fix(rag): correct voyage-3-lite dimension from 1024 to 512 in manifest#155
Merged
Conversation
Initial PR commit followed the (now-corrected) embeddings.py docstring and reported `embedding.dimension = 1024`. The schema declares `vector(512)` and pgvector enforces dim on INSERT — the production column has to be 512 for ingestion to be working. voyage-3-lite is 512-d. Companion fix to alpha-engine-lib PR #17 which updates the docstring. Tests: 8/8 (test_embedding_metadata updated to assert 512). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Follow-up to PR #154 (already merged). The manifest emitter shipped with
_EMBEDDING_DIMENSION = 1024, taking the alpha-engine-libembeddings.pydocstring at face value. The docstring was wrong:schema.sql:31declaresembedding vector(512)and pgvector enforces dimension on INSERT, so the production column is 512 (the system has been ingesting documents successfully for weeks).Companion fix: alpha-engine-lib PR #17 corrects the docstring.
Changes
rag/pipelines/emit_manifest.py—_EMBEDDING_DIMENSION1024 → 512, comment updated to point at the schema as the source of truthtests/test_emit_manifest.py—test_embedding_metadataasserts 512 with a comment explaining the pgvector enforcementWhy a separate PR
PR #154 was squash-merged before this fix landed.
Test plan
pytest tests/test_emit_manifest.py -q— 8/8 passs3://alpha-engine-research/rag/manifest/latest.jsonwithembedding.dimension: 512🤖 Generated with Claude Code