Jason Woltje fb3c308efd feat(P4-002): semantic search — pgvector embeddings + search API ...

Add EmbeddingService using OpenAI-compatible embeddings API (supports
text-embedding-3-small, configurable via EMBEDDING_MODEL and
EMBEDDING_API_URL env vars). Wire embedding generation into insight
creation and semantic search endpoint. POST /api/memory/search now
generates a query embedding and performs cosine distance search via
pgvector when OPENAI_API_KEY is configured.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-13 08:49:19 -05:00

..

src

feat(P4-002): semantic search — pgvector embeddings + search API

2026-03-13 08:49:19 -05:00

package.json

feat(P4-001): @mosaic/memory — preference + insight stores

2026-03-13 08:46:40 -05:00

tsconfig.json

fix: switch gateway to ESM + explicit @Inject for tsx compatibility

2026-03-12 20:43:08 -05:00

vitest.config.ts

feat(P0-001): scaffold monorepo structure (#60)

2026-03-13 01:11:46 +00:00