Skip to content

fix(rag): correct voyage-3-lite dimension from 1024 to 512 in manifest #155

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
cipher813 merged 1 commit into from
May 5, 2026
Merged

fix(rag): correct voyage-3-lite dimension from 1024 to 512 in manifest #155

Show file tree
Hide file tree
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
5 changes: 3 additions & 2 deletions rag/pipelines/emit_manifest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,10 +41,11 @@

logger = logging.getLogger(__name__)

# Hardcoded; ``rag.embeddings.embed_*`` defaults to voyage-3-lite (1024d).
# Hardcoded; ``rag.embeddings.embed_*`` defaults to voyage-3-lite (512d,
# matches the ``embedding vector(512)`` column in ``rag/schema.sql``).
# Surfaced in the manifest so consumers don't have to re-derive it.
_EMBEDDING_MODEL = "voyage-3-lite"
_EMBEDDING_DIMENSION = 1024
_EMBEDDING_DIMENSION = 512


def _by_source() -> dict[str, dict[str, int]]:
Expand Down
4 changes: 3 additions & 1 deletion tests/test_emit_manifest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,7 +86,9 @@ def test_coverage_percentiles(manifest):


def test_embedding_metadata(manifest):
assert manifest["embedding"] == {"model": "voyage-3-lite", "dimension": 1024}
# voyage-3-lite is 512d — matches `embedding vector(512)` in the lib's
# rag/schema.sql. pgvector enforces dim on INSERT.
assert manifest["embedding"] == {"model": "voyage-3-lite", "dimension": 512}


def test_ingestion_overall_picks_max(manifest):
Expand Down
Loading