         _show_progress: bool = False,
+        *args,
+        **kwargs,
     ) -> 'T':
         return cls.load_binary(
-            data, protocol=protocol, compress=compress, _show_progress=_show_progress
+            data,
+            protocol=protocol,
+            compress=compress,
+            _show_progress=_show_progress,
         )
 
     def save_binary(
@@ -280,7 +295,9 @@ def to_protobuf(self) -> 'DocumentArrayProto':
         return dap
 
     @classmethod
-    def from_protobuf(cls: Type['T'], pb_msg: 'DocumentArrayProto') -> 'T':
+    def from_protobuf(
+        cls: Type['T'], pb_msg: 'DocumentArrayProto', *args, **kwargs
+    ) -> 'T':
         from .... import Document
 
         return cls(Document.from_protobuf(od) for od in pb_msg.docs)
@@ -295,6 +312,8 @@ def from_base64(
         protocol: str = 'pickle-array',
         compress: Optional[str] = None,
         _show_progress: bool = False,
+        *args,
+        **kwargs,
     ) -> 'T':
         return cls.load_binary(
             base64.b64decode(data),
diff --git a/docarray/array/mixins/io/csv.py b/docarray/array/mixins/io/csv.py
index 9edca8820d2..9c68ce3fefe 100644
--- a/docarray/array/mixins/io/csv.py
+++ b/docarray/array/mixins/io/csv.py
@@ -88,6 +88,8 @@ def load_csv(
         cls: Type['T'],
         file: Union[str, TextIO],
         field_resolver: Optional[Dict[str, str]] = None,
+        *args,
+        **kwargs,
     ) -> 'T':
         """Load array elements from a binary file.
 
diff --git a/docarray/array/mixins/io/dataframe.py b/docarray/array/mixins/io/dataframe.py
index 65d2fd7637e..2ae729a0823 100644
--- a/docarray/array/mixins/io/dataframe.py
+++ b/docarray/array/mixins/io/dataframe.py
@@ -24,7 +24,7 @@ def to_dataframe(self, **kwargs) -> 'DataFrame':
         return DataFrame.from_dict(self.to_list(), **kwargs)
 
     @classmethod
-    def from_dataframe(cls: Type['T'], df: 'DataFrame') -> 'T':
+    def from_dataframe(cls: Type['T'], df: 'DataFrame', *args, **kwargs) -> 'T':
         """Import a :class:`DocumentArray` from a :class:`pandas.DataFrame` object.
 
         :param df: a :class:`pandas.DataFrame` object.
diff --git a/docarray/array/mixins/io/from_gen.py b/docarray/array/mixins/io/from_gen.py
index e038b526ffb..45f9f7f3889 100644
--- a/docarray/array/mixins/io/from_gen.py
+++ b/docarray/array/mixins/io/from_gen.py
@@ -36,6 +36,8 @@ def from_ndarray(
         axis: int = 0,
         size: Optional[int] = None,
         shuffle: bool = False,
+        *args,
+        **kwargs,
     ) -> 'T':
         """Build from a numpy array.
 
@@ -65,6 +67,8 @@ def from_files(
         sampling_rate: Optional[float] = None,
         read_mode: Optional[str] = None,
         to_dataturi: bool = False,
+        *args,
+        **kwargs,
     ) -> 'T':
         """Build from a list of file path or the content of the files.
 
@@ -98,6 +102,8 @@ def from_csv(
         size: Optional[int] = None,
         sampling_rate: Optional[float] = None,
         dialect: Union[str, 'csv.Dialect'] = 'excel',
+        *args,
+        **kwargs,
     ) -> 'T':
         """Build from CSV.
 
@@ -171,6 +177,8 @@ def from_ndjson(
         field_resolver: Optional[Dict[str, str]] = None,
         size: Optional[int] = None,
         sampling_rate: Optional[float] = None,
+        *args,
+        **kwargs,
     ) -> 'T':
         """Build from line separated JSON. Yields documents.
 
@@ -203,6 +211,8 @@ def from_lines(
         field_resolver: Optional[Dict[str, str]] = None,
         size: Optional[int] = None,
         sampling_rate: Optional[float] = None,
+        *args,
+        **kwargs,
     ) -> 'T':
         """Build from lines, json and csv. Yields documents or strings.
 
diff --git a/docarray/array/mixins/io/json.py b/docarray/array/mixins/io/json.py
index 2740bfa7fa0..3147c0fe1da 100644
--- a/docarray/array/mixins/io/json.py
+++ b/docarray/array/mixins/io/json.py
@@ -32,7 +32,11 @@ def save_json(
 
     @classmethod
     def load_json(
-        cls: Type['T'], file: Union[str, TextIO], protocol: str = 'jsonschema', **kwargs
+        cls: Type['T'],
+        file: Union[str, TextIO],
+        protocol: str = 'jsonschema',
+        *args,
+        **kwargs
     ) -> 'T':
         """Load array elements from a JSON file.
 
@@ -57,17 +61,23 @@ def load_json(
 
     @classmethod
     def from_json(
-        cls: Type['T'], file: Union[str, TextIO], protocol: str = 'jsonschema', **kwargs
+        cls: Type['T'],
+        file: Union[str, TextIO],
+        protocol: str = 'jsonschema',
+        *args,
+        **kwargs
     ) -> 'T':
-        return cls.load_json(file, protocol=protocol, **kwargs)
+        return cls.load_json(file, protocol=protocol, *args, **kwargs)
 
     @classmethod
     def from_list(
-        cls: Type['T'], values: List, protocol: str = 'jsonschema', **kwargs
+        cls: Type['T'], values: List, protocol: str = 'jsonschema', *args, **kwargs
     ) -> 'T':
         from .... import Document
 
-        return cls(Document.from_dict(v, protocol=protocol, **kwargs) for v in values)
+        return cls(
+            Document.from_dict(v, protocol=protocol, *args, **kwargs) for v in values
+        )
 
     def to_list(self, protocol: str = 'jsonschema', **kwargs) -> List:
         """Convert the object into a Python list.
diff --git a/docarray/array/mixins/io/pushpull.py b/docarray/array/mixins/io/pushpull.py
index 4461bffee3b..6688863c785 100644
--- a/docarray/array/mixins/io/pushpull.py
+++ b/docarray/array/mixins/io/pushpull.py
@@ -91,9 +91,7 @@ def read(self, n=-1):
 
     @classmethod
     def pull(
-        cls: Type['T'],
-        token: str,
-        show_progress: bool = False,
+        cls: Type['T'], token: str, show_progress: bool = False, *args, **kwargs
     ) -> 'T':
         """Pulling a :class:`DocumentArray` from Jina Cloud Service to local.
 
diff --git a/docarray/array/mixins/match.py b/docarray/array/mixins/match.py
index 6a8ae335df6..d880bd1a88c 100644
--- a/docarray/array/mixins/match.py
+++ b/docarray/array/mixins/match.py
@@ -148,7 +148,6 @@ def _match(self, darray, cdist, limit, normalization, metric_name):
         :param metric_name: if provided, then match result will be marked with this string.
         :return: distances and indices
         """
-
         x_mat = self.embeddings
         y_mat = darray.embeddings
 
diff --git a/docarray/array/mixins/pydantic.py b/docarray/array/mixins/pydantic.py
index 7673aba5133..1aa6c22a698 100644
--- a/docarray/array/mixins/pydantic.py
+++ b/docarray/array/mixins/pydantic.py
@@ -8,7 +8,7 @@
 
 class PydanticMixin:
     @classmethod
-    def get_json_schema(cls, indent: int = 2) -> str:
+    def get_json_schema(cls, indent: int = 2, *args, **kwargs) -> str:
         """Return a JSON Schema of DocumentArray class."""
         from pydantic import schema_json_of
         from ...document.pydantic_model import PydanticDocumentArray
@@ -23,8 +23,7 @@ def to_pydantic_model(self) -> 'PydanticDocumentArray':
 
     @classmethod
     def from_pydantic_model(
-        cls: Type['T'],
-        model: List['BaseModel'],
+        cls: Type['T'], model: List['BaseModel'], *args, **kwargs
     ) -> 'T':
         """Convert a list of PydanticDocument into
 
diff --git a/docarray/document/mixins/porting.py b/docarray/document/mixins/porting.py
index 9880e9c6055..13393c5b10b 100644
--- a/docarray/document/mixins/porting.py
+++ b/docarray/document/mixins/porting.py
@@ -13,7 +13,7 @@
 class PortingMixin:
     @classmethod
     def from_dict(
-        cls: Type['T'], obj: Dict, protocol: str = 'jsonschema', **kwargs
+        cls: Type['T'], obj: Dict, protocol: str = 'jsonschema', *args, **kwargs
     ) -> 'T':
         """Convert a dict object into a Document.
 
@@ -31,14 +31,14 @@ def from_dict(
             from ...proto.docarray_pb2 import DocumentProto
 
             pb_msg = DocumentProto()
-            json_format.ParseDict(obj, pb_msg, **kwargs)
+            json_format.ParseDict(obj, pb_msg, *args, **kwargs)
             return cls.from_protobuf(pb_msg)
         else:
             raise ValueError(f'protocol=`{protocol}` is not supported')
 
     @classmethod
     def from_json(
-        cls: Type['T'], obj: str, protocol: str = 'jsonschema', **kwargs
+        cls: Type['T'], obj: str, protocol: str = 'jsonschema', *args, **kwargs
     ) -> 'T':
         """Convert a JSON string into a Document.
 
@@ -85,8 +85,9 @@ def to_dict(self, protocol: str = 'jsonschema', **kwargs) -> Dict[str, Any]:
             return dataclasses.asdict(self._data)
 
     def to_bytes(
-        self, protocol: str = 'pickle', compress: Optional[str] = None
+        self, protocol: str = 'protobuf', compress: Optional[str] = None
     ) -> bytes:
+
         if protocol == 'pickle':
             bstr = pickle.dumps(self)
         elif protocol == 'protobuf':
@@ -101,8 +102,10 @@ def to_bytes(
     def from_bytes(
         cls: Type['T'],
         data: bytes,
-        protocol: str = 'pickle',
+        protocol: str = 'protobuf',
         compress: Optional[str] = None,
+        *args,
+        **kwargs,
     ) -> 'T':
         """Build Document object from binary bytes
 
@@ -158,6 +161,8 @@ def from_base64(
         data: str,
         protocol: str = 'pickle',
         compress: Optional[str] = None,
+        *args,
+        **kwargs,
     ) -> 'T':
         """Build Document object from binary bytes
 
@@ -166,4 +171,6 @@ def from_base64(
         :param compress: compress method to use
         :return: a Document object
         """
-        return cls.from_bytes(base64.b64decode(data), protocol, compress)
+        return cls.from_bytes(
+            base64.b64decode(data), protocol, compress, *args, **kwargs
+        )
diff --git a/docarray/document/mixins/protobuf.py b/docarray/document/mixins/protobuf.py
index d5154bdfac7..1f090e74867 100644
--- a/docarray/document/mixins/protobuf.py
+++ b/docarray/document/mixins/protobuf.py
@@ -7,10 +7,10 @@
 
 class ProtobufMixin:
     @classmethod
-    def from_protobuf(cls: Type['T'], pb_msg: 'DocumentProto') -> 'T':
+    def from_protobuf(cls: Type['T'], pb_msg: 'DocumentProto', *args, **kwargs) -> 'T':
         from ...proto.io import parse_proto
 
-        return parse_proto(pb_msg)
+        return parse_proto(pb_msg, *args, **kwargs)
 
     def to_protobuf(self) -> 'DocumentProto':
         from ...proto.io import flush_proto
diff --git a/docarray/document/mixins/pydantic.py b/docarray/document/mixins/pydantic.py
index 72347eb2d4d..2d78f12a47b 100644
--- a/docarray/document/mixins/pydantic.py
+++ b/docarray/document/mixins/pydantic.py
@@ -14,7 +14,7 @@ class PydanticMixin:
     """Provide helper functions to convert to/from a Pydantic model"""
 
     @classmethod
-    def get_json_schema(cls, indent: int = 2) -> str:
+    def get_json_schema(cls, indent: int = 2, *args, **kwargs) -> str:
         """Return a JSON Schema of Document class."""
         from ..pydantic_model import PydanticDocument as DP
 
@@ -38,7 +38,7 @@ def to_pydantic_model(self) -> 'PydanticDocument':
         return DP(**_p_dict)
 
     @classmethod
-    def from_pydantic_model(cls: Type['T'], model: 'BaseModel') -> 'T':
+    def from_pydantic_model(cls: Type['T'], model: 'BaseModel', *args, **kwargs) -> 'T':
         """Build a Document object from a Pydantic model
 
         :param model: the pydantic data model object that represents a Document

From 800221d8d8f70a2c7cda21e8545924890791c1ff Mon Sep 17 00:00:00 2001
From: David Buchaca Prats <davidbuchaca@gmail.com>
Date: Thu, 3 Feb 2022 15:22:35 +0100
Subject: [PATCH 3/7] refactor: remove uneeded args kwargs

---
 docarray/array/mixins/io/binary.py    | 16 ++--------------
 docarray/array/mixins/io/csv.py       |  2 --
 docarray/array/mixins/io/dataframe.py |  2 +-
 docarray/array/mixins/io/json.py      | 16 ++++------------
 docarray/array/mixins/io/pushpull.py  |  4 +---
 docarray/array/mixins/pydantic.py     |  6 ++----
 docarray/document/mixins/porting.py   |  8 +-------
 docarray/document/mixins/pydantic.py  |  4 ++--
 8 files changed, 13 insertions(+), 45 deletions(-)

diff --git a/docarray/array/mixins/io/binary.py b/docarray/array/mixins/io/binary.py
index 6269e26150a..80571a1f269 100644
--- a/docarray/array/mixins/io/binary.py
+++ b/docarray/array/mixins/io/binary.py
@@ -24,8 +24,6 @@ def load_binary(
         compress: Optional[str] = None,
         _show_progress: bool = False,
         streaming: bool = False,
-        *args,
-        **kwargs,
     ) -> Union['DocumentArray', Generator['Document', None, None]]:
         """Load array elements from a compressed binary file.
 
@@ -55,9 +53,7 @@ def load_binary(
                 **kwargs,
             )
         else:
-            return cls._load_binary_all(
-                file_ctx, protocol, compress, _show_progress, *args, **kwargs
-            )
+            return cls._load_binary_all(file_ctx, protocol, compress, _show_progress)
 
     @classmethod
     def _load_binary_stream(
@@ -66,8 +62,6 @@ def _load_binary_stream(
         protocol=None,
         compress=None,
         _show_progress=False,
-        *args,
-        **kwargs,
     ) -> Generator['Document', None, None]:
         """Yield `Document` objects from a binary file
 
@@ -105,9 +99,7 @@ def _load_binary_stream(
                 )
 
     @classmethod
-    def _load_binary_all(
-        cls, file_ctx, protocol, compress, show_progress, *args, **kwargs
-    ):
+    def _load_binary_all(cls, file_ctx, protocol, compress, show_progress):
         """Read a `DocumentArray` object from a binary file
 
         :param protocol: protocol to use
@@ -176,8 +168,6 @@ def from_bytes(
         protocol: str = 'pickle-array',
         compress: Optional[str] = None,
         _show_progress: bool = False,
-        *args,
-        **kwargs,
     ) -> 'T':
         return cls.load_binary(
             data,
@@ -312,8 +302,6 @@ def from_base64(
         protocol: str = 'pickle-array',
         compress: Optional[str] = None,
         _show_progress: bool = False,
-        *args,
-        **kwargs,
     ) -> 'T':
         return cls.load_binary(
             base64.b64decode(data),
diff --git a/docarray/array/mixins/io/csv.py b/docarray/array/mixins/io/csv.py
index 9c68ce3fefe..9edca8820d2 100644
--- a/docarray/array/mixins/io/csv.py
+++ b/docarray/array/mixins/io/csv.py
@@ -88,8 +88,6 @@ def load_csv(
         cls: Type['T'],
         file: Union[str, TextIO],
         field_resolver: Optional[Dict[str, str]] = None,
-        *args,
-        **kwargs,
     ) -> 'T':
         """Load array elements from a binary file.
 
diff --git a/docarray/array/mixins/io/dataframe.py b/docarray/array/mixins/io/dataframe.py
index 2ae729a0823..65d2fd7637e 100644
--- a/docarray/array/mixins/io/dataframe.py
+++ b/docarray/array/mixins/io/dataframe.py
@@ -24,7 +24,7 @@ def to_dataframe(self, **kwargs) -> 'DataFrame':
         return DataFrame.from_dict(self.to_list(), **kwargs)
 
     @classmethod
-    def from_dataframe(cls: Type['T'], df: 'DataFrame', *args, **kwargs) -> 'T':
+    def from_dataframe(cls: Type['T'], df: 'DataFrame') -> 'T':
         """Import a :class:`DocumentArray` from a :class:`pandas.DataFrame` object.
 
         :param df: a :class:`pandas.DataFrame` object.
diff --git a/docarray/array/mixins/io/json.py b/docarray/array/mixins/io/json.py
index 3147c0fe1da..2c14fdd3593 100644
--- a/docarray/array/mixins/io/json.py
+++ b/docarray/array/mixins/io/json.py
@@ -35,8 +35,6 @@ def load_json(
         cls: Type['T'],
         file: Union[str, TextIO],
         protocol: str = 'jsonschema',
-        *args,
-        **kwargs
     ) -> 'T':
         """Load array elements from a JSON file.
 
@@ -57,27 +55,21 @@ def load_json(
             constructor = Document.from_dict
 
         with file_ctx as fp:
-            return cls(constructor(v, protocol=protocol, **kwargs) for v in fp)
+            return cls(constructor(v, protocol=protocol) for v in fp)
 
     @classmethod
     def from_json(
         cls: Type['T'],
         file: Union[str, TextIO],
         protocol: str = 'jsonschema',
-        *args,
-        **kwargs
     ) -> 'T':
-        return cls.load_json(file, protocol=protocol, *args, **kwargs)
+        return cls.load_json(file, protocol=protocol)
 
     @classmethod
-    def from_list(
-        cls: Type['T'], values: List, protocol: str = 'jsonschema', *args, **kwargs
-    ) -> 'T':
+    def from_list(cls: Type['T'], values: List, protocol: str = 'jsonschema') -> 'T':
         from .... import Document
 
-        return cls(
-            Document.from_dict(v, protocol=protocol, *args, **kwargs) for v in values
-        )
+        return cls(Document.from_dict(v, protocol=protocol) for v in values)
 
     def to_list(self, protocol: str = 'jsonschema', **kwargs) -> List:
         """Convert the object into a Python list.
diff --git a/docarray/array/mixins/io/pushpull.py b/docarray/array/mixins/io/pushpull.py
index 6688863c785..e6c5df8aa70 100644
--- a/docarray/array/mixins/io/pushpull.py
+++ b/docarray/array/mixins/io/pushpull.py
@@ -90,9 +90,7 @@ def read(self, n=-1):
             )
 
     @classmethod
-    def pull(
-        cls: Type['T'], token: str, show_progress: bool = False, *args, **kwargs
-    ) -> 'T':
+    def pull(cls: Type['T'], token: str, show_progress: bool = False) -> 'T':
         """Pulling a :class:`DocumentArray` from Jina Cloud Service to local.
 
         :param token: the upload token set during :meth:`.push`
diff --git a/docarray/array/mixins/pydantic.py b/docarray/array/mixins/pydantic.py
index 1aa6c22a698..d3fa3df478a 100644
--- a/docarray/array/mixins/pydantic.py
+++ b/docarray/array/mixins/pydantic.py
@@ -8,7 +8,7 @@
 
 class PydanticMixin:
     @classmethod
-    def get_json_schema(cls, indent: int = 2, *args, **kwargs) -> str:
+    def get_json_schema(cls, indent: int = 2) -> str:
         """Return a JSON Schema of DocumentArray class."""
         from pydantic import schema_json_of
         from ...document.pydantic_model import PydanticDocumentArray
@@ -22,9 +22,7 @@ def to_pydantic_model(self) -> 'PydanticDocumentArray':
         return [d.to_pydantic_model() for d in self]
 
     @classmethod
-    def from_pydantic_model(
-        cls: Type['T'], model: List['BaseModel'], *args, **kwargs
-    ) -> 'T':
+    def from_pydantic_model(cls: Type['T'], model: List['BaseModel']) -> 'T':
         """Convert a list of PydanticDocument into
 
         :param model: the pydantic data model object that represents a DocumentArray
diff --git a/docarray/document/mixins/porting.py b/docarray/document/mixins/porting.py
index 13393c5b10b..7506a03754c 100644
--- a/docarray/document/mixins/porting.py
+++ b/docarray/document/mixins/porting.py
@@ -104,8 +104,6 @@ def from_bytes(
         data: bytes,
         protocol: str = 'protobuf',
         compress: Optional[str] = None,
-        *args,
-        **kwargs,
     ) -> 'T':
         """Build Document object from binary bytes
 
@@ -161,8 +159,6 @@ def from_base64(
         data: str,
         protocol: str = 'pickle',
         compress: Optional[str] = None,
-        *args,
-        **kwargs,
     ) -> 'T':
         """Build Document object from binary bytes
 
@@ -171,6 +167,4 @@ def from_base64(
         :param compress: compress method to use
         :return: a Document object
         """
-        return cls.from_bytes(
-            base64.b64decode(data), protocol, compress, *args, **kwargs
-        )
+        return cls.from_bytes(base64.b64decode(data), protocol, compress)
diff --git a/docarray/document/mixins/pydantic.py b/docarray/document/mixins/pydantic.py
index 2d78f12a47b..72347eb2d4d 100644
--- a/docarray/document/mixins/pydantic.py
+++ b/docarray/document/mixins/pydantic.py
@@ -14,7 +14,7 @@ class PydanticMixin:
     """Provide helper functions to convert to/from a Pydantic model"""
 
     @classmethod
-    def get_json_schema(cls, indent: int = 2, *args, **kwargs) -> str:
+    def get_json_schema(cls, indent: int = 2) -> str:
         """Return a JSON Schema of Document class."""
         from ..pydantic_model import PydanticDocument as DP
 
@@ -38,7 +38,7 @@ def to_pydantic_model(self) -> 'PydanticDocument':
         return DP(**_p_dict)
 
     @classmethod
-    def from_pydantic_model(cls: Type['T'], model: 'BaseModel', *args, **kwargs) -> 'T':
+    def from_pydantic_model(cls: Type['T'], model: 'BaseModel') -> 'T':
         """Build a Document object from a Pydantic model
 
         :param model: the pydantic data model object that represents a Document

From 48d5993df7bb98dd38737459c3ebee42b9a6fbf7 Mon Sep 17 00:00:00 2001
From: David Buchaca Prats <davidbuchaca@gmail.com>
Date: Thu, 3 Feb 2022 15:35:10 +0100
Subject: [PATCH 4/7] refactor: remove unwanted args

---
 docarray/array/mixins/io/binary.py   | 6 +-----
 docarray/array/mixins/io/from_gen.py | 8 --------
 docarray/document/mixins/porting.py  | 6 +++---
 docarray/document/mixins/protobuf.py | 4 ++--
 4 files changed, 6 insertions(+), 18 deletions(-)

diff --git a/docarray/array/mixins/io/binary.py b/docarray/array/mixins/io/binary.py
index 80571a1f269..32bcc194f34 100644
--- a/docarray/array/mixins/io/binary.py
+++ b/docarray/array/mixins/io/binary.py
@@ -49,8 +49,6 @@ def load_binary(
                 protocol=protocol,
                 compress=compress,
                 _show_progress=_show_progress,
-                *args,
-                **kwargs,
             )
         else:
             return cls._load_binary_all(file_ctx, protocol, compress, _show_progress)
@@ -285,9 +283,7 @@ def to_protobuf(self) -> 'DocumentArrayProto':
         return dap
 
     @classmethod
-    def from_protobuf(
-        cls: Type['T'], pb_msg: 'DocumentArrayProto', *args, **kwargs
-    ) -> 'T':
+    def from_protobuf(cls: Type['T'], pb_msg: 'DocumentArrayProto') -> 'T':
         from .... import Document
 
         return cls(Document.from_protobuf(od) for od in pb_msg.docs)
diff --git a/docarray/array/mixins/io/from_gen.py b/docarray/array/mixins/io/from_gen.py
index 45f9f7f3889..2428e2e103e 100644
--- a/docarray/array/mixins/io/from_gen.py
+++ b/docarray/array/mixins/io/from_gen.py
@@ -67,8 +67,6 @@ def from_files(
         sampling_rate: Optional[float] = None,
         read_mode: Optional[str] = None,
         to_dataturi: bool = False,
-        *args,
-        **kwargs,
     ) -> 'T':
         """Build from a list of file path or the content of the files.
 
@@ -102,8 +100,6 @@ def from_csv(
         size: Optional[int] = None,
         sampling_rate: Optional[float] = None,
         dialect: Union[str, 'csv.Dialect'] = 'excel',
-        *args,
-        **kwargs,
     ) -> 'T':
         """Build from CSV.
 
@@ -177,8 +173,6 @@ def from_ndjson(
         field_resolver: Optional[Dict[str, str]] = None,
         size: Optional[int] = None,
         sampling_rate: Optional[float] = None,
-        *args,
-        **kwargs,
     ) -> 'T':
         """Build from line separated JSON. Yields documents.
 
@@ -211,8 +205,6 @@ def from_lines(
         field_resolver: Optional[Dict[str, str]] = None,
         size: Optional[int] = None,
         sampling_rate: Optional[float] = None,
-        *args,
-        **kwargs,
     ) -> 'T':
         """Build from lines, json and csv. Yields documents or strings.
 
diff --git a/docarray/document/mixins/porting.py b/docarray/document/mixins/porting.py
index 7506a03754c..f09481e5fdc 100644
--- a/docarray/document/mixins/porting.py
+++ b/docarray/document/mixins/porting.py
@@ -13,7 +13,7 @@
 class PortingMixin:
     @classmethod
     def from_dict(
-        cls: Type['T'], obj: Dict, protocol: str = 'jsonschema', *args, **kwargs
+        cls: Type['T'], obj: Dict, protocol: str = 'jsonschema', **kwargs
     ) -> 'T':
         """Convert a dict object into a Document.
 
@@ -31,14 +31,14 @@ def from_dict(
             from ...proto.docarray_pb2 import DocumentProto
 
             pb_msg = DocumentProto()
-            json_format.ParseDict(obj, pb_msg, *args, **kwargs)
+            json_format.ParseDict(obj, pb_msg, **kwargs)
             return cls.from_protobuf(pb_msg)
         else:
             raise ValueError(f'protocol=`{protocol}` is not supported')
 
     @classmethod
     def from_json(
-        cls: Type['T'], obj: str, protocol: str = 'jsonschema', *args, **kwargs
+        cls: Type['T'], obj: str, protocol: str = 'jsonschema', **kwargs
     ) -> 'T':
         """Convert a JSON string into a Document.
 
diff --git a/docarray/document/mixins/protobuf.py b/docarray/document/mixins/protobuf.py
index 1f090e74867..d5154bdfac7 100644
--- a/docarray/document/mixins/protobuf.py
+++ b/docarray/document/mixins/protobuf.py
@@ -7,10 +7,10 @@
 
 class ProtobufMixin:
     @classmethod
-    def from_protobuf(cls: Type['T'], pb_msg: 'DocumentProto', *args, **kwargs) -> 'T':
+    def from_protobuf(cls: Type['T'], pb_msg: 'DocumentProto') -> 'T':
         from ...proto.io import parse_proto
 
-        return parse_proto(pb_msg, *args, **kwargs)
+        return parse_proto(pb_msg)
 
     def to_protobuf(self) -> 'DocumentProto':
         from ...proto.io import flush_proto

From 3dd666f6058f24cb8d1d26338c25d4e561b54d30 Mon Sep 17 00:00:00 2001
From: David Buchaca Prats <davidbuchaca@gmail.com>
Date: Thu, 3 Feb 2022 15:39:27 +0100
Subject: [PATCH 5/7] refactor: revert document mixin changes

---
 docarray/document/mixins/porting.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/docarray/document/mixins/porting.py b/docarray/document/mixins/porting.py
index f09481e5fdc..fbfcd859c71 100644
--- a/docarray/document/mixins/porting.py
+++ b/docarray/document/mixins/porting.py
@@ -85,7 +85,7 @@ def to_dict(self, protocol: str = 'jsonschema', **kwargs) -> Dict[str, Any]:
             return dataclasses.asdict(self._data)
 
     def to_bytes(
-        self, protocol: str = 'protobuf', compress: Optional[str] = None
+        self, protocol: str = 'pickle', compress: Optional[str] = None
     ) -> bytes:
 
         if protocol == 'pickle':
@@ -102,7 +102,7 @@ def to_bytes(
     def from_bytes(
         cls: Type['T'],
         data: bytes,
-        protocol: str = 'protobuf',
+        protocol: str = 'pickle',
         compress: Optional[str] = None,
     ) -> 'T':
         """Build Document object from binary bytes

From e57c87588b494beaca33c6e79ef3b24ba5cb511b Mon Sep 17 00:00:00 2001
From: David Buchaca Prats <davidbuchaca@gmail.com>
Date: Thu, 3 Feb 2022 15:39:49 +0100
Subject: [PATCH 6/7] refactor: revert document mixin changes

---
 docarray/document/mixins/porting.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/docarray/document/mixins/porting.py b/docarray/document/mixins/porting.py
index fbfcd859c71..9880e9c6055 100644
--- a/docarray/document/mixins/porting.py
+++ b/docarray/document/mixins/porting.py
@@ -87,7 +87,6 @@ def to_dict(self, protocol: str = 'jsonschema', **kwargs) -> Dict[str, Any]:
     def to_bytes(
         self, protocol: str = 'pickle', compress: Optional[str] = None
     ) -> bytes:
-
         if protocol == 'pickle':
             bstr = pickle.dumps(self)
         elif protocol == 'protobuf':

From cb254632486d4d1d68efb6fe2a4d28186a7a3330 Mon Sep 17 00:00:00 2001
From: David Buchaca Prats <davidbuchaca@gmail.com>
Date: Thu, 3 Feb 2022 16:27:57 +0100
Subject: [PATCH 7/7] refactor: restore kwargs from main

---
 docarray/array/mixins/io/json.py | 18 ++++++++----------
 docarray/array/mixins/match.py   |  1 +
 2 files changed, 9 insertions(+), 10 deletions(-)

diff --git a/docarray/array/mixins/io/json.py b/docarray/array/mixins/io/json.py
index 2c14fdd3593..2740bfa7fa0 100644
--- a/docarray/array/mixins/io/json.py
+++ b/docarray/array/mixins/io/json.py
@@ -32,9 +32,7 @@ def save_json(
 
     @classmethod
     def load_json(
-        cls: Type['T'],
-        file: Union[str, TextIO],
-        protocol: str = 'jsonschema',
+        cls: Type['T'], file: Union[str, TextIO], protocol: str = 'jsonschema', **kwargs
     ) -> 'T':
         """Load array elements from a JSON file.
 
@@ -55,21 +53,21 @@ def load_json(
             constructor = Document.from_dict
 
         with file_ctx as fp:
-            return cls(constructor(v, protocol=protocol) for v in fp)
+            return cls(constructor(v, protocol=protocol, **kwargs) for v in fp)
 
     @classmethod
     def from_json(
-        cls: Type['T'],
-        file: Union[str, TextIO],
-        protocol: str = 'jsonschema',
+        cls: Type['T'], file: Union[str, TextIO], protocol: str = 'jsonschema', **kwargs
     ) -> 'T':
-        return cls.load_json(file, protocol=protocol)
+        return cls.load_json(file, protocol=protocol, **kwargs)
 
     @classmethod
-    def from_list(cls: Type['T'], values: List, protocol: str = 'jsonschema') -> 'T':
+    def from_list(
+        cls: Type['T'], values: List, protocol: str = 'jsonschema', **kwargs
+    ) -> 'T':
         from .... import Document
 
-        return cls(Document.from_dict(v, protocol=protocol) for v in values)
+        return cls(Document.from_dict(v, protocol=protocol, **kwargs) for v in values)
 
     def to_list(self, protocol: str = 'jsonschema', **kwargs) -> List:
         """Convert the object into a Python list.
diff --git a/docarray/array/mixins/match.py b/docarray/array/mixins/match.py
index d880bd1a88c..6a8ae335df6 100644
--- a/docarray/array/mixins/match.py
+++ b/docarray/array/mixins/match.py
@@ -148,6 +148,7 @@ def _match(self, darray, cdist, limit, normalization, metric_name):
         :param metric_name: if provided, then match result will be marked with this string.
         :return: distances and indices
         """
+
         x_mat = self.embeddings
         y_mat = darray.embeddings