> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/Arize-ai/openinference/llms.txt
> Use this file to discover all available pages before exploring further.

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

## 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

```python theme={null}
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

```python theme={null}
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](https://github.com/Arize-ai/openinference)
* [OpenInference and Phoenix Documentation](https://docs.arize.com/phoenix)
* [Customizing Spans](https://github.com/Arize-ai/openinference/tree/main/python/openinference-instrumentation#customizing-spans)
* [Tracing Configuration (PII Masking)](https://github.com/Arize-ai/openinference/tree/main/python/openinference-instrumentation#tracing-configuration)

## Contributing

To contribute a new instrumentation or report issues, visit the [OpenInference GitHub repository](https://github.com/Arize-ai/openinference).