Create a New LLM Monitoring Application¶

1. Navigate to Agent Monitoring > Application List.
2. Click "Create Application".
3. Select the LLM Monitoring Application tab.

Integration Type¶

On the Create Application page, the default integration is Langfuse:

Access Configuration¶

Three options are available here:

Integrate Python

Integrate JS/TS

Integrate Other Models/Frameworks

Integrate Python¶

1. Install Dependencies¶

pip install langfuse

2. Initialize the Client¶

LANGFUSE_PUBLIC_KEY="app_id"
LANGFUSE_SECRET_KEY="llm_bb0f30d.....66eec"
LANGFUSE_HOST="https://llm-openway.guance.com"

from langfuse import Langfuse
langfuse = Langfuse()

from langfuse import Langfuse
langfuse = Langfuse(
  public_key="app_id",
  secret_key="llm_bb0f30d.....66eec",
  host="https://llm-openway.guance.com"
)

3. Verify Connection¶

You can use langfuse.auth_check() to verify successful integration. This is not recommended in production because it increases application latency.

from langfuse import Langfuse
# Initialize (by constructor parameters)
langfuse = Langfuse(
    public_key="app_id",
    secret_key="llm_d9f06c320a9***6e9807",
    host="https://llm-openway.guance.com"
)
# Verify connection. This is a synchronous call, not recommended for production. This method is only for configuration validation.
if langfuse.auth_check():
    print("Langfuse client is authenticated and ready!")

If integration fails, you may encounter the following error:

langfuse.api.resources.commons.errors.unauthorized_error.UnauthorizedError: status_code: 401, body: {}

This error usually indicates that the App ID or Client Token is incorrect. Please check your parameter configuration.

For more details and end-to-end examples, see Python.

Integrate JS/TS¶

1. Install Dependencies¶

npm install @langfuse/tracing @langfuse/otel @opentelemetry/sdk-node

Click to view more package information.

2. Register Credentials¶

Set the following environment variables in your application environment. Ensure there is a .env file in your project root and a package like dotenv to load the variables.

LANGFUSE_SECRET_KEY="llm_122f6b85d0c7454fa0f9*****d360"
LANGFUSE_PUBLIC_KEY="pk-lf-..."
LANGFUSE_BASE_URL="https://llm-openway.guance.com",

3. Initialize OpenTelemetry¶

The Langfuse SDK tracing is built on OpenTelemetry, so you need to set up the OpenTelemetry SDK. The LangfuseSpanProcessor is a key component for sending traces to Langfuse.

import { NodeSDK } from "@opentelemetry/sdk-node";
import { LangfuseSpanProcessor } from "@langfuse/otel";
const sdk = new NodeSDK({
  spanProcessors: [new LangfuseSpanProcessor()],
});
sdk.start();

Click to view the Ollama integration example.

For more details and end-to-end examples, see JS/TS.

Integrate Others¶

For integrations with other models/frameworks, such as DeepSeek, Ollama, LangChain, Dify, etc., refer to the Langfuse official documentation for configuration.

LangChain OpenTelemetry Integration¶

Supports integrating LangChain applications via OpenTelemetry. After integration, you can view call traces, inputs, outputs, and token consumption in the LLM monitoring application.

The system parses OpenTelemetry gen_ai related attributes and displays:

• Input: The input content of the model call;
• Output: The output content returned by the model;
• Token: Input, output, and total token consumption;
• Model, service, call status, and other related information.

Fill in Variables in Code¶

Fill in the following information on the right side of the page:

After confirming the information is correct, click Create to complete the LLM monitoring application integration.