Observability for xAI / Grok with Langfuse

This guide shows you how to integrate Grok with Langfuse using the OpenAI SDK.

What is Grok? Grok is X.ai’s advanced AI platform that streamlines natural language processing for intelligent application integration. Learn more at Grok Documentation.

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

Step 1: Install Dependencies

Make sure you have installed the necessary Python packages:

%pip install openai langfuse

Step 2: Set Up Environment Variables

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


# Get your Grok API key from your Grok account settings
os.environ.setdefault("GROK_API_KEY", "xai-...");

Step 3: Use Grok with the OpenAI SDK

To utilize Grok through the OpenAI SDK, we use the Langfuse drop-in replacement for OpenAI. Replace the base URL with Grok’s endpoint.

# Instead of importing openai directly:
from langfuse.openai import openai

client = openai.OpenAI(
  api_key=os.environ.get("GROK_API_KEY"),
  base_url="https://api.x.ai/v1"  # Grok's endpoint
)

Step 4: Run an Example

The following example demonstrates how to make a simple request using Grok's API. All API calls will be automatically traced by Langfuse.

response = client.chat.completions.create(
  model="grok-2-latest",
  messages=[
    {"role": "system", "content": "You are an assistant."},
    {"role": "user", "content": "What is Langfuse?"}
  ],
  name = "Grok-2-Trace"
)

print(response.choices[0].message.content)

Step 5: Enhance Tracing (Optional)

You can enhance your Grok traces:

• Add metadata, tags, log levels and user IDs to traces
• Group traces by sessions
• @observe() decorator to trace additional application logic
• Use Langfuse Prompt Management and link prompts to traces
• Add score to traces

Visit the OpenAI SDK integration docs to see more examples on passing additional parameters. Find out more about Langfuse Evaluations and Prompt Management in the Langfuse documentation.

Step 6: 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

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.

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