Observability for Qwen with Langfuse

This notebook shows how to trace Qwen API calls with Langfuse using the OpenAI SDK drop-in replacement.

What is Qwen? Qwen is a family of large language models developed by Alibaba Cloud, offering models like Qwen-Plus, Qwen-Max, and Qwen-Turbo through an OpenAI-compatible API.

What is Langfuse? Langfuse is an open-source AI engineering platform that helps teams trace, debug, and evaluate their LLM applications. Use Langfuse Cloud (hosted by Langfuse, free tier, no infrastructure to run) or self-host it.

Step 1: Install Dependencies

%pip install openai langfuse

Step 2: Set Up Environment Variables

Get your Langfuse keys from the project settings in Langfuse Cloud or set up self-hosting.

import os

# Get keys for your project from the project settings page: https://cloud.langfuse.com
os.environ.setdefault("LANGFUSE_PUBLIC_KEY", "pk-lf-...");
os.environ.setdefault("LANGFUSE_SECRET_KEY", "sk-lf-...");
os.environ.setdefault("LANGFUSE_BASE_URL", "https://cloud.langfuse.com"); # 🇪🇺 EU region
# os.environ.setdefault("LANGFUSE_BASE_URL", "https://us.cloud.langfuse.com") # 🇺🇸 US region

os.environ.setdefault("DASHSCOPE_API_KEY", "sk-...");  # Get your API key from https://qwen.ai/apiplatform

Step 3: Use Langfuse OpenAI Drop-in Replacement

Instead of importing openai directly, import it from langfuse.openai. All calls through this client are automatically traced in Langfuse.

The Qwen API is OpenAI-compatible, so we just point the client at the DashScope endpoint.

import os
from langfuse.openai import openai

client = openai.OpenAI(
    api_key=os.environ.get("DASHSCOPE_API_KEY"),
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

Step 4: Run an Example

Send a chat completion request to a Qwen model. The trace will appear in your Langfuse dashboard automatically.

response = client.chat.completions.create(
    model="qwen3.6-plus",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What makes open-source AI models important?"},
    ],
    name="Qwen-Trace",
)
print(response.choices[0].message.content)

Step 5: View Traces in Langfuse

After running the example, open your Langfuse dashboard to see the full trace including prompts, completions, tool calls, token usage, and latency.

Example trace in Langfuse

Interoperability with the Python SDK

You can use this integration together with the Langfuse SDKs to add additional attributes to the observation.

from langfuse import observe, propagate_attributes, get_client

langfuse = get_client()

@observe()
def my_llm_pipeline(input):
    # Add additional attributes (user_id, session_id, metadata, version, tags) to all spans created within this execution scope
    with propagate_attributes(
        user_id="user_123",
        session_id="session_abc",
        tags=["agent", "my-observation"],
        metadata={"email": "user@langfuse.com"},
        version="1.0.0"
    ):

        # YOUR APPLICATION CODE HERE
        result = call_llm(input)

        return result

# Run the function
my_llm_pipeline("Hi")

from langfuse import get_client, propagate_attributes

langfuse = get_client()

with langfuse.start_as_current_observation(
    as_type="span",
    name="my-observation",
    trace_context={"trace_id": "abcdef1234567890abcdef1234567890"},  # Must be 32 hex chars
) as observation:

    # Add additional attributes (user_id, session_id, metadata, version, tags)
    # to all observations created within this execution scope
    with propagate_attributes(
        user_id="user_123",
        session_id="session_abc",
        metadata={"experiment": "variant_a", "env": "prod"},
        version="1.0",
    ):
        # YOUR APPLICATION CODE HERE
        result = call_llm("some input")

# Flush events in short-lived applications
langfuse.flush()

Troubleshooting

export LANGFUSE_DEBUG="True"

Next Steps

Once you have instrumented your code, you can manage, evaluate and debug your application:

Manage prompts in Langfuse Add evaluation scores Run LLM-as-a-judge Evaluators Create datasets Create custom dashboards Test queries in the Playground