Skip to content

🐛 normalise vectors after embedding when texts are split #267

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
aitor-perez-epfl merged 1 commit into from
Dec 3, 2025
Merged

🐛 normalise vectors after embedding when texts are split #267

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
7 changes: 7 additions & 0 deletions graphai/core/embedding/embedding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -236,6 +236,7 @@ def _get_model_output(self, model, text):
def _embed(self, model, text, force_split):
text_too_large = False
result = self._get_model_output(model, text)

if result is None:
if force_split:
model_max_tokens = self._get_model_max_tokens(model)
Expand All @@ -251,6 +252,12 @@ def _embed(self, model, text, force_split):
result = results.sum(axis=0).flatten()
else:
text_too_large = True

# Normalise for all vectors to have unit length
norm = np.linalg.norm(result)
if norm > 0:
result = result / norm

return result, text_too_large

def embed(self, text, model_type='all-MiniLM-L12-v2', force_split=True):
Expand Down