OpenInference

The OpenInference provider uses instrumentations built by Arize Phoenix that provide OpenTelemetry-compliant tracing for AI applications with semantic conventions for LLMs, embeddings, and retrieval.

Configuration

Basic
Advanced

apiVersion: openlit.io/v1alpha1
kind: AutoInstrumentation
metadata:
  name: openinference-instrumentation
spec:
  selector:
    matchLabels:
      instrumentation.provider: "openinference"
  python:
    instrumentation:
      provider: "openinference"
      version: "latest"
  otlp:
    endpoint: "http://openlit:4318"

apiVersion: openlit.io/v1alpha1
kind: AutoInstrumentation
metadata:
  name: openinference-production
spec:
  selector:
    matchLabels:
      environment: "production"
  python:
    instrumentation:
      provider: "openinference"
      version: "latest"
      customPackages: "langchain>=0.1.0,llama-index>=0.9.0,openai>=1.0.0"
      env:
      - name: OTEL_SERVICE_NAME
        value: "ai-chat-service"
      - name: OTEL_DEPLOYMENT_ENVIRONMENT
        value: "production"
      - name: OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT
        value: "true"
  otlp:
    endpoint: "http://openlit:4318"
    timeout: 30
  resource:
    environment: "production"
    serviceName: "ai-chat-service"

Provider Specific Features

OpenInference offers comprehensive instrumentation coverage using pure OpenTelemetry standards:

Custom Package Installation

Install additional AI framework packages alongside OpenInference:

spec:
  python:
    instrumentation:
      customPackages: "langchain>=0.1.0,llama-index>=0.9.0,openai>=1.0.0"

Common AI Framework Packages:

LangChain: langchain>=0.1.0,langchain-community>=0.0.20
LlamaIndex: llama-index>=0.9.0,llama-index-vector-stores-chroma>=0.1.0
LLM Providers: openai>=1.0.0,anthropic>=0.8.0,google-generativeai>=0.3.0
Vector Databases: chromadb>=0.4.0,pinecone-client>=2.0.0

Comprehensive AI Framework Support

Built-in instrumentors for major AI frameworks:

# Included instrumentors (automatically enabled)
- openinference-instrumentation-openai
- openinference-instrumentation-anthropic  
- openinference-instrumentation-langchain
- openinference-instrumentation-llama-index
- openinference-instrumentation-bedrock
- openinference-instrumentation-mistralai
- openinference-instrumentation-groq
- openinference-instrumentation-vertexai
- openinference-instrumentation-dspy
- openinference-instrumentation-instructor
- openinference-instrumentation-litellm
- openinference-instrumentation-haystack
- openinference-instrumentation-guardrails
- openinference-instrumentation-portkey

OpenTelemetry Standard Compliance

Pure OpenTelemetry implementation with standard semantic conventions: Features:

100% OpenTelemetry semantic conventions compliance
Vendor-neutral tracing data
Multi-backend compatibility (Jaeger, Grafana, DataDog, etc.)
Standard resource attributes and span naming

Environment Variables

Variable	Description	Default
`OTEL_SERVICE_NAME`	Service name for tracing	`"openinference-app"`
`OTEL_DEPLOYMENT_ENVIRONMENT`	Deployment environment	`"production"`
`OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT`	Capture message content	`true`

Getting Started

Configuration

Instrumentations

Destinations

Configuration

Provider Specific Features

Custom Package Installation

Comprehensive AI Framework Support

OpenTelemetry Standard Compliance

Environment Variables

Getting Started

Configuration

Instrumentations

Destinations

​Configuration

​Provider Specific Features

​Custom Package Installation

​Comprehensive AI Framework Support

​OpenTelemetry Standard Compliance

​Environment Variables

Configuration

Provider Specific Features

Custom Package Installation

Comprehensive AI Framework Support

OpenTelemetry Standard Compliance

Environment Variables