Skip to main content
Langfuse is an open-source observability platform for LLM applications that provides tracing, monitoring, and debugging. The integration is built into the Launchpad’s core using the native Langfuse SDK.
You can self-host for full data control and privacy, which is useful when sensitive data must stay within your infrastructure.

​
Why Langfuse?

  • Complete Tracing: Track every workflow step, node execution, and LLM call
  • Performance Monitoring: Monitor response times, costs, and success rates
  • Debug Issues: Detailed logs and traces for troubleshooting failures
Datalumina uses this integration in production to monitor and trace workflows.

​
Quick Setup

1

Get Langfuse Account

Create a free account at langfuse.com and get your API keys
2

Update Environment

Add to your .env files:
LANGFUSE_PUBLIC_KEY=pk-lf-...
LANGFUSE_SECRET_KEY=sk-lf-...
LANGFUSE_BASE_URL=https://cloud.langfuse.com  # Or your self-hosted URL
3

Enable Tracing in Your Workflow

Pass enable_tracing=True when initializing your workflow:
workflow = MyWorkflow(enable_tracing=True)
result = workflow.run(event_data)
4

Test Integration

Run a workflow and check your Langfuse dashboard for traces:
python playground/workflow_playground.py

​
How It Works

The Langfuse integration uses the native Langfuse SDK to create spans around workflow and node execution: 
from langfuse import get_client

class Workflow(ABC):
    def __init__(self, enable_tracing: bool = True):
        if enable_tracing:
            langfuse = get_client()
            if langfuse.auth_check():
                self.langfuse = langfuse
            else:
                raise LangfuseAuthenticationError(
                    "Failed to authenticate with Langfuse."
                )
When tracing is enabled:
  • A parent span is created for the entire workflow execution
  • Each node gets its own child span with inputs and outputs
  • LLM calls within AgentNodes are automatically instrumented
  • Errors are captured with full context

​
Enabling and Disabling Tracing

Tracing is controlled per-workflow instance: 
# Enable tracing (default for most workflows)
workflow = StreamingExampleWorkflow(enable_tracing=True)

# Disable tracing for local testing or performance
workflow = StreamingExampleWorkflow(enable_tracing=False)
If enable_tracing=True but Langfuse credentials are missing or invalid, the workflow will raise a LangfuseAuthenticationError.

​
Core Integration Features

  • Automatic Tracing: Every workflow execution is automatically traced when enabled
  • Node-Level Visibility: Individual node executions, inputs, and outputs are captured
  • LLM Call Tracking: All LLM interactions including prompts, responses, and metadata
  • Error Monitoring: Failed executions with full stack traces and context
  • Streaming Support: SSE streaming workflows are fully traced

​
Dashboard Features

​
Workflow Traces

View complete workflow execution paths with timing, inputs, and outputs for each node.

​
Performance Analytics

Monitor average response times, success rates, and cost analysis across workflows.

​
LLM Usage Tracking

Track token usage, model performance, and costs across different LLM providers.

​
Debug Information

Detailed error logs with full context when workflows fail or perform unexpectedly.