Docs and articles
R-72
Technology
Tessera DB Tutorial: Set Up Auto-Embedding for Semantic Search
Configure an embedding provider once. Every record with text properties gets indexed for vector search automatically — no separate pipeline.
PAR2 Labs
August 29, 2026
2 min
Auto-embedding is the difference between "we support vector search" and "every text property is searchable by meaning, by default." You configure a provider once, and Tessera does the rest on every write.
01
Step 1: Start with a stand-in embedder
For local development and tests, Tessera can use a deterministic stand-in embedder that needs no external service. It produces consistent vectors for identical inputs but no real semantic structure — fine for exercising the pipeline end to end, not for judging retrieval quality.
02
Step 2: Wire in a real embedder
For real semantic search, point Tessera at an embedding model — a hosted provider or a local model. Any function that turns text into a vector will do.
Dimension consistency
01
The vectors your provider returns must match the vector width Tessera is configured for. Set that before enabling the embedder; vectors of the wrong length are skipped with a warning.
Any function that turns text into a vector will do.
03
Step 3: Insert and watch it index
From here, every insert with a text property auto-embeds. Import an article with a title and body and the body is embedded the moment the row lands — searchable immediately, with no separate step.
04
Step 4: Search by meaning
Search with plain text: the server embeds your query the same way it embedded your data and returns the nearest records. You'll get an article back about international money transfers even if those exact words never appear in it — that's the embedding doing its job. (This vector-from-text path requires a configured embedding provider.)
Key Takeaways
01
Started with a deterministic stand-in embedder to exercise the pipeline without an external service.
02
Pointed Tessera at a real embedding model, with its vector width matching the width Tessera is configured for.
03
Inserted records whose text properties were embedded the moment they landed.
04
Searched by meaning with plain text, embedded by the server the same way as the data.
PAR2 Labs · Technology
Talk to us