skillmatcher

Read the equation

This relation defines engine's threshold. Vectors from the provider are L2-normalized, so cosine == dot product. in the source section “skillmatcher”. It specifies the displayed relationship between the named quantities or parameters. Its interpretation depends on the source’s stated variables and conditions; this record does not assign an unprovided physical or cognitive meaning to them.

Terms & definitions

The recovered passage does not supply a separate symbol table. Read the source context for the notation used in this version; familiar letters may carry different meanings in other builds.

How it works

1. Read engine's threshold. Vectors from the provider are L2-normalized, so cosine == dot product. as the quantity being defined or updated by this relation.

2. Substitute the source-defined variables or recorded values and follow the displayed arithmetic and indexing exactly.

3. Use this version’s variable definitions and update order. The same symbol may be assigned a different meaning in another build.

Assumptions & limits

• This source expression was recovered from the pinned code revision. Its presence does not establish that the associated program was built, run, or scientifically validated.

Original context

	"github.com/missionworkforce/missionmatch/internal/modules/matching/engine"
	"github.com/missionworkforce/missionmatch/internal/platform/embeddings"
)

// EmbeddingSkillMatcher implements engine.SkillMatcher using the embedding provider: it embeds the
// required skill name and each candidate skill name and picks the best cosine match at/above the
// engine's threshold. Vectors from the provider are L2-normalized, so cosine == dot product.
//
// This is the semantic ("synonyms / adjacent skills") layer the engine defers to AFTER exact match.
// With the deterministic offline embedder, unrelated skills score near zero, so it never invents a
// false semantic match — exact matching still dominates. Determinism follows from the embedder's.
type EmbeddingSkillMatcher struct {
	embedder embeddings.Embedder
	ctx      context.Context
}

// NewEmbeddingSkillMatcher wraps an embedder as an engine.SkillMatcher.

engine's threshold. Vectors from the provider are L2-normalized, so cosine == dot product.

Related builds

Related mathematical records