Skip to main content

Function: embedText()

embedText(opts): Promise<EmbedTextResult>

Defined in: packages/agentos/src/api/embedText.ts:415

Generates embedding vectors for one or more text inputs using a provider-agnostic provider:model string.

Resolves credentials via the standard AgentOS provider pipeline, then dispatches to the appropriate embedding endpoint (OpenAI, Ollama, OpenRouter or Gemini). Returns raw float arrays suitable for vector similarity search, clustering, or any downstream ML pipeline.

Parameters​

opts​

EmbedTextOptions

Embedding options including model, input text(s), and optional provider/key overrides.

Returns​

Promise<EmbedTextResult>

A promise resolving to the embedding vectors, provider metadata, and token usage.

Throws​

When provider resolution fails (missing API key, unknown provider, etc.).

Throws​

When the embedding API returns a non-2xx status.

Example​

import { embedText } from '@framers/agentos';

// Single input
const { embeddings } = await embedText({
  provider: 'openai',
  model: 'text-embedding-3-small',
  input: 'Hello world',
});
console.log(embeddings[0].length); // 1536

// Batch with reduced dimensions
const batch = await embedText({
  provider: 'openai',
  model: 'text-embedding-3-small',
  input: ['Hello', 'World'],
  dimensions: 256,
});
console.log(batch.embeddings.length); // 2
console.log(batch.embeddings[0].length); // 256

See​