LangGraphInstrumentor

LangGraphInstrumentor

An OpenTelemetry instrumentor for LangGraph applications.

This class provides automatic instrumentation for applications built with LangGraph. It captures traces from the execution of LangGraph graphs and sends them to the Fiddler platform for monitoring and analysis.

Instrumentation works by monkey-patching LangChain's callback system to inject a custom callback handler that captures trace data. Once instrumented, all LangGraph operations will automatically generate telemetry data.

Note: Instrumentation persists for the lifetime of the application unless explicitly removed by calling uninstrument(). Calling instrument() multiple times is safe - it will not create duplicate handlers.

Thread Safety: The instrumentation applies globally to the process and affects all threads. In concurrent environments (multi-threading, async), all contexts share the same instrumented callback system.

To use the instrumentor, you first need to create a FiddlerClient instance. Then, you can create an instance of LangGraphInstrumentor and call the instrument() method.

Examples

Basic usage:

from fiddler_langgraph import FiddlerClient, LangGraphInstrumentor

client = FiddlerClient(application_id="...", api_key="...", url="https://your-instance.fiddler.ai")
instrumentor = LangGraphInstrumentor(client=client)
instrumentor.instrument()

Removing instrumentation:

# Clean up instrumentation when shutting down
instrumentor.uninstrument()

Context manager pattern (advanced):

with LangGraphInstrumentor(client).instrument():
    # Instrumented operations here
    agent.invoke({"messages": [...]})
# Automatically uninstrumented after block

Parameters

Parameter	Type	Required	Default	Description
client	FiddlerClient	✓	-	The FiddlerClient instance.

Raises

ImportError -- If LangGraph version is incompatible or not installed.

instrumentation_dependencies()

Returns the package dependencies required for this instrumentor.

Returns

A collection of package dependency strings.

Return type: Collection[str]