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

# Logfire Via OpenInference

> Streams a YFinance stock agent's spans to Logfire over OTLP HTTP using the OpenInference Agno instrumentor.

Demonstrates instrumenting an Agno agent with OpenInference and sending traces to Logfire.

```python logfire_via_openinference.py theme={null}
"""
Logfire Via OpenInference
=========================

Demonstrates instrumenting an Agno agent with OpenInference and sending traces to Logfire.
"""

import asyncio
import os

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.yfinance import YFinanceTools
from openinference.instrumentation.agno import AgnoInstrumentor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import SimpleSpanProcessor

# ---------------------------------------------------------------------------
# Setup
# ---------------------------------------------------------------------------
LOGFIRE_WRITE_TOKEN = os.getenv("LOGFIRE_WRITE_TOKEN")

# os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = (
#     "https://logfire-us.pydantic.dev"  # US data region
# )
os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = (
    "https://logfire-eu.pydantic.dev"  # EU data region
)
# os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = "http://localhost:4318"  # Local deployment

os.environ["OTEL_EXPORTER_OTLP_HEADERS"] = f"Authorization={LOGFIRE_WRITE_TOKEN}"

tracer_provider = TracerProvider()
tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter()))

# Start instrumenting agno
AgnoInstrumentor().instrument(tracer_provider=tracer_provider)


# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    name="Stock Price Agent",
    model=OpenAIChat(id="gpt-5.2"),
    tools=[YFinanceTools()],
    instructions="You are a stock price agent. Answer questions in the style of a stock analyst.",
)


# ---------------------------------------------------------------------------
# Run Example
# ---------------------------------------------------------------------------
async def main() -> None:
    await agent.aprint_response(
        "What is the current price of Tesla? Then find the current price of NVIDIA",
        stream=True,
    )


if __name__ == "__main__":
    asyncio.run(main())
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno openai openinference-instrumentation-agno opentelemetry-exporter-otlp opentelemetry-sdk yfinance
    ```
  </Step>

  <Step title="Export environment variables">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export LOGFIRE_WRITE_TOKEN="your_logfire_write_token_here"
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:LOGFIRE_WRITE_TOKEN="your_logfire_write_token_here"
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Choose the Logfire region">
    Set `OTEL_EXPORTER_OTLP_ENDPOINT` in the code to the endpoint for your Logfire project's US or EU region. The source enables the EU endpoint by default.
  </Step>

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

    ```bash theme={null}
    python logfire_via_openinference.py
    ```
  </Step>
</Steps>

Full source: [cookbook/observability/logfire\_via\_openinference.py](https://github.com/agno-agi/agno/blob/main/cookbook/observability/logfire_via_openinference.py)