> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Langfuse Via OpenLIT

> Export traces from a web-search agent to Langfuse by wiring an OTLP HTTP span exporter into OpenLIT's global tracer with batching disabled.

Demonstrates sending Agno traces to Langfuse through OpenLIT.

```python langfuse_via_openlit.py theme={null}
"""
Langfuse Via OpenLIT
====================

Demonstrates sending Agno traces to Langfuse through OpenLIT.
"""

import base64
import os

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.websearch import WebSearchTools

# ---------------------------------------------------------------------------
# Setup
# ---------------------------------------------------------------------------
LANGFUSE_AUTH = base64.b64encode(
    f"{os.getenv('LANGFUSE_PUBLIC_KEY')}:{os.getenv('LANGFUSE_SECRET_KEY')}".encode()
).decode()

os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = (
    "https://us.cloud.langfuse.com/api/public/otel"  # US data region
)
# os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = "https://cloud.langfuse.com/api/public/otel"  # EU data region
# os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = "http://localhost:3000/api/public/otel"  # Local deployment (>= v3.22.0)

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

from opentelemetry.exporter.otlp.proto.http.trace_exporter import (  # noqa: E402
    OTLPSpanExporter,
)
from opentelemetry.sdk.trace import TracerProvider  # noqa: E402
from opentelemetry.sdk.trace.export import SimpleSpanProcessor  # noqa: E402

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

# Sets the global default tracer provider
from opentelemetry import trace  # noqa: E402

trace.set_tracer_provider(trace_provider)

# Creates a tracer from the global tracer provider
tracer = trace.get_tracer(__name__)

import openlit  # noqa: E402

# Initialize OpenLIT instrumentation. The disable_batch flag is set to true to process traces immediately.
openlit.init(tracer=tracer, disable_batch=True)


# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIChat(id="gpt-5.6-luna"),
    tools=[WebSearchTools()],
    markdown=True,
)


# ---------------------------------------------------------------------------
# Run Example
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response("What is currently trending on Twitter?")
```

## Run the Example

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

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno ddgs openai openlit opentelemetry-exporter-otlp opentelemetry-sdk
```

**2. Export environment variables**

```bash Mac/Linux theme={null}
export LANGFUSE_PUBLIC_KEY="your_langfuse_public_key_here"
export LANGFUSE_SECRET_KEY="your_langfuse_secret_key_here"
export OPENAI_API_KEY="your_openai_api_key_here"
```

```bash Windows theme={null}
$Env:LANGFUSE_PUBLIC_KEY="your_langfuse_public_key_here"
$Env:LANGFUSE_SECRET_KEY="your_langfuse_secret_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
```

**3. Run the example**

Save the code above as `langfuse_via_openlit.py`, then run:

```bash theme={null}
python langfuse_via_openlit.py
```

Full source: [cookbook/observability/langfuse\_via\_openlit.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/observability/langfuse_via_openlit.py)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.