LogoLogo
Python SDKSlack
  • Documentation
  • Cookbooks
  • Self-Hosting
  • Release Notes
  • Reference
  • Arize AI
  • Quickstarts
  • ✨Arize Copilot
  • Concepts
    • Agent Evaluation
    • Tracing
      • What is OpenTelemetry?
      • What is OpenInference?
      • Openinference Semantic Conventions
    • Evaluation
  • 🧪Develop
    • Quickstart: Experiments
    • Datasets
      • Create a dataset
      • Update a dataset
      • Export a dataset
    • Experiments
      • Run experiments
      • Run experiments with code
        • Experiments SDK differences in AX vs Phoenix
        • Log experiment results via SDK
      • Evaluate experiments
      • Evaluate experiment with code
      • CI/CD with experiments
        • Github Action Basics
        • Gitlab CI/CD Basics
      • Download experiment
    • Prompt Playground
      • Use tool calling
      • Use image inputs
    • Playground Integrations
      • OpenAI
      • Azure OpenAI
      • AWS Bedrock
      • VertexAI
      • Custom LLM Models
    • Prompt Hub
  • 🧠Evaluate
    • Online Evals
      • Run evaluations in the UI
      • Run evaluations with code
      • Test LLM evaluator in playground
      • View task details & logs
      • ✨Copilot: Eval Builder
      • ✨Copilot: Eval Analysis
      • ✨Copilot: RAG Analysis
    • Experiment Evals
    • LLM as a Judge
      • Custom Eval Templates
      • Arize Templates
        • Agent Tool Calling
        • Agent Tool Selection
        • Agent Parameter Extraction
        • Agent Path Convergence
        • Agent Planning
        • Agent Reflection
        • Hallucinations
        • Q&A on Retrieved Data
        • Summarization
        • Code Generation
        • Toxicity
        • AI vs Human (Groundtruth)
        • Citation
        • User Frustration
        • SQL Generation
    • Code Evaluations
    • Human Annotations
  • 🔭Observe
    • Quickstart: Tracing
    • Tracing
      • Setup tracing
      • Trace manually
        • Trace inputs and outputs
        • Trace function calls
        • Trace LLM, Retriever and Tool Spans
        • Trace prompt templates & variables
        • Trace as Inferences
        • Send Traces from Phoenix -> Arize
        • Advanced Tracing (OTEL) Examples
      • Add metadata
        • Add events, exceptions and status
        • Add attributes, metadata and tags
        • Send data to a specific project
        • Get the current span context and tracer
      • Configure tracing options
        • Configure OTEL tracer
        • Mask span attributes
        • Redact sensitive data from traces
        • Instrument with OpenInference helpers
      • Query traces
        • Filter Traces
          • Time Filtering
        • Export Traces
        • ✨AI Powered Search & Filter
        • ✨AI Powered Trace Analysis
        • ✨AI Span Analysis & Evaluation
    • Tracing Integrations
      • OpenAI
      • OpenAI Agents SDK
      • LlamaIndex
      • LlamaIndex Workflows
      • LangChain
      • LangGraph
      • Hugging Face smolagents
      • Autogen
      • Google GenAI (Gemini)
      • Vertex AI
      • Amazon Bedrock
      • Amazon Bedrock Agents
      • MistralAI
      • Anthropic
      • LangFlow
      • Haystack
      • LiteLLM
      • CrewAI
      • Groq
      • DSPy
      • Guardrails AI
      • Prompt flow
      • Vercel AI SDK
      • Llama
      • Together AI
      • OpenTelemetry (arize-otel)
      • BeeAI
    • Evals on Traces
    • Guardrails
    • Sessions
    • Dashboards
      • Dashboard Widgets
      • Tracking Token Usage
      • ✨Copilot: Dashboard Widget Creation
    • Monitors
      • Integrations: Monitors
        • Slack
          • Manual Setup
        • OpsGenie
        • PagerDuty
      • LLM Red Teaming
    • Custom Metrics & Analytics
      • Arize Query Language Syntax
        • Conditionals and Filters
        • All Operators
        • All Functions
      • Custom Metric Examples
      • ✨Copilot: ArizeQL Generator
  • 📈Machine Learning
    • Machine Learning
      • User Guide: ML
      • Quickstart: ML
      • Concepts: ML
        • What Is A Model Schema
        • Delayed Actuals and Tags
        • ML Glossary
      • How To: ML
        • Upload Data to Arize
          • Pandas SDK Example
          • Local File Upload
            • File Upload FAQ
          • Table Ingestion Tuning
          • Wildcard Paths for Cloud Storage
          • Troubleshoot Data Upload
          • Sending Data FAQ
        • Monitors
          • ML Monitor Types
          • Configure Monitors
            • Notifications Providers
          • Programmatically Create Monitors
          • Best Practices for Monitors
        • Dashboards
          • Dashboard Widgets
          • Dashboard Templates
            • Model Performance
            • Pre-Production Performance
            • Feature Analysis
            • Drift
          • Programmatically Create Dashboards
        • Performance Tracing
          • Time Filtering
          • ✨Copilot: Performance Insights
        • Drift Tracing
          • ✨Copilot: Drift Insights
          • Data Distribution Visualization
          • Embeddings for Tabular Data (Multivariate Drift)
        • Custom Metrics
          • Arize Query Language Syntax
            • Conditionals and Filters
            • All Operators
            • All Functions
          • Custom Metric Examples
          • Custom Metrics Query Language
          • ✨Copilot: ArizeQL Generator
        • Troubleshoot Data Quality
          • ✨Copilot: Data Quality Insights
        • Explainability
          • Interpreting & Analyzing Feature Importance Values
          • SHAP
          • Surrogate Model
          • Explainability FAQ
          • Model Explainability
        • Bias Tracing (Fairness)
        • Export Data to Notebook
        • Automate Model Retraining
        • ML FAQ
      • Use Cases: ML
        • Binary Classification
          • Fraud
          • Insurance
        • Multi-Class Classification
        • Regression
          • Lending
          • Customer Lifetime Value
          • Click-Through Rate
        • Timeseries Forecasting
          • Demand Forecasting
          • Churn Forecasting
        • Ranking
          • Collaborative Filtering
          • Search Ranking
        • Natural Language Processing (NLP)
        • Common Industry Use Cases
      • Integrations: ML
        • Google BigQuery
          • GBQ Views
          • Google BigQuery FAQ
        • Snowflake
          • Snowflake Permissions Configuration
        • Databricks
        • Google Cloud Storage (GCS)
        • Azure Blob Storage
        • AWS S3
          • Private Image Link Access Via AWS S3
        • Kafka
        • Airflow Retrain
        • Amazon EventBridge Retrain
        • MLOps Partners
          • Algorithmia
          • Anyscale
          • Azure & Databricks
          • BentoML
          • CML (DVC)
          • Deepnote
          • Feast
          • Google Cloud ML
          • Hugging Face
          • LangChain 🦜🔗
          • MLflow
          • Neptune
          • Paperspace
          • PySpark
          • Ray Serve (Anyscale)
          • SageMaker
            • Batch
            • RealTime
            • Notebook Instance with Greater than 20GB of Data
          • Spell
          • UbiOps
          • Weights & Biases
      • API Reference: ML
        • Python SDK
          • Pandas Batch Logging
            • Client
            • log
            • Schema
            • TypedColumns
            • EmbeddingColumnNames
            • ObjectDetectionColumnNames
            • PromptTemplateColumnNames
            • LLMConfigColumnNames
            • LLMRunMetadataColumnNames
            • NLP_Metrics
            • AutoEmbeddings
            • utils.types.ModelTypes
            • utils.types.Metrics
            • utils.types.Environments
          • Single Record Logging
            • Client
            • log
            • TypedValue
            • Ranking
            • Multi-Class
            • Object Detection
            • Embedding
            • LLMRunMetadata
            • utils.types.ModelTypes
            • utils.types.Metrics
            • utils.types.Environments
        • Java SDK
          • Constructor
          • log
          • bulkLog
          • logValidationRecords
          • logTrainingRecords
        • R SDK
          • Client$new()
          • Client$log()
        • Rest API
    • Computer Vision
      • How to: CV
        • Generate Embeddings
          • How to Generate Your Own Embedding
          • Let Arize Generate Your Embeddings
        • Embedding & Cluster Analyzer
        • ✨Copilot: Embedding Summarization
        • Similarity Search
        • Embedding Drift
        • Embeddings FAQ
      • Integrations: CV
      • Use Cases: CV
        • Image Classification
        • Image Segmentation
        • Object Detection
      • API Reference: CV
Powered by GitBook

Support

  • Chat Us On Slack
  • support@arize.com

Get Started

  • Signup For Free
  • Book A Demo

Copyright © 2025 Arize AI, Inc

On this page
  • OpenInference OTEL Tracing
  • Installation
  • Setting Up Tracing
  • Using your Tracer
  • 1. As a decorator to trace entire functions
  • 2. As a with clause to trace specific code blocks
  • OpenInference Span Kinds
  • Chains
  • Using Context Managers
  • Using Decorators
  • Agents
  • Using Context Managers
  • Using Decorators
  • Tools
  • Using Context Managers
  • Using Decorators
  • Additional Features
  • Suppress Tracing
  • Using Context Attributes

Was this helpful?

  1. Observe
  2. Tracing
  3. Configure tracing options

Instrument with OpenInference helpers

As part of the OpenInference library, Arize provides helpful abstractions to make manual instrumentation easier.

Last updated 2 months ago

Was this helpful?

OpenInference OTEL Tracing

This documentation provides a guide on using OpenInference OTEL tracing decorators and methods for instrumenting functions, chains, agents, and tools using OpenTelemetry.

These tools can be combined with, or used in place of, OpenTelemetry instrumentation code. They are designed to simplify the instrumentation process.

Installation

Ensure you have OpenInference and OpenTelemetry installed:

pip install openinference opentelemetry-api opentelemetry-sdk

Setting Up Tracing

You can configure the tracer using either TracerProvider from openinference.instrumentation or using arize.otel.register.

Using TracerProvider

from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.resources import Resource
from opentelemetry.sdk.trace.export import ConsoleSpanExporter, SimpleSpanProcessor

from openinference.instrumentation import TracerProvider
from openinference.semconv.resource import ResourceAttributes

endpoint = "http://127.0.0.1:6006/v1/traces"
resource = Resource(attributes={ResourceAttributes.PROJECT_NAME: "openinference-tracer"})
tracer_provider = TracerProvider(resource=resource)
tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))
tracer_provider.add_span_processor(SimpleSpanProcessor(ConsoleSpanExporter()))
tracer = tracer_provider.get_tracer(__name__)

Using arize.otel.register

import opentelemetry
from arize.otel import register

# Setup OTel via our convenience function
tracer_provider = register(
    space_id = "your-space-id", # in app space settings page
    api_key = "your-api-key", # in app space settings page
    project_name = "your-project-name", # name this to whatever you would like
)

tracer = tracer_provider.get_tracer(__name__)

Using your Tracer

Your tracer object can now be used in two primary ways:

1. As a decorator to trace entire functions

@tracer.chain
def my_func(input: str) -> str:
    return "output"

This entire function will appear as a Span in Arize. Input and output attributes in Arize will be set automatically based on my_func's parameters and return. The status attribute will also be set automatically.

2. As a with clause to trace specific code blocks

with tracer.start_as_current_span(
    "my-span-name",
    openinference_span_kind="chain",
) as span:
    span.set_input("input")
    span.set_output("output")
    span.set_status(Status(StatusCode.OK))

The code within this clause will be captured as a Span in Arize. Here the input, output, and status must be set manually.

This approach is useful when you need only a portion of a method to be captured as a Span.

OpenInference Span Kinds

OpenInference Span Kinds denote the possible types of spans you might capture, and will be rendered different in the Arize UI.

The possible values are:

Span Kind
Use

CHAIN

General logic operations, functions, or code blocks

LLM

Making LLM calls

TOOL

Completing tool calls

RETRIEVER

Retrieving documents

EMBEDDING

Generating embeddings

AGENT

Agent invokations - typically a top level or near top level span

RERANKER

Reranking retrieved context

UNKNOWN

Unknown

GUARDRAIL

Guardrail checks

EVALUATOR

Evaluators - typically only use by Arize when automatically tracing evaluation and experiment calls

Chains

Using Context Managers

with tracer.start_as_current_span(
    "chain-span-with-plain-text-io",
    openinference_span_kind="chain",
) as span:
    span.set_input("input")
    span.set_output("output")
    span.set_status(Status(StatusCode.OK))

Using Decorators

@tracer.chain
def decorated_chain_with_plain_text_output(input: str) -> str:
    return "output"

decorated_chain_with_plain_text_output("input")

Using JSON Output

@tracer.chain
def decorated_chain_with_json_output(input: str) -> Dict[str, Any]:
    return {"output": "output"}

decorated_chain_with_json_output("input")

Overriding Span Name

@tracer.chain(name="decorated-chain-with-overriden-name")
def this_name_should_be_overriden(input: str) -> Dict[str, Any]:
    return {"output": "output"}

this_name_should_be_overriden("input")

Agents

Using Context Managers

with tracer.start_as_current_span(
    "agent-span-with-plain-text-io",
    openinference_span_kind="agent",
) as span:
    span.set_input("input")
    span.set_output("output")
    span.set_status(Status(StatusCode.OK))

Using Decorators

@tracer.agent
def decorated_agent(input: str) -> str:
    return "output"

decorated_agent("input")

Tools

Using Context Managers

with tracer.start_as_current_span(
    "tool-span",
    openinference_span_kind="tool",
) as span:
    span.set_input("input")
    span.set_output("output")
    span.set_tool(
        name="tool-name",
        description="tool-description",
        parameters={"input": "input"},
    )
    span.set_status(Status(StatusCode.OK))

Using Decorators

@tracer.tool
def decorated_tool(input1: str, input2: int) -> None:
    """
    tool-description
    """

decorated_tool("input1", 1)

Overriding Tool Name

@tracer.tool(
    name="decorated-tool-with-overriden-name",
    description="overriden-tool-description",
)
def this_tool_name_should_be_overriden(input1: str, input2: int) -> None:
    """
    this tool description should be overriden
    """

this_tool_name_should_be_overriden("input1", 1)

Additional Features

Suppress Tracing

with suppress_tracing():
    with tracer.start_as_current_span(
        "THIS-SPAN-SHOULD-NOT-BE-TRACED",
        openinference_span_kind="chain",
    ) as span:
        span.set_input("input")
        span.set_output("output")
        span.set_status(Status(StatusCode.OK))

Using Context Attributes

with using_attributes(session_id="123"):
    with tracer.start_as_current_span(
        "chain-span-with-context-attributes",
        openinference_span_kind="chain",
    ) as span:
        span.set_input("input")
        span.set_output("output")
        span.set_status(Status(StatusCode.OK))

This documentation provides an overview of how to use OpenInference OTEL tracing decorators with chains, agents, and tools. For more details, refer to the OpenInference official documentation.

🔭
LogoGitHub - Arize-ai/openinference: OpenTelemetry Instrumentation for AI ObservabilityGitHub