fix: docstring tests with pydantic v2 (docarray#1816)

samsja · web-flow · commit c2b08fa5cd9f · 2023-10-02T10:33:03.000+02:00
Signed-off-by: samsja &lt;sami.jaghouar@hotmail.fr&gt;
diff --git a/docarray/array/doc_list/doc_list.py b/docarray/array/doc_list/doc_list.py
@@ -68,7 +68,7 @@ class DocList(
 
 
     class Image(BaseDoc):
-        tensor: Optional[NdArray[100]]
+        tensor: Optional[NdArray[100]] = None
         url: ImageUrl
 
 
diff --git a/docarray/documents/audio.py b/docarray/documents/audio.py
@@ -60,7 +60,7 @@ class AudioDoc(BaseDoc):
 
     # extend it
     class MyAudio(AudioDoc):
-        name: Optional[TextDoc]
+        name: Optional[TextDoc] = None
 
 
     audio = MyAudio(
diff --git a/docarray/documents/image.py b/docarray/documents/image.py
@@ -58,7 +58,7 @@ class ImageDoc(BaseDoc):
 
     # extend it
     class MyImage(ImageDoc):
-        second_embedding: Optional[AnyEmbedding]
+        second_embedding: Optional[AnyEmbedding] = None
 
 
     image = MyImage(
diff --git a/docarray/documents/mesh/mesh_3d.py b/docarray/documents/mesh/mesh_3d.py
@@ -60,7 +60,7 @@ class Mesh3D(BaseDoc):
 
     # extend it
     class MyMesh3D(Mesh3D):
-        name: Optional[str]
+        name: Optional[str] = None
 
 
     mesh = MyMesh3D(url='https://people.sc.fsu.edu/~jburkardt/data/obj/al.obj')
diff --git a/docarray/documents/point_cloud/point_cloud_3d.py b/docarray/documents/point_cloud/point_cloud_3d.py
@@ -62,7 +62,7 @@ class PointCloud3D(BaseDoc):
 
     # extend it
     class MyPointCloud3D(PointCloud3D):
-        second_embedding: Optional[AnyEmbedding]
+        second_embedding: Optional[AnyEmbedding] = None
 
 
     pc = MyPointCloud3D(url='https://people.sc.fsu.edu/~jburkardt/data/obj/al.obj')
diff --git a/docarray/documents/text.py b/docarray/documents/text.py
@@ -54,7 +54,7 @@ class TextDoc(BaseDoc):
 
     # extend it
     class MyText(TextDoc):
-        second_embedding: Optional[AnyEmbedding]
+        second_embedding: Optional[AnyEmbedding] = None
 
 
     txt_doc = MyText(url='https://www.gutenberg.org/files/1065/1065-0.txt')
diff --git a/docarray/documents/video.py b/docarray/documents/video.py
@@ -66,7 +66,7 @@ class VideoDoc(BaseDoc):
 
     # extend it
     class MyVideo(VideoDoc):
-        name: Optional[TextDoc]
+        name: Optional[TextDoc] = None
 
 
     video = MyVideo(
diff --git a/docarray/typing/bytes/audio_bytes.py b/docarray/typing/bytes/audio_bytes.py
@@ -33,9 +33,9 @@ def load(self) -> Tuple[AudioNdArray, int]:
 
         class MyAudio(BaseDoc):
             url: AudioUrl
-            tensor: Optional[AudioNdArray]
-            bytes_: Optional[AudioBytes]
-            frame_rate: Optional[float]
+            tensor: Optional[AudioNdArray] = None
+            bytes_: Optional[AudioBytes] = None
+            frame_rate: Optional[float] = None
 
 
         doc = MyAudio(url='https://www.kozco.com/tech/piano2.wav')
diff --git a/docarray/typing/tensor/audio/audio_ndarray.py b/docarray/typing/tensor/audio/audio_ndarray.py
@@ -22,9 +22,9 @@ class AudioNdArray(AbstractAudioTensor, NdArray):
 
     class MyAudioDoc(BaseDoc):
         title: str
-        audio_tensor: Optional[AudioNdArray]
-        url: Optional[AudioUrl]
-        bytes_: Optional[AudioBytes]
+        audio_tensor: Optional[AudioNdArray] = None
+        url: Optional[AudioUrl] = None
+        bytes_: Optional[AudioBytes] = None
 
 
     # from tensor
diff --git a/docarray/typing/tensor/audio/audio_torch_tensor.py b/docarray/typing/tensor/audio/audio_torch_tensor.py
@@ -22,9 +22,9 @@ class AudioTorchTensor(AbstractAudioTensor, TorchTensor, metaclass=metaTorchAndN
 
     class MyAudioDoc(BaseDoc):
         title: str
-        audio_tensor: Optional[AudioTorchTensor]
-        url: Optional[AudioUrl]
-        bytes_: Optional[AudioBytes]
+        audio_tensor: Optional[AudioTorchTensor] = None
+        url: Optional[AudioUrl] = None
+        bytes_: Optional[AudioBytes] = None
 
 
     doc_1 = MyAudioDoc(
diff --git a/docarray/typing/tensor/image/image_ndarray.py b/docarray/typing/tensor/image/image_ndarray.py
@@ -25,9 +25,9 @@ class ImageNdArray(AbstractImageTensor, NdArray):
 
     class MyImageDoc(BaseDoc):
         title: str
-        tensor: Optional[ImageNdArray]
-        url: Optional[ImageUrl]
-        bytes: Optional[ImageBytes]
+        tensor: Optional[ImageNdArray] = None
+        url: Optional[ImageUrl] = None
+        bytes: Optional[ImageBytes] = None
 
 
     # from url
diff --git a/docarray/typing/tensor/image/image_torch_tensor.py b/docarray/typing/tensor/image/image_torch_tensor.py
@@ -28,9 +28,9 @@ class ImageTorchTensor(AbstractImageTensor, TorchTensor, metaclass=metaTorchAndN
 
     class MyImageDoc(BaseDoc):
         title: str
-        tensor: Optional[ImageTorchTensor]
-        url: Optional[ImageUrl]
-        bytes: Optional[ImageBytes]
+        tensor: Optional[ImageTorchTensor] = None
+        url: Optional[ImageUrl] = None
+        bytes: Optional[ImageBytes] = None
 
 
     doc = MyImageDoc(
diff --git a/docarray/typing/tensor/video/video_ndarray.py b/docarray/typing/tensor/video/video_ndarray.py
@@ -29,8 +29,8 @@ class VideoNdArray(NdArray, VideoTensorMixin):
 
     class MyVideoDoc(BaseDoc):
         title: str
-        url: Optional[VideoUrl]
-        video_tensor: Optional[VideoNdArray]
+        url: Optional[VideoUrl] = None
+        video_tensor: Optional[VideoNdArray] = None
 
 
     doc_1 = MyVideoDoc(
diff --git a/docarray/typing/tensor/video/video_torch_tensor.py b/docarray/typing/tensor/video/video_torch_tensor.py
@@ -28,8 +28,8 @@ class VideoTorchTensor(TorchTensor, VideoTensorMixin, metaclass=metaTorchAndNode
 
     class MyVideoDoc(BaseDoc):
         title: str
-        url: Optional[VideoUrl]
-        video_tensor: Optional[VideoTorchTensor]
+        url: Optional[VideoUrl] = None
+        video_tensor: Optional[VideoTorchTensor] = None
 
 
     doc_1 = MyVideoDoc(
diff --git a/docarray/typing/url/audio_url.py b/docarray/typing/url/audio_url.py
@@ -46,7 +46,7 @@ def load(self: T) -> Tuple[AudioNdArray, int]:
 
         class MyDoc(BaseDoc):
             audio_url: AudioUrl
-            audio_tensor: Optional[AudioNdArray]
+            audio_tensor: Optional[AudioNdArray] = None
 
 
         doc = MyDoc(audio_url='https://www.kozco.com/tech/piano2.wav')
diff --git a/docarray/typing/url/video_url.py b/docarray/typing/url/video_url.py
@@ -48,9 +48,9 @@ def load(self: T, **kwargs) -> VideoLoadResult:
 
         class MyDoc(BaseDoc):
             video_url: VideoUrl
-            video: Optional[VideoNdArray]
-            audio: Optional[AudioNdArray]
-            key_frame_indices: Optional[NdArray]
+            video: Optional[VideoNdArray] = None
+            audio: Optional[AudioNdArray] = None
+            key_frame_indices: Optional[NdArray] = None
 
 
         doc = MyDoc(
diff --git a/docs/data_types/3d_mesh/3d_mesh.md b/docs/data_types/3d_mesh/3d_mesh.md
@@ -42,7 +42,7 @@ from docarray.typing import Mesh3DUrl
 
 class MyMesh3D(BaseDoc):
     mesh_url: Mesh3DUrl
-    tensors: Optional[VerticesAndFaces]
+    tensors: Optional[VerticesAndFaces] = None
 
 
 doc = MyMesh3D(mesh_url="https://people.sc.fsu.edu/~jburkardt/data/obj/al.obj")
@@ -1355,7 +1355,7 @@ from docarray.typing import PointCloud3DUrl
 
 class MyPointCloud(BaseDoc):
     url: PointCloud3DUrl
-    tensors: Optional[PointsAndColors]
+    tensors: Optional[PointsAndColors] = None
 
 
 doc = MyPointCloud(url="https://people.sc.fsu.edu/~jburkardt/data/obj/al.obj")
@@ -2655,20 +2655,20 @@ The [`Mesh3D`][docarray.documents.mesh.Mesh3D] class provides a [`Mesh3DUrl`][do
 
 ``` { .python }
 class Mesh3D(BaseDoc):
-    url: Optional[Mesh3DUrl]
-    tensors: Optional[VerticesAndFaces]
-    embedding: Optional[AnyEmbedding]
-    bytes_: Optional[bytes]
+    url: Optional[Mesh3DUrl] = None
+    tensors: Optional[VerticesAndFaces] = None
+    embedding: Optional[AnyEmbedding] = None
+    bytes_: Optional[bytes] = None
 ```
 
 ### `PointCloud3D`
 
 ``` { .python }
 class PointCloud3D(BaseDoc):
-    url: Optional[PointCloud3DUrl]
-    tensors: Optional[PointsAndColors]
-    embedding: Optional[AnyEmbedding]
-    bytes_: Optional[bytes]
+    url: Optional[PointCloud3DUrl] = None
+    tensors: Optional[PointsAndColors] = None
+    embedding: Optional[AnyEmbedding] = None
+    bytes_: Optional[bytes] = None
 ```
 
 You can use them directly, extend or compose them:
diff --git a/docs/data_types/audio/audio.md b/docs/data_types/audio/audio.md
@@ -187,11 +187,11 @@ To get started and play around with your audio data, DocArray provides a predefi
 
 ``` { .python }
 class AudioDoc(BaseDoc):
-    url: Optional[AudioUrl]
-    tensor: Optional[AudioTensor]
-    embedding: Optional[AnyEmbedding]
-    bytes_: Optional[AudioBytes]
-    frame_rate: Optional[int]
+    url: Optional[AudioUrl] = None
+    tensor: Optional[AudioTensor] = None
+    embedding: Optional[AnyEmbedding] = None
+    bytes_: Optional[AudioBytes] = None
+    frame_rate: Optional[int] = None
 ```
 
 You can use this class directly or extend it to your preference:
@@ -203,7 +203,7 @@ from typing import Optional
 
 # extend AudioDoc
 class MyAudio(AudioDoc):
-    name: Optional[str]
+    name: Optional[str] = None
 
 
 audio = MyAudio(
diff --git a/docs/data_types/image/image.md b/docs/data_types/image/image.md
@@ -171,10 +171,10 @@ To get started and play around with the image modality, DocArray provides a pred
 
 ``` { .python }
 class ImageDoc(BaseDoc):
-    url: Optional[ImageUrl]
-    tensor: Optional[ImageTensor]
-    embedding: Optional[AnyEmbedding]
-    bytes_: Optional[ImageBytes]
+    url: Optional[ImageUrl] = None
+    tensor: Optional[ImageTensor] = None
+    embedding: Optional[AnyEmbedding] = None
+    bytes_: Optional[ImageBytes] = None
 ```
 
 You can use this class directly or extend it to your preference:
@@ -188,7 +188,7 @@ from typing import Optional
 # extending ImageDoc
 class MyImage(ImageDoc):
     image_title: str
-    second_embedding: Optional[AnyEmbedding]
+    second_embedding: Optional[AnyEmbedding] = None
 
 
 image = MyImage(
diff --git a/docs/data_types/text/text.md b/docs/data_types/text/text.md
@@ -101,8 +101,8 @@ To get started and play around with your text data, DocArray provides a predefin
 
 ``` { .python }
 class TextDoc(BaseDoc):
-    text: Optional[str]
-    url: Optional[TextUrl]
-    embedding: Optional[AnyEmbedding]
-    bytes_: Optional[bytes]
+    text: Optional[str] = None
+    url: Optional[TextUrl] = None
+    embedding: Optional[AnyEmbedding] = None
+    bytes_: Optional[bytes] = None
 ```
diff --git a/docs/data_types/video/video.md b/docs/data_types/video/video.md
@@ -188,12 +188,12 @@ To get started and play around with your video data, DocArray provides a predefi
 
 ``` { .python }
 class VideoDoc(BaseDoc):
-    url: Optional[VideoUrl]
+    url: Optional[VideoUrl] = None
     audio: Optional[AudioDoc] = AudioDoc()
-    tensor: Optional[VideoTensor]
-    key_frame_indices: Optional[AnyTensor]
-    embedding: Optional[AnyEmbedding]
-    bytes_: Optional[bytes]
+    tensor: Optional[VideoTensor] = None
+    key_frame_indices: Optional[AnyTensor] = None
+    embedding: Optional[AnyEmbedding] = None
+    bytes_: Optional[bytes] = None
 ```
 
 You can use this class directly or extend it to your preference:
@@ -206,7 +206,7 @@ from docarray.documents import VideoDoc
 
 # extend it
 class MyVideo(VideoDoc):
-    name: Optional[str]
+    name: Optional[str] = None
 
 
 video = MyVideo(
diff --git a/docs/how_to/add_doc_index.md b/docs/how_to/add_doc_index.md
@@ -187,7 +187,7 @@ The values of `self._column_infos` are `_ColumnInfo` dataclasses, which have the
 class _ColumnInfo:
     docarray_type: Type
     db_type: Any
-    n_dim: Optional[int]
+    n_dim: Optional[int] = None
     config: Dict[str, Any]
 ```
 
diff --git a/docs/how_to/multimodal_training_and_serving.md b/docs/how_to/multimodal_training_and_serving.md
@@ -101,7 +101,7 @@ class Tokens(BaseDoc):
 
 ```python
 class Text(BaseText):
-    tokens: Optional[Tokens]
+    tokens: Optional[Tokens] = None
 ```
 
 Notice the [`TorchTensor`][docarray.typing.TorchTensor] type. It is a thin wrapper around `torch.Tensor` that can be used like any other Torch tensor, 
@@ -119,9 +119,9 @@ supported ML framework):
 
 ```python
 class ImageDoc(BaseDoc):
-    url: Optional[ImageUrl]
-    tensor: Optional[TorchTesor]
-    embedding: Optional[TorchTensor]
+    url: Optional[ImageUrl] = None
+    tensor: Optional[TorchTesor] = None
+    embedding: Optional[TorchTensor] = None
 ```
 
 Actually, the `BaseText` above also already includes `tensor`, `url` and `embedding` fields, so we can use those on our
@@ -141,6 +141,7 @@ This will be unnecessary once [this issue](https://github.com/docarray/docarray/
 
 ```python
 from docarray import DocVec
+
 DocVec[Tokens]
 DocVec[TextDoc]
 DocVec[ImageDoc]
diff --git a/docs/user_guide/representing/array.md b/docs/user_guide/representing/array.md
@@ -454,7 +454,7 @@ Both [`DocList`][docarray.array.doc_list.doc_list.DocList] and [`DocVec`][docarr
 
 
     class MyDoc(BaseDoc):
-        nested_doc: Optional[BaseDoc]
+        nested_doc: Optional[BaseDoc] = None
     ```
 
 Using nested optional fields differs slightly between DocList and DocVes, so watch out. But in a nutshell:
@@ -484,7 +484,7 @@ class ImageDoc(BaseDoc):
 
 
 class ArticleDoc(BaseDoc):
-    image: Optional[ImageDoc]
+    image: Optional[ImageDoc] = None
     title: str
 ```
 
diff --git a/tests/documentation/test_docs.py b/tests/documentation/test_docs.py
@@ -4,7 +4,6 @@
 from mktestdocs import grab_code_blocks
 from mktestdocs.__main__ import _executors, check_raw_string
 
-from docarray.utils._internal.pydantic import is_pydantic_v2
 from tests.index.elastic.fixture import start_storage_v8  # noqa: F401
 
 file_to_skip = ['fastAPI', 'jina', 'index', 'first_steps.md']
@@ -64,7 +63,6 @@ def check_md_file(fpath, memory=False, lang="python", keyword_ignore=[]):
     files_to_check.remove(file)
 
 
-@pytest.mark.skipif(is_pydantic_v2, reason="Not working with pydantic v2 for now")
 @pytest.mark.parametrize('fpath', files_to_check, ids=str)
 def test_files_good(fpath):
     check_md_file(fpath=fpath, memory=True, keyword_ignore=['pickle', 'jac'])
diff --git a/tests/documentation/test_docstring.py b/tests/documentation/test_docstring.py
@@ -16,7 +16,6 @@
 import docarray.store
 import docarray.typing
 from docarray.utils import filter, find, map
-from docarray.utils._internal.pydantic import is_pydantic_v2
 
 SUB_MODULE_TO_CHECK = [
     docarray,
@@ -54,7 +53,6 @@ def get_obj_to_check(lib):
     members.extend(get_codeblock_members(obj))
 
 
-@pytest.mark.skipif(is_pydantic_v2, reason="Not working with pydantic v2 for now")
 @pytest.mark.parametrize("obj", members, ids=lambda d: d.__qualname__)
 def test_member(obj):
     check_docstring(obj)
