genai:semantic-conventions
OfficialStandardize AI observability.
Authorkagenti
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill provides a standardized way to instrument AI agents using OpenTelemetry, ensuring consistent and meaningful observability data for LLM operations.
Core Features & Use Cases
- Standardized Attributes: Defines
gen_ai.*attributes for requests, responses, and conversation context. - Cross-Platform Compatibility: Enables transformation of
gen_ai.*attributes to OpenInference (for Phoenix) and MLflow formats. - Use Case: Instrument your LangChain or LlamaIndex agent to automatically log model calls, token usage, and conversation IDs to your observability backend (like Phoenix or MLflow) without custom mapping logic.
Quick Start
Use the genai:semantic-conventions skill to automatically instrument your OpenAI SDK calls with OpenTelemetry.
Dependency Matrix
Required Modules
opentelemetry-sdkopentelemetry-exporter-otlpopentelemetry-instrumentation-openai
Components
referencesscripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: genai:semantic-conventions Download link: https://github.com/kagenti/kagenti/archive/main.zip#genai-semantic-conventions Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.