Make the embedding model swappable via env for A/B testing

Trialing Qwen3-Embedding-0.6B (1024-dim, instruct-prefixed queries)
against nomic required code changes at every hardcoded seam; now it's a
config flip plus a reembed_embeddings run.

- EMBEDDING_DIM env (default 768) replaces every hardcoded dim check:
  daily summary / calendar / search / location DAOs, Ollama batch
  validation, reembed_embeddings
- entities gains the dim guard it never had — a wrong-dim vector
  silently kills dedup/recall (cosine over mismatched lengths is 0),
  so store None and warn instead
- embed_query / embed_document split with EMBED_QUERY_PREFIX /
  EMBED_DOCUMENT_PREFIX (literal \n expanded): retrieval models treat
  the two sides differently — nomic wants search_query:/search_document:,
  Qwen3 wants Instruct:...\nQuery: on queries only. All query-side
  call sites and all corpus writers now declare their side.
- document the contract in CLAUDE.md: change the model or any of these
  vars → re-run reembed_embeddings or search is garbage

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Cameron Cordes
2026-06-11 21:40:40 -04:00
parent b1493f5aca
commit efd05db523
12 changed files with 159 additions and 67 deletions
+5 -4
View File
@@ -216,11 +216,12 @@ impl LocationHistoryDao for SqliteLocationHistoryDao {
// Validate embedding dimensions if provided (rare for location data)
if let Some(ref emb) = location.embedding
&& emb.len() != 768
&& emb.len() != crate::ai::embedding_dim()
{
return Err(anyhow::anyhow!(
"Invalid embedding dimensions: {} (expected 768)",
emb.len()
"Invalid embedding dimensions: {} (expected {})",
emb.len(),
crate::ai::embedding_dim()
));
}
@@ -292,7 +293,7 @@ impl LocationHistoryDao for SqliteLocationHistoryDao {
for location in locations {
// Validate embedding if provided (rare)
if let Some(ref emb) = location.embedding
&& emb.len() != 768
&& emb.len() != crate::ai::embedding_dim()
{
log::warn!(
"Skipping location with invalid embedding dimensions: {}",