Application List¶

In the Application List, you can view information about applications created under various integrated application frameworks.

Concepts¶

Create Application¶

Go to the Create Application page, which currently supports Integrating Langfuse by default:

1. Define the application name and application ID;

2. System automatically generates configuration parameters;

3. A Client Token is generated by default, which you can replace as needed;

4. Select the integration configuration;

5. Click "Create".

After successful creation, you can go to the "Application List" page to view it.

Integration Configuration¶

Generally supports three types 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 if the integration was successful. It is not recommended to use this in production as it increases application latency.

from langfuse import Langfuse
# Initialize (via parameter construction)
langfuse = Langfuse(
  public_key="app_id",
  secret_key="llm_bb0f30d.....66eec",
  host="https://llm-openway.guance.com"
)
# Verify connection, this is a synchronous call, not recommended for production, this method is only for verifying configuration
if langfuse.auth_check():
  print("Langfuse client is authenticated and ready!")

If the integration fails, you might 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, refer to 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 you have a .env file in your project root directory and a package like dotenv to load the variables.

LANGFUSE_SECRET_KEY="llm_122f6b85d0c7454fa0f9*****d360"
LANGFUSE_PUBLIC_KEY="pk-lf-..."
LANGFUSE_BASE_URL="http://testing-openway.dataflux.cn",

3. Initialize OpenTelemetry

Langfuse SDK tracing is built on OpenTelemetry, so you need to set up the OpenTelemetry SDK. The LangfuseSpanProcessor is the 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, refer to JS/TS.

Integrate Others¶

If you need to integrate other models/frameworks, such as DeepSeek, Ollama, LangChain, Dify, etc., refer to the Langfuse Official Complete Documentation for configuration.

Application List¶

In the Application List, you can view information such as the application name, call count, error rate, total tokens, P50/P75 duration, etc.

You can manage the list through the following operations:

• Search and locate by application name;

• Filter by selecting a time range using the Time Widget;

• Edit/Delete applications;

• Click on a single application to directly jump to the Explorer page with that application as the query condition.

Further Reading¶