Embeddings

Model-Agnostic Approach

MIF stores embedding metadata, not raw vectors:

embedding:
  model: text-embedding-3-small
  modelVersion: "2024-01"
  dimensions: 1536
  sourceText: "The text that was embedded"
  normalized: true

This allows:

• Re-embedding on import with different models
• Smaller file sizes
• Model migration without data loss

Optional Vector Storage

For providers that need vector portability:

External Reference:

embedding:
  model: text-embedding-3-small
  sourceText: "..."
  vectorUri: "urn:mif:vector:550e8400-e29b-41d4-a716-446655440000"

JSON-LD with external vector URI:

"embedding": {
  "model": "text-embedding-3-small",
  "sourceText": "...",
  "vectorUri": "urn:mif:vector:550e8400-e29b-41d4-a716-446655440000"
}