Monitor HuggingFace using OpenTelemetry

Shield360 uses OpenTelemetry Auto-Instrumentation to help you monitor LLM applications built using models from HuggingFace. This includes tracking performance, token usage, costs, and how users interact with the application.

Auto-instrumentation means you don’t have to set up monitoring manually for different LLMs, frameworks, or databases. By simply adding Shield360 in your application, all the necessary monitoring configurations are automatically set up.

The integration is compatible with

• HuggingFace Transformers Python SDK client >= 4.48.0
• HuggingFace Inference TypeScript SDK (@huggingface/inference) >= 2.0.0
• Transformers.js (@huggingface/transformers >= 3 or @xenova/transformers) for local inference

Supported APIs

SDK	Instrumented surface	Inference type
Python	TextGenerationPipeline.__call__	Local (transformers)
TypeScript	@huggingface/inference chat completions	Remote (Inference API)
TypeScript	Transformers.js pipeline calls (@huggingface/transformers / @xenova/transformers)	Local

Local text-generation is reported as the chat operation to match the Python SDK. Other local Transformers.js pipelines (summarization, translation, fill-mask, question-answering, classification) are reported as text_completion, and feature-extraction / sentence-similarity as embeddings.

Prerequisites

• Install the HuggingFace SDK yourself. Shield360 does not bundle it as a dependency.
• For TypeScript, call shield360.init() before the HuggingFace module is first loaded so OpenTelemetry can hook into the SDK at runtime.

TypeScript example (local Transformers.js)

import shield360 from "shield360";

shield360.init({ otlpEndpoint: "YOUR_OTEL_ENDPOINT" });

import { pipeline } from "@huggingface/transformers";

const generator = await pipeline("text-generation", "Xenova/distilgpt2");
const output = await generator("OpenTelemetry makes observability", {
  max_new_tokens: 32,
  temperature: 0.7,
});

Configuration

Option	Behavior
captureMessageContent	Gates gen_ai.input.messages / gen_ai.output.messages on spans and in events
disableEvents	Suppresses all inference events
disableMetrics	Global - metrics instruments are not set up
disabledInstrumentors: ['transformers']	Disables the local Transformers.js instrumentation
disabledInstrumentors: ['huggingface']	Disables the remote Inference API instrumentation

Note

On the Python SDK, inference events are only emitted when capture_message_content is enabled. On the TypeScript SDK, inference events are emitted when disableEvents is false, regardless of captureMessageContent (message fields within the event are still gated by content capture).

Get started

Install Shield360

Open your command line or terminal and run:

Python

pip install shield360

Typescript

npm install shield360
# Remote Inference API
npm install @huggingface/inference
# or local inference with Transformers.js
npm install @huggingface/transformers

The older @xenova/transformers package is also supported for local inference.

Initialize Shield360 in your Application

Python

Zero Code Instrumentation

Perfect for existing applications - no code modifications needed:

Via CLI Arguments

# Configure via CLI arguments
shield360-instrument \
  --service-name my-ai-app \
  --environment production \
  --otlp-endpoint YOUR_OTEL_ENDPOINT \
  python your_app.py

Via Environment Variables

# Configure via environment variables
export OTEL_SERVICE_NAME=my-ai-app
export OTEL_DEPLOYMENT_ENVIRONMENT=production
export OTEL_EXPORTER_OTLP_ENDPOINT=YOUR_OTEL_ENDPOINT

# Run with zero code changes
shield360-instrument python your_app.py

Note

Perfect for: Legacy applications, production systems where code changes need approval, quick testing, or when you want to add observability without touching existing code.

One-Line Instrumentation

Via Function Parameters

import shield360

shield360.init(otlp_endpoint="YOUR_OTEL_ENDPOINT")

Via Environment Variables

Add the following two lines to your application code:

import shield360

shield360.init()

Then, configure the your OTLP endpoint using environment variable:

export OTEL_EXPORTER_OTLP_ENDPOINT=YOUR_OTEL_ENDPOINT

Typescript

One-Line Instrumentation (SDK)

Via Function Parameters

import shield360 from "shield360"

shield360.init({ otlpEndpoint: "YOUR_OTEL_ENDPOINT" })

Via Environment Variables

Add the following two lines to your application code:

import shield360 from "shield360"

shield360.init()

Then, configure the your OTLP endpoint using environment variable:

export OTEL_EXPORTER_OTLP_ENDPOINT=YOUR_OTEL_ENDPOINT

Replace: YOUR_OTEL_ENDPOINT with the URL of your OpenTelemetry backend, such as http://127.0.0.1:4318 if you are using Shield360 and a local OTel Collector.

To send metrics and traces to other Observability tools, refer to the supported destinations.

For more advanced configurations and application use cases, visit the SDK configuration reference or TypeScript SDK reference.

---

Quickstart: LLM Observability

Production-ready AI monitoring setup in 2 simple steps with zero code changes

Configuration

Configure the Shield360 SDK according to you requirements.

Destinations

Send telemetry to Datadog, Grafana, New Relic, and other observability stacks