Observability for Fireworks AI with Langfuse
This guide shows you how to integrate Fireworks AI with Langfuse. Fireworks AI’s API endpoints are fully compatible with the OpenAI SDK, allowing you to trace and monitor your AI applications seamlessly.
What is Fireworks AI? Fireworks AI is a platform that provides API access to state-of-the-art open-source and proprietary AI models with OpenAI-compatible endpoints.
What is Langfuse? Langfuse is an open source LLM engineering platform that helps teams trace API calls, monitor performance, and debug issues in their AI applications.
Step 1: Install Dependencies
%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["LANGFUSE_PUBLIC_KEY"] = "pk-lf-..."
os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-..."
os.environ["LANGFUSE_HOST"] = "https://cloud.langfuse.com" # 🇪🇺 EU region
# os.environ["LANGFUSE_HOST"] = "https://us.cloud.langfuse.com" # 🇺🇸 US region
# Set your Fireworks API details
os.environ["FIREWORKS_AI_API_BASE"] = "https://api.fireworks.ai/inference/v1"
os.environ["FIREWORKS_AI_API_KEY"] = "fw_..."
Step 3: Use Langfuse OpenAI Drop-in Replacement
from langfuse.openai import openai
client = openai.OpenAI(
api_key=os.environ.get("FIREWORKS_AI_API_KEY"),
base_url=os.environ.get("FIREWORKS_AI_API_BASE")
)
Step 4: Run an Example
response = client.chat.completions.create(
model="accounts/fireworks/models/llama-v3p1-8b-instruct",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Why is open source important?"},
],
name = "Fireworks-AI-Trace" # name of the trace
)
print(response.choices[0].message.content)
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
Interoperability with the Python SDK
You can use this integration together with the Langfuse Python SDK to add additional attributes to the trace.
The @observe()
decorator provides a convenient way to automatically wrap your instrumented code and add additional attributes to the trace.
from langfuse import observe, get_client
langfuse = get_client()
@observe()
def my_instrumented_function(input):
output = my_llm_call(input)
langfuse.update_current_trace(
input=input,
output=output,
user_id="user_123",
session_id="session_abc",
tags=["agent", "my-trace"],
metadata={"email": "[email protected]"},
version="1.0.0"
)
return output
Learn more about using the Decorator in the Python SDK docs.
Next Steps
Once you have instrumented your code, you can manage, evaluate and debug your application: