Routecraft

embedding

← All adapters

import { embedding } from '@routecraft/ai'

Generate vector embeddings from text. Requires embeddingPlugin() in your context plugins.

import { embedding } from '@routecraft/ai'

craft()
  .id('embed-document')
  .from(source)
  .enrich(embedding('openai:text-embedding-3-small', {
    using: (ex) => ex.body.content,
  }))
  .to(vectorStore)
// Result replaces the body: { embedding: [0.123, -0.456, ...] }
// (use only() to keep the document, e.g. only((r) => r.embedding, 'embedding'))

// Embed a combination of fields
.enrich(embedding('ollama:nomic-embed-text', {
  using: (ex) => `${ex.body.title} ${ex.body.description}`,
}))

Model ID format: "provider:model-name" (e.g., "huggingface:all-MiniLM-L6-v2", "ollama:nomic-embed-text").

Supported providers: huggingface (local ONNX, no API key), ollama, openai, mock (deterministic test vectors)

Options:

OptionTypeRequiredDescription
using(exchange) => string | string[]YesExtract the text to embed from the exchange

Result shape (replaces the body in bare .enrich() / .to(); pass an aggregator such as only() to merge):

FieldTypeDescription
embeddingnumber[]Vector representation of the input text

Provider credentials are configured once in embeddingPlugin() and shared across all embedding() calls. See Plugins reference.