Langchain Instrumentation

Langchain is a powerful framework for building LLM applications. LangWatch integrates with Langchain to provide detailed observability into your chains, agents, LLM calls, and tool usage.

This guide covers the primary approaches to instrumenting Langchain with LangWatch:

1. Using LangWatch’s Langchain Callback Handler (Recommended): The most direct method, using a specific callback provided by LangWatch to capture rich Langchain-specific trace data.
2. Using Community OpenTelemetry Instrumentors: Leveraging dedicated Langchain instrumentors like those from OpenInference or OpenLLMetry.
3. Utilizing Langchain’s Native OpenTelemetry Export (Advanced): Configuring Langchain to send its own OpenTelemetry traces to an endpoint where LangWatch can collect them.

​

1. Using LangWatch’s Langchain Callback Handler (Recommended)

This is the preferred and most comprehensive method for instrumenting Langchain with LangWatch. The LangWatch SDK provides a LangchainCallbackHandler that deeply integrates with Langchain’s event system.

import langwatch
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
from langchain.schema import StrOutputParser
from langchain.schema.runnable import Runnable
from langchain.schema.runnable.config import RunnableConfig
import os
import asyncio

# Initialize LangWatch
langwatch.setup()

# Standard Langchain setup
model = ChatOpenAI(streaming=True)
prompt = ChatPromptTemplate.from_messages(
    [("system", "You are a concise assistant."), ("human", "{question}")]
)
runnable = prompt | model | StrOutputParser()

@langwatch.trace(name="Langchain - QA with Callback")
async def handle_message_with_callback(user_question: str):
    current_trace = langwatch.get_current_trace()
    current_trace.update(metadata={"user_id": "callback-user"})

    langwatch_callback = current_trace.get_langchain_callback()

    final_response = ""
    async for chunk in runnable.astream(
        {"question": user_question},
        config=RunnableConfig(callbacks=[langwatch_callback])
    ):
        final_response += chunk
    return final_response

async def main_callback():
    if not os.getenv("OPENAI_API_KEY"):
        print("OPENAI_API_KEY not set. Skipping Langchain callback example.")
        return
    response = await handle_message_with_callback("What is Langchain? Explain briefly.")
    print(f"AI (Callback): {response}")

if __name__ == "__main__":
    asyncio.run(main_callback())

How it Works:

• @langwatch.trace(): Creates a parent LangWatch trace.
• current_trace.get_langchain_callback(): Retrieves a LangWatch-specific callback handler linked to the current trace.
• RunnableConfig(callbacks=[langwatch_callback]): Injects the handler into Langchain’s execution. Langchain emits events (on_llm_start, on_chain_end, etc.), which the handler converts into detailed LangWatch spans, correctly parented under the main trace.

Key points:

• Provides the most detailed Langchain-specific structural information (chains, agents, tools, LLMs as distinct steps).
• Works for all Langchain execution methods (astream, stream, invoke, ainvoke).

​

2. Using Community OpenTelemetry Instrumentors

Dedicated Langchain instrumentors from libraries like OpenInference and OpenLLMetry can also be used to capture Langchain operations as OpenTelemetry traces, which LangWatch can then ingest.

​

Instrumenting Langchain with Dedicated Instrumentors

​

i. Via langwatch.setup()

# OpenInference Example
import langwatch
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
from langchain.schema import StrOutputParser
from openinference.instrumentation.langchain import LangchainInstrumentor
import os
import asyncio

langwatch.setup(
    instrumentors=[LangchainInstrumentor()] # Add OpenInference LangchainInstrumentor
)

model = ChatOpenAI()
prompt = ChatPromptTemplate.from_messages([
    ("system", "You are brief."), ("human", "{question}")]
)
runnable = prompt | model | StrOutputParser()

@langwatch.trace(name="Langchain - OpenInference via Setup")
async def handle_message_oinference_setup(user_question: str):
    response = await runnable.ainvoke({"question": user_question})
    return response

async def main_community_oinference_setup():
    if not os.getenv("OPENAI_API_KEY"):
        print("OPENAI_API_KEY not set. Skipping OpenInference Langchain (setup) example.")
        return
    response = await handle_message_oinference_setup("Explain Langchain instrumentation with OpenInference.")
    print(f"AI (OInference Setup): {response}")

if __name__ == "__main__":
    asyncio.run(main_community_oinference_setup())

​

ii. Direct Instrumentation

# OpenInference Example
import langwatch
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
from langchain.schema import StrOutputParser
from openinference.instrumentation.langchain import LangchainInstrumentor
import os
import asyncio

langwatch.setup()
LangchainInstrumentor().instrument() # Instrument Langchain directly

model = ChatOpenAI()
prompt = ChatPromptTemplate.from_messages([
    ("system", "You are very brief."), ("human", "{question}")]
)
runnable = prompt | model | StrOutputParser()

@langwatch.trace(name="Langchain - OpenInference Direct")
async def handle_message_oinference_direct(user_question: str):
    response = await runnable.ainvoke({"question": user_question})
    return response

async def main_community_oinference_direct():
    if not os.getenv("OPENAI_API_KEY"):
        print("OPENAI_API_KEY not set. Skipping OpenInference Langchain (direct) example.")
        return
    response = await handle_message_oinference_direct("How does direct Langchain instrumentation work?")
    print(f"AI (OInference Direct): {response}")

if __name__ == "__main__":
    asyncio.run(main_community_oinference_direct())

Key points for dedicated Langchain instrumentors:

• Directly instrument Langchain operations, providing traces from Langchain’s perspective.
• Requires installing the respective instrumentation package (e.g., openinference-instrumentation-langchain or opentelemetry-instrumentation-langchain for OpenLLMetry).

​

3. Utilizing Langchain’s Native OpenTelemetry Export (Advanced)

Langchain itself can be configured to export OpenTelemetry traces. If you set this up and configure Langchain to send traces to an OpenTelemetry collector endpoint that LangWatch is also configured to receive from (or if LangWatch is your OTLP endpoint), then LangWatch can ingest these natively generated Langchain traces.

Setup (Conceptual):

1. Configure Langchain for OpenTelemetry export. This usually involves setting environment variables:

   export LANGCHAIN_TRACING_V2=true
   export LANGCHAIN_ENDPOINT= # Your OTLP gRPC endpoint (e.g., http://localhost:4317)
   # Potentially other OTEL_EXPORTER_OTLP_* variables for more granular control
   

2. Initialize LangWatch: langwatch.setup().

# This example assumes Langchain is configured via environment variables
# to send OTel traces to an endpoint LangWatch can access.
import langwatch
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
from langchain.schema import StrOutputParser
import os
import asyncio

langwatch.setup() # LangWatch is ready to receive OTel traces

model = ChatOpenAI()
prompt = ChatPromptTemplate.from_messages([
    ("system", "You are brief."), ("human", "{question}")]
)
runnable = prompt | model | StrOutputParser()

@langwatch.trace(name="Langchain - Native OTel Export") # Optional: group Langchain traces
async def handle_message_native_otel(user_question: str):
    response = await runnable.ainvoke({"question": user_question})
    return response

async def main_native_otel():
    if not os.getenv("OPENAI_API_KEY") or not os.getenv("LANGCHAIN_TRACING_V2") == "true":
        print("Required env vars (OPENAI_API_KEY, LANGCHAIN_TRACING_V2='true') not set. Skipping native OTel.")
        return
    response = await handle_message_native_otel("Tell me about Langchain OTel export itself.")
    print(f"AI (Native OTel): {response}")

if __name__ == "__main__":
    asyncio.run(main_native_otel())

Key points for Langchain’s native OTel export:

• LangWatch acts as a backend/collector for OpenTelemetry traces generated directly by Langchain.
• Requires careful configuration of Langchain’s environment variables.
• The level of detail depends on Langchain’s native OpenTelemetry instrumentation quality.