LangChain

Coralogix's AI Observability integrations make it easy to monitor any LangChain-powered application. With a dedicated LangChain integration, Coralogix consolidates spans emitted by OpenAI, Anthropic, AWS Bedrock, and other LangChain chat providers so teams can understand performance, drift, and tool usage without stitching logs across services.

How LangChain works

This library ships production-ready OpenTelemetry instrumentation for LangChain. It automatically hooks into LangChain's callback manager, traces chat and tool-call workflows, and records usage metrics. The integration accelerates debugging, highlights token consumption, and standardizes observability across multi-provider LangChain deployments.

Supported providers

The following providers are supported with full prompt/completion attributes:

Provider	Chat model class	System value
OpenAI	ChatOpenAI	openai
Anthropic	ChatAnthropic	anthropic
AWS Bedrock	ChatBedrock, ChatBedrockConverse, BedrockChat	aws.bedrock

Other chat model classes are still instrumented with system value langchain. A span is always created; the model name uses metadata or the provider class name when not available in standard keys.

What you need

• Python version 3.10 and above.
• Coralogix API keys.
• LangChain 1.0.0 or newer along with the provider-specific SDKs (for example langchain-openai or langchain-aws).

Ensure each underlying provider SDK (OpenAI, Anthropic, AWS Bedrock, etc.) is configured with valid credentials before enabling instrumentation.

Installation

Run the following command.

pip install "llm-tracekit-langchain"

Authentication

Exporting spans to Coralogix requires configuring OTLP credentials before enabling instrumentation. Use setup_export_to_coralogix or the corresponding environment variables to supply authentication details.

Using setup_export_to_coralogix

from llm_tracekit.langchain import setup_export_to_coralogix

setup_export_to_coralogix(
    service_name="ai-service",
    application_name="ai-application",
    subsystem_name="ai-subsystem",
    capture_content=True,
)

Using environment variables

If arguments are not passed to setup_export_to_coralogix, the helper reads the following environment variables:

• CX_TOKEN: Your Coralogix API key.
• CX_ENDPOINT: Select the ingress.:443 endpoint that corresponds to your Coralogix domain using the domain selector at the top of the page.
• CX_APPLICATION_NAME: Your application's name.
• CX_SUBSYSTEM_NAME: Your subsystem's name.

Set up tracing

Instrument

LangChain instrumentation is installed globally by wrapping BaseCallbackManager. Create an instance of LangChainInstrumentor and call instrument before instantiating your chains.

from llm_tracekit.langchain import LangChainInstrumentor

LangChainInstrumentor().instrument()

Uninstrument

To remove instrumentation, call the uninstrument method.

LangChainInstrumentor().uninstrument()

Full example

from llm_tracekit.langchain import LangChainInstrumentor, setup_export_to_coralogix
from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage

# Optional: configure sending spans to Coralogix
# Reads connection details from environment variables: CX_TOKEN, CX_ENDPOINT
setup_export_to_coralogix(
    service_name="ai-service",
    application_name="ai-application",
    subsystem_name="ai-subsystem",
    capture_content=True,
)

# Activate instrumentation
LangChainInstrumentor().instrument()

# Example LangChain usage
llm = ChatOpenAI(model="gpt-4o-mini")
messages = [HumanMessage(content="Write a short poem on open telemetry.")]
response = llm.invoke(messages)

# Pass user via config metadata
response = llm.invoke(
    messages,
    config={"metadata": {"user": "[email protected]"}}
)

Enable message content capture

By default, message content — such as prompts, completions, tool call arguments, and tool responses — is not captured.

To capture message content as span attributes, do one of the following:

• Pass capture_content=True when calling setup_export_to_coralogix.
• Set the environment variable OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT to true.

Many Coralogix AI evaluations rely on message content; enabling capture is a best practice.

Key differences from OpenTelemetry

Prompts, tool invocations, and model responses are stored as span attributes instead of log events, preserving a single correlated timeline for each LangChain run.

Semantic conventions

LangChain-specific attributes