Observability for Portkey LLM Gateway with Langfuse

This guide shows you how to integrate Portkey's AI gateway with Langfuse. Portkey's API endpoints are fully compatible with the OpenAI SDK, allowing you to trace and monitor your AI applications seamlessly.

What is Portkey? Portkey is an AI gateway that provides a unified interface to interact with 250+ AI models, offering advanced tools for control, visibility, and security in your Generative AI apps.

What is Langfuse? Langfuse is an open source AI engineering platform that helps teams trace LLM calls, monitor performance, and debug issues in their AI applications.

Step 1: Install Dependencies

%pip install openai langfuse portkey_ai

Step 2: Set Up Environment Variables

Next, set up your Langfuse API keys. You can get these keys by signing up for a free Langfuse Cloud account or by self-hosting Langfuse. These environment variables are essential for the Langfuse client to authenticate and send data to your Langfuse project.

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
# Other Langfuse data regions include 🇺🇸 US: https://us.cloud.langfuse.com, 🇯🇵 Japan: https://jp.cloud.langfuse.com and ⚕️ HIPAA: https://hipaa.cloud.langfuse.com

from langfuse import get_client

get_client().auth_check()

True

Step 3: Use Langfuse OpenAI Drop-in Replacement

Next, you can use Langfuse’s OpenAI-compatible client (from langfuse.openai import OpenAI) to trace all requests sent through the Portkey gateway. For detailed setup instructions on the LLM gateway and virtual LLM keys, refer to the Portkey documentation.

from langfuse.openai import OpenAI
from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL

client = OpenAI(
    api_key="xxx", #Since we are using a virtual key we do not need this
    base_url = PORTKEY_GATEWAY_URL,
    default_headers = createHeaders(
    api_key = "***",
    virtual_key = "***"
    )
)

Step 4: Run an Example

response = client.chat.completions.create(
  model="gpt-4o",  # Or any model supported by your chosen provider
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What are the benefits of using an AI gateway?"},
  ],
)
print(response.choices[0].message.content)

# Flush via global client
langfuse = get_client()
langfuse.flush()

Step 5: See Traces in Langfuse

After running the example, log in to Langfuse to view the detailed traces, including:

• Request parameters
• Response content
• Token usage and latency metrics
• LLM model information through Portkey gateway

Public example trace link in Langfuse

Interoperability with the Python SDK

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

Decorator Context Manager

The @observe() decorator provides a convenient way to automatically wrap your instrumented code and 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")

Learn more about using the Decorator in the Langfuse SDK instrumentation docs.

Context Manager

The Context Manager allows you to wrap your instrumented code using context managers (with with statements), which allows you to add additional attributes to the observation.

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

First, enable debug mode in the Python SDK:

export LANGFUSE_DEBUG="True"

Then run your application and check the debug logs:

• OTel observations appear in the logs: Your application is instrumented correctly but observations are not reaching Langfuse. To resolve this:

1. Call langfuse.flush() at the end of your application to ensure all observations are exported.
2. Verify that you are using the correct API keys and base URL.

• No OTel spans in the logs: Your application is not instrumented correctly. Make sure the instrumentation runs before your application code.

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