Skip to content

refactor: hnswlib performance #1727

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

Merged
JoanFM merged 15 commits into from
Jul 31, 2023
Merged

refactor: hnswlib performance #1727

Changes from 2 commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
9aebf2e
refactor: hnswlib performance
Jul 26, 2023
02849c4
Merge branch 'main' of https://github.com/docarray/docarray into refa…
Jul 26, 2023
3f56d44
fix: reconstruct on filter
Jul 27, 2023
f8bb5f9
fix: reconstruct from proper type
Jul 27, 2023
ae33fe6
fix: get the proper embedding back
Jul 27, 2023
a91e23e
chore: avoid extra debugging (#1730)
Jul 27, 2023
fa9b9ce
Merge branch 'main' of https://github.com/docarray/docarray into refa…
Jul 27, 2023
79b0fea
Merge branch 'get-current-count-hnswlib' of https://github.com/docarr…
Jul 27, 2023
58ee168
chore: add comment to take over later
Jul 28, 2023
83e55f5
test: refactor hnswlib test subindex
Jul 28, 2023
281cf7e
Merge branch 'test-refactor' of https://github.com/docarray/docarray …
Jul 28, 2023
2ea5804
chore: fix test
Jul 28, 2023
1c8337e
Merge branch 'main' of https://github.com/docarray/docarray into refa…
Jul 28, 2023
8c0bf6c
chore: apply optim
Jul 28, 2023
c062c8c
Merge branch 'main' into refactor-hnswlib-performance
Jul 30, 2023
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
47 changes: 28 additions & 19 deletions tests/index/hnswlib/test_subindex.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,20 +27,7 @@ class MyDoc(BaseDoc):


@pytest.fixture(scope='session')
def index():
index = HnswDocumentIndex[MyDoc](work_dir='./tmp')
return index


def test_subindex_init(index):
assert isinstance(index._subindices['docs'], HnswDocumentIndex)
assert isinstance(index._subindices['list_docs'], HnswDocumentIndex)
assert isinstance(
index._subindices['list_docs']._subindices['docs'], HnswDocumentIndex
)


def test_subindex_index(index):
def index_docs():
my_docs = [
MyDoc(
id=f'{i}',
Expand Down Expand Up @@ -82,15 +69,31 @@ def test_subindex_index(index):
)
for i in range(5)
]
return my_docs


def test_subindex_init(tmpdir, index_docs):
index = HnswDocumentIndex[MyDoc](work_dir=str(tmpdir))
index.index(index_docs)
assert isinstance(index._subindices['docs'], HnswDocumentIndex)
assert isinstance(index._subindices['list_docs'], HnswDocumentIndex)
assert isinstance(
index._subindices['list_docs']._subindices['docs'], HnswDocumentIndex
)


index.index(my_docs)
def test_subindex_index(tmpdir, index_docs):
index = HnswDocumentIndex[MyDoc](work_dir=str(tmpdir))
index.index(index_docs)
assert index.num_docs() == 5
assert index._subindices['docs'].num_docs() == 25
assert index._subindices['list_docs'].num_docs() == 25
assert index._subindices['list_docs']._subindices['docs'].num_docs() == 125


def test_subindex_get(index):
def test_subindex_get(tmpdir, index_docs):
index = HnswDocumentIndex[MyDoc](work_dir=str(tmpdir))
index.index(index_docs)
doc = index['1']
assert type(doc) == MyDoc
assert doc.id == '1'
Expand All @@ -116,7 +119,9 @@ def test_subindex_get(index):
assert np.allclose(doc.my_tens, np.ones(30) * 2)


def test_find_subindex(index):
def test_find_subindex(tmpdir, index_docs):
index = HnswDocumentIndex[MyDoc](work_dir=str(tmpdir))
index.index(index_docs)
# root level
query = np.ones((30,))
with pytest.raises(ValueError):
Expand Down Expand Up @@ -148,15 +153,19 @@ def test_find_subindex(index):
assert root_doc.id == f'{doc.id.split("-")[2]}'


def test_subindex_del(index):
def test_subindex_del(tmpdir, index_docs):
index = HnswDocumentIndex[MyDoc](work_dir=str(tmpdir))
index.index(index_docs)
del index['0']
assert index.num_docs() == 4
assert index._subindices['docs'].num_docs() == 20
assert index._subindices['list_docs'].num_docs() == 20
assert index._subindices['list_docs']._subindices['docs'].num_docs() == 100


def test_subindex_contain(index):
def test_subindex_contain(tmpdir, index_docs):
index = HnswDocumentIndex[MyDoc](work_dir=str(tmpdir))
index.index(index_docs)
# Checks for individual simple_docs within list_docs
for i in range(4):
doc = index[f'{i + 1}']
Expand Down