All Python Instrumentations

Complete list of all OpenInference Python instrumentation packages

OpenInference provides comprehensive Python instrumentation for AI/ML frameworks and LLM providers. All instrumentations are fully OpenTelemetry compatible and can be sent to any OpenTelemetry collector for viewing, such as Arize Phoenix.

Available Instrumentations

The following table lists all available Python instrumentation packages:

Package	Description	PyPI
openinference-instrumentation-openai	Auto-instrumentation for OpenAI’s Python SDK	PyPI
openinference-instrumentation-anthropic	Auto-instrumentation for Anthropic SDK	PyPI
openinference-instrumentation-langchain	Auto-instrumentation for LangChain (1.x and Classic)	PyPI
openinference-instrumentation-llama-index	Auto-instrumentation for LlamaIndex	PyPI
openinference-instrumentation-bedrock	Auto-instrumentation for AWS Bedrock (boto3 and aioboto3)	PyPI
openinference-instrumentation-vertexai	Auto-instrumentation for Google Vertex AI	PyPI
openinference-instrumentation-mistralai	Auto-instrumentation for Mistral AI SDK	PyPI
openinference-instrumentation-dspy	Auto-instrumentation for DSPy	PyPI
openinference-instrumentation-haystack	Auto-instrumentation for Haystack pipelines	PyPI
openinference-instrumentation-groq	Auto-instrumentation for Groq SDK	PyPI
openinference-instrumentation-litellm	Auto-instrumentation for LiteLLM	PyPI
openinference-instrumentation-instructor	Auto-instrumentation for Instructor library	PyPI
openinference-instrumentation-crewai	Auto-instrumentation for CrewAI agents	PyPI
openinference-instrumentation-google-genai	Auto-instrumentation for Google GenAI	PyPI
openinference-instrumentation-google-adk	Auto-instrumentation for Google ADK	PyPI
openinference-instrumentation-pydantic-ai	Auto-instrumentation for PydanticAI	PyPI
openinference-instrumentation-openai-agents	Auto-instrumentation for OpenAI Agents SDK	PyPI
openinference-instrumentation-autogen	Auto-instrumentation for Autogen (ag2)	PyPI
openinference-instrumentation-autogen-agentchat	Auto-instrumentation for Autogen AgentChat	PyPI
openinference-instrumentation-agent-framework	Auto-instrumentation for Microsoft Agent Framework	PyPI
openinference-instrumentation-agentspec	Auto-instrumentation for Agent Spec	PyPI
openinference-instrumentation-agno	Auto-instrumentation for Agno agents	PyPI
openinference-instrumentation-smolagents	Auto-instrumentation for smolagents	PyPI
openinference-instrumentation-strands-agents	Auto-instrumentation for Strands Agents	PyPI
openinference-instrumentation-beeai	Auto-instrumentation for BeeAI	PyPI
openinference-instrumentation-guardrails	Auto-instrumentation for Guardrails	PyPI
openinference-instrumentation-openllmetry	Converts OpenLLMetry traces to OpenInference	PyPI
openinference-instrumentation-openlit	Auto-instrumentation for OpenLit	PyPI
openinference-instrumentation-pipecat	Auto-instrumentation for Pipecat	PyPI
openinference-instrumentation-portkey	Auto-instrumentation for Portkey	PyPI
openinference-instrumentation-mcp	Auto-instrumentation for MCP SDK (context propagation)	PyPI
openinference-instrumentation-promptflow	Auto-instrumentation for PromptFlow	PyPI

Getting Started

All instrumentations follow a similar pattern:

1. Install the instrumentation package
2. Configure the OpenTelemetry tracer provider
3. Instrument your application
4. Run your code and view traces

Basic Example

from openinference.instrumentation.<package> import <Package>Instrumentor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk import trace as trace_sdk
from opentelemetry.sdk.trace.export import SimpleSpanProcessor

# Configure tracer
endpoint = "http://127.0.0.1:6006/v1/traces"
tracer_provider = trace_sdk.TracerProvider()
tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))

# Instrument
<Package>Instrumentor().instrument(tracer_provider=tracer_provider)

# Your application code here

Common Features

All OpenInference instrumentations support:

• Session tracking - Track user sessions across multiple requests
• User identification - Associate traces with specific users
• Metadata and tags - Add custom metadata and tags to traces
• Prompt template tracking - Track prompt templates and variables
• PII masking - Configure trace masking for sensitive data
• Context propagation - Automatic propagation of tracing context

Using Context Attributes

from openinference.instrumentation import using_attributes

with using_attributes(
    session_id="my-session-id",
    user_id="user-123",
    metadata={"key": "value"},
    tags=["production", "feature-x"],
):
    # Your instrumented code here
    pass

Additional Resources

• OpenInference Specification
• OpenInference and Phoenix Documentation
• Customizing Spans
• Tracing Configuration (PII Masking)

Contributing

To contribute a new instrumentation or report issues, visit the OpenInference GitHub repository.