Skip to main content
The runEmbedding() method generates text embeddings using OpenAI, Google, or Amazon Bedrock embedding models. Like runLocal(), embedding requests go directly to the provider and traces are sent to Tracia asynchronously in the background. 
import { Tracia } from 'tracia';

const tracia = new Tracia({ apiKey: process.env.TRACIA_API_KEY });

const result = await tracia.runEmbedding({
  model: 'text-embedding-3-small',
  input: 'What is the meaning of life?',
});

console.log(result.embeddings[0].values.length); // 1536

​
How It Works

When you call runEmbedding(), the SDK:
  1. Calls the provider directly - Your embedding request goes straight to OpenAI, Google, or Amazon Bedrock. Tracia is not in the request path.
  2. Sends the trace asynchronously - After the provider responds, trace data is sent to Tracia in the background. This is non-blocking and adds zero latency to your application.
Embedding spans appear in the Tracia dashboard with the EMBEDDING span kind, so you can track embedding usage, latency, and costs alongside your LLM completions.

​
Quick Examples

const result = await tracia.runEmbedding({
  model: 'text-embedding-3-small',
  input: 'Hello world',
});

console.log(result.embeddings[0].values.length); // 1536

​
Available Pages

Basic Usage

Single and batch embeddings, dimensions, sessions

Supported Models

OpenAI, Google, and Amazon Bedrock embedding models

​
Types

​
RunEmbeddingInput

interface RunEmbeddingInput {
  // Required
  input: string | string[];  // Text(s) to embed
  model: string;             // Embedding model name

  // Optional
  provider?: LLMProvider;    // Provider override (auto-detected from model)
  providerApiKey?: string;   // Provider API key override
  dimensions?: number;       // Dimension override (model-dependent)
  timeoutMs?: number;        // Request timeout in milliseconds

  // Span options
  sendTrace?: boolean;       // Send trace to Tracia (default: true)
  spanId?: string;           // Custom span ID
  tags?: string[];           // Tags for the span
  userId?: string;           // User ID for the span
  sessionId?: string;        // Session ID for the span
  traceId?: string;          // Group related spans together
  parentSpanId?: string;     // Link to parent span
}

​
RunEmbeddingResult

interface RunEmbeddingResult {
  embeddings: EmbeddingVector[];  // The generated embeddings
  spanId: string;                 // Unique span ID
  traceId: string;                // Trace ID for grouping
  latencyMs: number;              // Request latency in milliseconds
  usage: EmbeddingUsage;          // Token usage
  cost: number | null;            // Always null (cost calculated server-side)
  provider: LLMProvider;          // The provider used
  model: string;                  // The model used
}

​
EmbeddingVector

interface EmbeddingVector {
  values: number[];  // The embedding float values
  index: number;     // Index in the input array
}

​
EmbeddingUsage

interface EmbeddingUsage {
  totalTokens: number;  // Total tokens consumed
}