opentelemetry-semantic-conventions-ai

OpenTelemetry Semantic Conventions Extension for Large Language Models

opentelemetry-semantic-conventions-ai Permissive license Apache-2.0 Active v0.5.1 released 2026-03-26

Install

opentelemetry-semantic-conventions-ai on PyPI

pip

pip install opentelemetry-semantic-conventions-ai

uv

uv add opentelemetry-semantic-conventions-ai

poetry

poetry add opentelemetry-semantic-conventions-ai

Package facts

License	Apache-2.0 (permissive)
Python support	supports the current Python release (<4,>=3.9)
Install friction	low — pure-Python wheel
Runtime dependencies	2 — opentelemetry-sdk, opentelemetry-semantic-conventions
Maintenance	actively maintained — 140 days since the last release
First released	2023-09-14
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: opentelemetry_semantic_conventions_ai-0.5.1-py3-none-any.whl

About opentelemetry-semantic-conventions-ai

from the package's own PyPI description — quoted content, verbatim

OpenTelemetry Semantic Conventions extensions for gen-AI applications

This is an extension of the standard OpenTelemetry Semantic Conventions for gen AI applications. It defines additional attributes for spans that are useful for debugging and monitoring prompts, completions, token usage, etc.

Read as markdown · JSON record

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

Defines OpenTelemetry semantic conventions and span attributes for monitoring and debugging generative AI applications, including prompt, completion, and token usage tracking.

Low friction install with active maintenance. Depends on opentelemetry-sdk and opentelemetry-semantic-conventions, both widely-used observability libraries.

Apache-2.0 permissive license allows use in most commercial and open-source projects without significant restriction.

Usage

pip install opentelemetry-semantic-conventions-ai

from opentelemetry_semantic_conventions_ai import SpanAttributes

# Use predefined AI span attributes in your instrumentation
span.set_attribute(SpanAttributes.LLM_PROMPT, "user query")

Requires Python 3.9 or later (supports current versions up to <4).

Verdict: A lightweight, actively maintained extension for OpenTelemetry that standardizes observability for gen-AI workloads. No known vulnerabilities, permissive licensing, and minimal dependencies make it a safe addition to observability stacks targeting LLM and AI applications.

Needs verification

Adoption rate and real-world usage patterns among AI/LLM observability practitioners
Whether the span attributes align with industry standards or de facto conventions used by major LLM providers

opentelemetry semantic conventions aillm monitoring attributesgen-ai observability standardsprompt completion tracingtoken usage telemetryai application instrumentationgenerative ai span attributes