---
id: opentelemetry-instrumentation-langchain
version: "0.62.3"
license: Apache-2.0
license_treatment: permissive
maintenance: active
---

# opentelemetry-instrumentation-langchain — OpenTelemetry Langchain instrumentation

License: permissive · Maintenance: active · Downloads: 6.6M/mo

## What it is and what it does

This package integrates Langchain with OpenTelemetry to automatically trace LLM application execution. When enabled, it captures prompts, completions, and embeddings as attributes on OpenTelemetry spans, giving you visibility into how your Langchain-based application is behaving at runtime.

The instrumentation works by hooking into Langchain's execution flow and emitting span data to your configured OpenTelemetry exporter. By default it logs all content for debugging; you can disable this via the TRACELOOP_TRACE_CONTENT environment variable if you need to reduce trace size or protect sensitive user data. The package depends on the core OpenTelemetry API and instrumentation framework, plus semantic convention libraries for AI workloads.

Use it for:

- Debug Langchain chains and agents by inspecting prompts and completions in your tracing backend.
- Monitor LLM application performance and latency across distributed systems using OpenTelemetry exporters.
- Audit and log all prompts and model outputs for compliance or quality evaluation.
- Correlate LLM traces with other application traces for end-to-end observability.
- Reduce trace payload size by disabling content logging in production while keeping structural metrics.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Adds distributed tracing to Langchain LLM applications via OpenTelemetry, capturing prompts, completions, and embeddings as span attributes for visibility and debugging.

Yes, if you are building Langchain applications and already use or plan to use OpenTelemetry for observability. The package is actively maintained, has no known vulnerabilities, and integrates cleanly with the OpenTelemetry ecosystem. Install it only if you have an OpenTelemetry collector or exporter configured to receive the traces; the instrumentation alone produces no output.

## Install

pip install opentelemetry-instrumentation-langchain
uv add opentelemetry-instrumentation-langchain
poetry add opentelemetry-instrumentation-langchain

## Installing opentelemetry-instrumentation-langchain

Before you install: Low install friction with four runtime dependencies all from the OpenTelemetry ecosystem. The package is actively maintained with a recent release and no known vulnerabilities.

License in practice: Licensed under Apache-2.0 (permissive), allowing use in commercial and private projects with minimal restrictions beyond attribution.

Quickstart:

pip install opentelemetry-instrumentation-langchain

from opentelemetry.instrumentation.langchain import LangchainInstrumentor

LangchainInstrumentor().instrument()

Requires Python 3.10 or later; requires an OpenTelemetry collector or exporter to be configured separately to actually receive the traces.

Verify before relying:

- Whether the package supports all Langchain versions or has specific version constraints beyond what the fact sheet shows.
- Performance overhead of instrumentation on large-scale LLM applications.
- Whether TRACELOOP_TRACE_CONTENT environment variable fully disables all sensitive data logging or only the primary content fields.

## Package facts

- License: Apache-2.0 (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 6.6M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

langchain tracing opentelemetry, llm application observability, langchain instrumentation, distributed tracing for llm, langchain span logging, opentelemetry langchain, llm prompt tracing, llm-observability, distributed-tracing, langchain

[View on SkillFed](https://skillfed.io/packages/opentelemetry-instrumentation-langchain) · [View on PyPI](https://pypi.org/project/opentelemetry-instrumentation-langchain/)