Arize Phoenix via OpenInference

Overview

This example demonstrates how to instrument your Agno agent with OpenInference and send traces to Arize Phoenix.

Code

import asyncio
import os

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools
from phoenix.otel import register

# Set environment variables for Arize Phoenix
os.environ["PHOENIX_CLIENT_HEADERS"] = f"api_key={os.getenv('ARIZE_PHOENIX_API_KEY')}"
os.environ["PHOENIX_COLLECTOR_ENDPOINT"] = "https://app.phoenix.arize.com"

# Configure the Phoenix tracer
tracer_provider = register(
    project_name="agno-stock-price-agent",  # Default is 'default'
    auto_instrument=True,  # Automatically use the installed OpenInference instrumentation
)

# Create and configure the agent
agent = Agent(
    name="Stock Price Agent",
    model=OpenAIChat(id="gpt-5-mini"),
    tools=[DuckDuckGoTools()],
    instructions="You are an internet search agent. Find and provide accurate information on any topic.",
    debug_mode=True,
)

# Use the agent
agent.print_response("What are the latest developments in artificial intelligence?")

Usage

1. Install Dependencies

   pip install -U agno arize-phoenix ddgs openai openinference-instrumentation-agno opentelemetry-sdk opentelemetry-exporter-otlp
   
2. Set Environment Variables

   export ARIZE_PHOENIX_API_KEY=<your-key>
   
3. Run the Agent

   Mac

   python cookbook/observability/arize_phoenix_via_openinference.py