Skip to content

feat(embeddings): use stdlib array type for improved performance #2060

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
merged 4 commits into from
Feb 6, 2025
Merged

feat(embeddings): use stdlib array type for improved performance #2060

Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
53c27b9
Use builtin array to convert f32 bytes to float list
tonybaloney Jan 28, 2025
8c8c1c0
adjust logic when you don't have numpy and haven't overriden the enco…
tonybaloney Jan 28, 2025
966c4f9
adjust conditional flow
tonybaloney Jan 28, 2025
dc81e24
Merge remote-tracking branch 'upstream/next' into array
tonybaloney Feb 1, 2025
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
29 changes: 17 additions & 12 deletions src/openai/resources/embeddings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@

from __future__ import annotations

import array
import base64
from typing import List, Union, Iterable, cast
from typing_extensions import Literal
Expand Down Expand Up @@ -102,7 +103,7 @@ def create(
"dimensions": dimensions,
"encoding_format": encoding_format,
}
if not is_given(encoding_format) and has_numpy():
if not is_given(encoding_format):
params["encoding_format"] = "base64"

def parser(obj: CreateEmbeddingResponse) -> CreateEmbeddingResponse:
Expand All @@ -113,12 +114,14 @@ def parser(obj: CreateEmbeddingResponse) -> CreateEmbeddingResponse:
for embedding in obj.data:
data = cast(object, embedding.embedding)
if not isinstance(data, str):
# numpy is not installed / base64 optimisation isn't enabled for this model yet
continue

embedding.embedding = np.frombuffer( # type: ignore[no-untyped-call]
base64.b64decode(data), dtype="float32"
).tolist()
if not has_numpy():
# use array for base64 optimisation
embedding.embedding = array.array("f", base64.b64decode(data)).tolist()
else:
embedding.embedding = np.frombuffer( # type: ignore[no-untyped-call]
base64.b64decode(data), dtype="float32"
).tolist()

return obj

Expand Down Expand Up @@ -215,7 +218,7 @@ async def create(
"dimensions": dimensions,
"encoding_format": encoding_format,
}
if not is_given(encoding_format) and has_numpy():
if not is_given(encoding_format):
params["encoding_format"] = "base64"

def parser(obj: CreateEmbeddingResponse) -> CreateEmbeddingResponse:
Expand All @@ -226,12 +229,14 @@ def parser(obj: CreateEmbeddingResponse) -> CreateEmbeddingResponse:
for embedding in obj.data:
data = cast(object, embedding.embedding)
if not isinstance(data, str):
# numpy is not installed / base64 optimisation isn't enabled for this model yet
continue

embedding.embedding = np.frombuffer( # type: ignore[no-untyped-call]
base64.b64decode(data), dtype="float32"
).tolist()
if not has_numpy():
# use array for base64 optimisation
embedding.embedding = array.array("f", base64.b64decode(data)).tolist()
else:
embedding.embedding = np.frombuffer( # type: ignore[no-untyped-call]
base64.b64decode(data), dtype="float32"
).tolist()

return obj

Expand Down
Loading