arize-otel

What it is and what it does

arize-otel is a convenience wrapper around OpenTelemetry that simplifies setup for tracing LLM applications and sending traces to Arize or custom OTLP endpoints. It provides a high-level `register()` function that returns a configured TracerProvider, handling authentication, endpoint configuration, span batching, and Arize-specific headers in one call. The package can automatically discover and instrument installed OpenInference instrumentors (for libraries like OpenAI, LangChain, etc.) or work with custom span processors that enrich traces before export.

The package is designed as a lightweight convenience layer—you can use raw OpenTelemetry primitives instead if needed, but arize-otel eliminates boilerplate for the common case of instrumenting an LLM application and routing traces to Arize. It supports both Arize's standard and European endpoints, custom GRPC or HTTP collectors, environment variable configuration, and options to disable batch processing or log spans to console for debugging.

Use it for:

• Instrument an OpenAI or LangChain application and send traces to Arize for LLM observability without writing OTEL boilerplate.
• Route traces from a single application to multiple Arize spaces or projects dynamically using register_with_routing.
• Send traces to a custom OTLP collector (on-premise or third-party) by specifying a custom endpoint and transport type.
• Debug trace collection during development by enabling console logging and disabling batch processing.
• Enrich spans with custom processors before export by passing span_processors to register().
• Set up tracing via environment variables instead of code for containerized or cloud-deployed LLM applications.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Wraps OpenTelemetry with Arize-aware defaults to instrument and send LLM application traces to Arize or custom OTLP endpoints.

Yes. The package is actively maintained, has no known vulnerabilities, low install friction, and a permissive license. It genuinely simplifies OpenTelemetry setup for LLM tracing to Arize—a common workflow. Install it if you're already using Arize or a compatible OTLP collector and want to avoid writing OTEL configuration boilerplate; skip it if you need raw OpenTelemetry control or are not sending traces to Arize.

Install

arize-otel on PyPI

pip install arize-otel

uv add arize-otel

poetry add arize-otel

Installing arize-otel

Before you install

Low install friction: pure Python wheel with five runtime dependencies on OpenTelemetry and OpenInference packages. Actively maintained with a release within the last 79 days and no known vulnerabilities.

License in practice

BSD permissive license allows use in commercial and proprietary projects with minimal restrictions.

Quickstart

pip install arize-otel

from arize.otel import register

tracer_provider = register(
    space_id="your-arize-space-id",
    api_key="your-arize-api-key",
    project_name="your-model-id",
    auto_instrument=True,
)

Verify before relying

• Whether auto_instrument=True successfully discovers all installed OpenInference instrumentors in practice
• Performance overhead of batch span processing on high-volume tracing workloads
• Compatibility with non-Arize OTLP collectors beyond the documented custom endpoint pattern

Package facts

Evidence: arize_otel-0.13.0-py3-none-any.whl

Keywords: Explainability, Monitoring, Observability, Tracing

Tags

More Python Modules packages