Skip to content

fix: validate embedding vector dimensions before vector store insertion (ref #2265) #2378

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

Open
hanhan761 wants to merge 2 commits into
base: main
Choose a base branch
from
+8 −1
Open

fix: validate embedding vector dimensions before vector store insertion (ref #2265) #2378

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5e1a95a
fix: bump nltk lower bound to 3.9.3 to address CVE-2025-14009 (fixes …
May 30, 2026
cecdf8a
fix: validate embedding vector dimensions before vector store inserti…
May 30, 2026
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 packages/graphrag/graphrag/index/operations/embed_text/embed_text.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,6 +133,13 @@ async def _flush_embedding_buffer(
)
)

if documents:
dims = {len(d.vector) for d in documents}
if len(dims) > 1:
msg = f"Inconsistent embedding dimensions: {dims}. Check that your embedding model returns consistent vector sizes."
callbacks.error(msg)
raise ValueError(msg)

vector_store.load_documents(documents)

if skipped > 0:
Expand Down
2 changes: 1 addition & 1 deletion packages/graphrag/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ dependencies = [
"graspologic-native~=1.2",
"json-repair~=0.30",
"networkx~=3.4",
"nltk~=3.9",
"nltk>=3.9.3",
"numpy~=2.1",
"pandas~=2.3",
"pyarrow~=22.0",
Expand Down