Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: encode text first when both text and uri are presented #795

Merged
merged 5 commits into from
Aug 5, 2022
Merged

feat: encode text first when both text and uri are presented #795

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
88f71ad
fix: encode text first when both text and uri are presented
ZiniuYu Aug 4, 2022
33e3235
fix: encode text first when both text and uri are presented
ZiniuYu Aug 4, 2022
b65445d
test: add split da test
ZiniuYu Aug 4, 2022
b03d330
fix: typo
ZiniuYu Aug 4, 2022
6220a2a
test: test split da
ZiniuYu Aug 4, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 3 additions & 5 deletions server/clip_server/executors/helper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,12 +73,10 @@ def preproc_text(


def split_img_txt_da(doc: 'Document', img_da: 'DocumentArray', txt_da: 'DocumentArray'):
if doc.uri:
img_da.append(doc)
elif doc.blob or (doc.tensor is not None):
img_da.append(doc)
elif doc.text:
if doc.text:
ZiniuYu marked this conversation as resolved.
Show resolved Hide resolved
txt_da.append(doc)
elif doc.blob or (doc.tensor is not None) or doc.uri:
img_da.append(doc)


def set_rank(docs, _logit_scale=np.exp(4.60517)):
Expand Down
41 changes: 41 additions & 0 deletions tests/test_helper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
import pytest
import numpy as np
from clip_server.executors.helper import numpy_softmax
from clip_server.executors.helper import split_img_txt_da
from docarray import Document, DocumentArray


@pytest.mark.parametrize('shape', [(5, 10), (5, 10, 10)])
Expand All @@ -17,3 +19,42 @@ def test_numpy_softmax(shape, axis):
np_softmax = numpy_softmax(logits, axis=axis)
torch_softmax = torch.from_numpy(logits).softmax(dim=axis).numpy()
np.testing.assert_array_almost_equal(np_softmax, torch_softmax)


@pytest.mark.parametrize(
'inputs',
[
(
DocumentArray(
[
Document(text='hello, world'),
Document(text='goodbye, world'),
Document(
text='hello, world',
uri='https://docarray.jina.ai/_static/favicon.png',
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

also coverage the docs with blob and tensor

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

tensor = [0, 1, 2, 3] or tensor = np.array([0, 1, 2, 3])

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🥹

),
Document(
uri='https://docarray.jina.ai/_static/favicon.png',
),
]
),
(3, 1),
),
(
DocumentArray(
[
Document(text='hello, world'),
Document(uri='https://docarray.jina.ai/_static/favicon.png'),
]
),
(1, 1),
),
],
)
def test_split_img_txt_da(inputs):
txt_da = DocumentArray()
img_da = DocumentArray()
for doc in inputs[0]:
split_img_txt_da(doc, img_da, txt_da)
assert len(txt_da) == inputs[1][0]
assert len(img_da) == inputs[1][1]