Description
Semantic Row Embeddings turn row content into stored vectors with the model and input type recorded alongside each result.
Semantic Row Embeddings is delivered through typed package contracts rather than a surface-specific shortcut. Its primary modules separate the public input or configuration shape from validation, durable state, and the operation that produces the result. That separation lets product surfaces and integrations invoke one implementation while tenant scope and existing domain rules remain in force. Errors stay bounded to the request instead of weakening the underlying data contract.
Selling Points
- Powers meaning-based retrieval and similarity workflows.
- Formats conversation bodies as speaker transcripts when configured.
- Emits explicit deferred signals when providers or budget are unavailable.
- Applies one typed package contract across every supported caller and surface.
- Keeps invalid inputs and unavailable dependencies from silently widening durable state.
User Story
As a researcher, I can retrieve conceptually similar records without relying on exact keywords. In practice, I configure or invoke the capability through a supported surface, supply only the inputs its contract accepts, and receive a result governed by the same rules as every other caller. I can inspect the resulting row, setting, event, or query state and correct my input when validation fails. I walk away with a repeatable workflow rather than a one-off client implementation.
Extension Surface
Configurable: Dotabases select bindings and body format; embedding providers plug in through a local seam.
The configurable rating is evidenced by packages/dotabases/src/behaviors/embedding/index.ts, which defines the supported seam used by trusted callers or configuration. The capability can be composed wherever that contract is available, but its invariants are not replaced by tenant-authored executable code. This keeps extension honest: callers control documented inputs and policy choices while the package owns validation and safety.
Capabilities & Limits
- Capability: Executes the scoped workflow described above through the cited live implementation paths.
- Capability: Preserves typed validation and applicable tenant, schema, lifecycle, or service boundaries.
- Limit: Requires a configured provider and cost allowance. Model consistency must be maintained across stored and query vectors. Semantic Row Embeddings supports the concrete operations described here and composes them with tenant, schema, or lifecycle checks already owned by the package. It does not grant raw database access, make unsupported inputs valid, or assume that optional providers and downstream consumers exist. Callers remain responsible for permissions and meaningful configuration, and product rendering or external delivery stays outside the package unless explicitly stated.
Implementation Map
packages/dotabases/src/behaviors/embedding/index.tsembeddingBehaviorpackages/dotabases/src/contracts/embedder.tsEmbeddingProviderLikepackages/db/src/schema/dotabases.tsdotabaseRows