Skip to main content

Interface: EmbedTextResult

Defined in: packages/agentos/src/api/embedText.ts:107

The result returned by embedText.

Example​

const { embeddings, usage } = await embedText({
  provider: 'openai',
  model: 'text-embedding-3-small',
  input: ['Hello', 'World'],
});
console.log(embeddings.length); // 2
console.log(embeddings[0].length); // e.g. 1536

Properties​

embeddings​

embeddings: number[][]

Defined in: packages/agentos/src/api/embedText.ts:113

One embedding vector per input string. Each vector is a plain number[] of floats whose dimensionality depends on the model (and the optional dimensions parameter).

model​

model: string

Defined in: packages/agentos/src/api/embedText.ts:116

Model identifier reported by the provider (may differ from the requested model).

provider​

provider: string

Defined in: packages/agentos/src/api/embedText.ts:119

Provider identifier used for the run.

usage​

usage: object

Defined in: packages/agentos/src/api/embedText.ts:126

Token usage for the embedding request. Most embedding APIs only report prompt tokens (the input); completion tokens are typically zero.

costUSD?​

optional costUSD: number

Cost in USD when the provider prices the call itself (Gemini embedding models with a catalog price). Absent when the provider reports none.

promptTokens​

promptTokens: number

Number of tokens consumed by the input text(s).

totalTokens​

totalTokens: number

Sum of prompt and any other tokens (usually equal to promptTokens).