Hugging Face

​

Setup

pnpm add braintrust @huggingface/inference

npm install braintrust @huggingface/inference

BRAINTRUST_API_KEY=<your-braintrust-api-key>
HUGGINGFACE_API_KEY=<your-huggingface-token>

# For organizations on the EU data plane, use https://api-eu.braintrust.dev
# For self-hosted deployments, use your data plane URL
# BRAINTRUST_API_URL=<your-braintrust-api-url>

​

Auto-instrumentation

import { initLogger } from "braintrust";
import * as huggingFace from "@huggingface/inference";

initLogger({
  projectName: "huggingface-example",
  apiKey: process.env.BRAINTRUST_API_KEY,
});

const client = new huggingFace.InferenceClient(
  process.env.HUGGINGFACE_API_KEY,
);

const response = await client.chatCompletion({
  model: "meta-llama/Llama-3.1-8B-Instruct",
  provider: "featherless-ai",
  messages: [
    {
      role: "user",
      content: "Reply with exactly OK.",
    },
  ],
  max_tokens: 16,
  temperature: 0,
});

console.log(response.choices?.[0]?.message?.content);

node --import braintrust/hook.mjs trace-huggingface-auto.js

​

Manual instrumentation

import { initLogger, wrapHuggingFace } from "braintrust";
import * as huggingFace from "@huggingface/inference";

initLogger({
  projectName: "huggingface-example",
  apiKey: process.env.BRAINTRUST_API_KEY,
});

const hf = wrapHuggingFace(huggingFace);
const client = new hf.InferenceClient(process.env.HUGGINGFACE_API_KEY);

const embedding = await client.featureExtraction({
  inputs: "Paris France",
  model: "thenlper/gte-large",
  provider: "hf-inference",
});

console.log(embedding);

• The module import itself, including InferenceClient, InferenceClientEndpoint, HfInference, and HfInferenceEndpoint.
• An already-constructed client instance.

​

What Braintrust traces

• Chat completions, including streaming chat with first-token timing.
• Text generation, including streaming text generation with first-token timing.
• Feature extraction, summarized as embedding count, length, and batch count.
• Token usage, including prompt, completion, and total tokens.
• Request metadata, including model, provider, and selected request parameters.
• Response identifiers, including ID, model, object, created, and finish reason.
• Routed endpoint URL when calling client.endpoint(...).

​

Resources

• Hugging Face Inference SDK
• Hugging Face Inference Providers
• Trace LLM calls