# Arize Phoenix Workflow Via OpenInference (/examples/integrations/observability/workflows/arize-phoenix-via-openinference-workflow)



Demonstrates tracing a multi-step Agno workflow in Arize Phoenix.

```python title="arize_phoenix_via_openinference_workflow.py"
"""
Arize Phoenix Workflow Via OpenInference
========================================

Demonstrates tracing a multi-step Agno workflow in Arize Phoenix.
"""

import os

from agno.agent.agent import Agent
from agno.tools.websearch import WebSearchTools
from agno.workflow.condition import Condition
from agno.workflow.step import Step
from agno.workflow.types import StepInput
from agno.workflow.workflow import Workflow
from phoenix.otel import register

# ---------------------------------------------------------------------------
# Setup
# ---------------------------------------------------------------------------
os.environ["PHOENIX_CLIENT_HEADERS"] = f"api_key={os.getenv('ARIZE_PHOENIX_API_KEY')}"
os.environ["PHOENIX_COLLECTOR_ENDPOINT"] = (
    "https://app.phoenix.arize.com/"  # Add the suffix for your organization
)

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


# ---------------------------------------------------------------------------
# Create Workflow
# ---------------------------------------------------------------------------
# Basic agents
researcher = Agent(
    name="Researcher",
    instructions="Research the given topic and provide detailed findings.",
    tools=[WebSearchTools()],
)

summarizer = Agent(
    name="Summarizer",
    instructions="Create a clear summary of the research findings.",
)

fact_checker = Agent(
    name="Fact Checker",
    instructions="Verify facts and check for accuracy in the research.",
    tools=[WebSearchTools()],
)

writer = Agent(
    name="Writer",
    instructions="Write a comprehensive article based on all available research and verification.",
)


# Condition evaluator
def needs_fact_checking(step_input: StepInput) -> bool:
    """Determine if the research contains claims that need fact-checking."""
    return True


# Workflow steps
research_step = Step(
    name="research",
    description="Research the topic",
    agent=researcher,
)

summarize_step = Step(
    name="summarize",
    description="Summarize research findings",
    agent=summarizer,
)

fact_check_step = Step(
    name="fact_check",
    description="Verify facts and claims",
    agent=fact_checker,
)

write_article = Step(
    name="write_article",
    description="Write final article",
    agent=writer,
)

basic_workflow = Workflow(
    name="Basic Linear Workflow",
    description="Research -> Summarize -> Condition(Fact Check) -> Write Article",
    steps=[
        research_step,
        summarize_step,
        Condition(
            name="fact_check_condition",
            description="Check if fact-checking is needed",
            evaluator=needs_fact_checking,
            steps=[fact_check_step],
        ),
        write_article,
    ],
)


# ---------------------------------------------------------------------------
# Run Workflow
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    print("Running Basic Linear Workflow Example")
    print("=" * 50)

    try:
        basic_workflow.print_response(
            input="Recent breakthroughs in quantum computing",
            stream=True,
        )
    except Exception as e:
        print(f"Error: {e}")
        import traceback

        traceback.print_exc()
```

## Configure your Phoenix instance [#configure-your-phoenix-instance]

Replace the source's generic `PHOENIX_COLLECTOR_ENDPOINT` value with the collector endpoint from your Phoenix instance's Settings page before calling `register()`. Exporting a different value in the shell is insufficient because the source overwrites it. See [Phoenix setup](https://arize.com/docs/phoenix/tracing/how-to-tracing/setup-tracing/setup-using-phoenix-otel).

For current Phoenix authentication, replace the `PHOENIX_CLIENT_HEADERS` assignment with:

```python
os.environ["PHOENIX_API_KEY"] = os.environ["ARIZE_PHOENIX_API_KEY"]
```

The condition evaluator always returns `True`, so this recipe always runs the fact-checking step when execution reaches it. Its decision is not based on the research content.

## Run the Example [#run-the-example]

<Steps>
    <Step title="Set up your virtual environment">
      <CodeBlockTabs defaultValue="Mac">
        <CodeBlockTabsList>
          <CodeBlockTabsTrigger value="Mac">
            Mac
          </CodeBlockTabsTrigger>

          <CodeBlockTabsTrigger value="Windows">
            Windows
          </CodeBlockTabsTrigger>
        </CodeBlockTabsList>

        <CodeBlockTab value="Mac">
          ```bash
          uv venv --python 3.12
          source .venv/bin/activate
          ```
        </CodeBlockTab>

        <CodeBlockTab value="Windows">
          ```bash
          uv venv --python 3.12
          .venv\Scripts\activate
          ```
        </CodeBlockTab>
      </CodeBlockTabs>
    </Step>

  <Step title="Install dependencies">
    ```bash
    uv pip install -U agno arize-phoenix ddgs fastapi openai openinference-instrumentation-agno
    ```
  </Step>

  <Step title="Export your API keys">
    <CodeBlockTabs defaultValue="Mac/Linux">
      <CodeBlockTabsList>
        <CodeBlockTabsTrigger value="Mac/Linux">
          Mac/Linux
        </CodeBlockTabsTrigger>

        <CodeBlockTabsTrigger value="Windows">
          Windows
        </CodeBlockTabsTrigger>
      </CodeBlockTabsList>

      <CodeBlockTab value="Mac/Linux">
        ```bash
        export ARIZE_PHOENIX_API_KEY="your_arize_phoenix_api_key_here"
        export OPENAI_API_KEY="your_openai_api_key_here"
        ```
      </CodeBlockTab>

      <CodeBlockTab value="Windows">
        ```bash
        $Env:ARIZE_PHOENIX_API_KEY="your_arize_phoenix_api_key_here"
        $Env:OPENAI_API_KEY="your_openai_api_key_here"
        ```
      </CodeBlockTab>
    </CodeBlockTabs>
  </Step>

  <Step title="Run the example">
    Save the code above as `arize_phoenix_via_openinference_workflow.py`, then run:

    ```bash
    python arize_phoenix_via_openinference_workflow.py
    ```
  </Step>
</Steps>

Full source: [cookbook/observability/workflows/arize\_phoenix\_via\_openinference\_workflow.py](https://github.com/agno-agi/agno/blob/8f36eaf2d18e91afa7b327eec66a3cd3685dcb87/cookbook/observability/workflows/arize_phoenix_via_openinference_workflow.py)