Background
v0.4 PPA `_stage2_retrieve()` uses a placeholder cosine over token-count vectors. The persona_triples schema already has an `embedding BLOB` column reserved.
What's needed
- Lazily compute bge-m3 1024-dim embeddings for new triples on insert
- Store as BLOB in the existing column
- Update `_stage2_retrieve()` to use the BLOB embeddings + numpy cosine
Why this matters
Token-count cosine is good enough to demo PPA but won't match the paper's reported C-Score gains. Real embeddings should close most of that gap.
Acceptance criteria
Related
This becomes moot if #5 (Mem0 integration) lands first — Mem0 handles embedding + retrieval. If we go straight to Mem0, close this issue.
Estimated effort
~1 day if we keep the SQLite path; ~0 if we jump to Mem0.
Background
v0.4 PPA `_stage2_retrieve()` uses a placeholder cosine over token-count vectors. The persona_triples schema already has an `embedding BLOB` column reserved.
What's needed
Why this matters
Token-count cosine is good enough to demo PPA but won't match the paper's reported C-Score gains. Real embeddings should close most of that gap.
Acceptance criteria
Related
This becomes moot if #5 (Mem0 integration) lands first — Mem0 handles embedding + retrieval. If we go straight to Mem0, close this issue.
Estimated effort
~1 day if we keep the SQLite path; ~0 if we jump to Mem0.