Langfuse

Example requires langfuse v3.0.0

import os
from langfuse import observe, get_client
from root import RootSignals 

# Initialize Langfuse client using environment variables
# LANGFUSE_SECRET_KEY, LANGFUSE_PUBLIC_KEY, LANGFUSE_HOST
langfuse = get_client()

# Initialize RootSignals client
rs = RootSignals()

Integration

observe(name="explain_concept_generation") # Name for traces in Langfuse UI
def explain_concept(topic: str) -> tuple[str | None, str | None]: # Returns content and trace_id
    # Get the trace_id for the current operation, created by @observe
    current_trace_id = langfuse.get_current_trace_id()
   
    prompt = prompt_template.format(question=topic)
    response_obj = client.chat.completions.create(
        messages=[{"role": "user", "content": prompt}],
        model="gpt-4",
    )
    content = response_obj.choices.message.content    
    return content, current_trace_id

def evaluate_concept(request: str, response: str, trace_id: str) -> None:

    # Invoke a specific Root Signals judge
    result = rs.judges.run(
        judge_id="4d369224-dcfa-45e9-939d-075fa1dad99e", 
        request=request,  # The input/prompt provided to the LLM
        response=response, # The LLM's output to be evaluated
    )

    # Iterate through evaluation results and log them as Langfuse scores
    for eval_result in result.evaluator_results:
        langfuse.create_score(
            trace_id=trace_id,                   # Links score to the specific Langfuse trace
            name=eval_result.evaluator_name,     # Name of the Root Signals evaluator (e.g., "Truthfulness")
            value=eval_result.score,             # Numerical score from the evaluator
            comment=eval_result.justification,   # Explanation for the score
        )
       
         
    

Table: Mapping Root Signals Output to Langfuse Score Parameters

Root Signals	Langfuse	Description in Langfuse Context
evaluator_name	name	The name of the evaluation criterion (e.g., "Hallucination," "Conciseness"). Used for identifying and filtering scores.
score	value	The numerical score assigned by the Root Signals evaluator.
justification	comment	The textual explanation from Root Signals for the score, providing qualitative insight into the evaluation

Done. Now you can explore detailed traces and metrics in the Langfuse dashboard.