Skip to content

fix(import): import sentence_transformers on demand as it's too slow #750

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 1 commit into from
Jul 14, 2025
Merged

fix(import): import sentence_transformers on demand as it's too slow #750

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
20 changes: 7 additions & 13 deletions python/cocoindex/functions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,14 +9,6 @@
from . import llm, op
from .typing import TypeAttr, Vector

# Check if sentence_transformers is available
try:
import sentence_transformers # type: ignore

_SENTENCE_TRANSFORMERS_AVAILABLE = True
except ImportError:
_SENTENCE_TRANSFORMERS_AVAILABLE = False


class ParseJson(op.FunctionSpec):
"""Parse a text into a JSON object."""
Expand Down Expand Up @@ -79,18 +71,19 @@ class SentenceTransformerEmbedExecutor:
"""Executor for SentenceTransformerEmbed."""

spec: SentenceTransformerEmbed
_model: "sentence_transformers.SentenceTransformer"
_model: Any | None = None

def analyze(self, text: Any) -> type:
if not _SENTENCE_TRANSFORMERS_AVAILABLE:
try:
# Only import sentence_transformers locally when it's needed, as its import is very slow.
import sentence_transformers # pylint: disable=import-outside-toplevel
except ImportError as e:
raise ImportError(
"sentence_transformers is required for SentenceTransformerEmbed function. "
"Install it with one of these commands:\n"
" pip install 'cocoindex[embeddings]'\n"
" pip install sentence-transformers"
)

import sentence_transformers # pylint: disable=import-outside-toplevel
) from e

args = self.spec.args or {}
self._model = sentence_transformers.SentenceTransformer(self.spec.model, **args)
Expand All @@ -102,5 +95,6 @@ def analyze(self, text: Any) -> type:
return result

def __call__(self, text: str) -> NDArray[np.float32]:
assert self._model is not None
result: NDArray[np.float32] = self._model.encode(text, convert_to_numpy=True)
return result
Loading