モデルに依存しない可観測性のためのLangfuse

# pip install langfuse
from langfuse import Langfuse

langfuse = Langfuse(
    public_key='pk-lf-...',
    secret_key='sk-lf-...',
    host='https://cloud.langfuse.com'  # or your self-hosted URL
)

print('Langfuse connected:', langfuse.auth_check())

from langfuse import Langfuse

langfuse = Langfuse()

# Create a trace for one user request
trace = langfuse.trace(
    name='rag-query',
    user_id='user_123',
    session_id='session_abc',
    tags=['production', 'rag']
)

# Add a retrieval span
retrieval_span = trace.span(
    name='vector-retrieval',
    input={'query': 'What is RAG?'}
)
chunks = vector_db.search('What is RAG?')
retrieval_span.end(output={'chunks': [c['text'][:100] for c in chunks]})

# Add an LLM generation
generation = trace.generation(
    name='answer-generation',
    model='gpt-4o',
    model_parameters={'temperature': 0.0},
    input=[{'role': 'user', 'content': 'Context: ...\nQuestion: What is RAG?'}]
)
response = openai_client.chat.completions.create(model='gpt-4o', messages=[...])
generation.end(
    output=response.choices[0].message.content,
    usage={'input': response.usage.prompt_tokens, 'output': response.usage.completion_tokens}
)

from langfuse.decorators import observe, langfuse_context

# @observe wraps the function as a span automatically
@observe()
def retrieve_chunks(query: str) -> list[dict]:
    return vector_db.search(query, top_k=5)

@observe()
def generate_answer(query: str, context: str) -> str:
    response = openai_client.chat.completions.create(
        model='gpt-4o',
        messages=[
            {'role': 'system', 'content': 'Answer using the context.'},
            {'role': 'user', 'content': f'Context: {context}\nQuestion: {query}'}
        ]
    )
    # Attach LLM usage data to the current span
    langfuse_context.update_current_observation(
        usage={'input': response.usage.prompt_tokens, 'output': response.usage.completion_tokens},
        model='gpt-4o'
    )
    return response.choices[0].message.content

@observe(name='rag-pipeline')  # top-level trace
def rag_pipeline(query: str) -> str:
    chunks = retrieve_chunks(query)  # becomes a nested span
    context = '\n'.join([c['text'] for c in chunks])
    return generate_answer(query, context)  # becomes another nested span

from langfuse.decorators import observe, langfuse_context
import anthropic
from openai import OpenAI

anthropic_client = anthropic.Anthropic()
openai_client = OpenAI()

@observe()
def call_claude(prompt: str) -> str:
    response = anthropic_client.messages.create(
        model='claude-3-5-sonnet-20241022',
        max_tokens=1024,
        messages=[{'role': 'user', 'content': prompt}]
    )
    langfuse_context.update_current_observation(
        model='claude-3-5-sonnet-20241022',
        usage={'input': response.usage.input_tokens, 'output': response.usage.output_tokens}
    )
    return response.content[0].text

@observe()
def call_gpt4(prompt: str) -> str:
    response = openai_client.chat.completions.create(
        model='gpt-4o',
        messages=[{'role': 'user', 'content': prompt}]
    )
    langfuse_context.update_current_observation(model='gpt-4o',
        usage={'input': response.usage.prompt_tokens, 'output': response.usage.completion_tokens})
    return response.choices[0].message.content

# Cost data is automatically computed - no manual config
# Langfuse knows: gpt-4o input = $0.005/1K tokens, output = $0.015/1K tokens

# Add metadata to enable cost breakdown by feature
@observe(name='rag-query')
def handle_rag_query(query: str, feature: str, user_id: str) -> str:
    langfuse_context.update_current_trace(
        user_id=user_id,
        tags=[feature, 'rag'],
        metadata={'feature': feature, 'query_length': len(query)}
    )
    return rag_pipeline(query)

# In Langfuse dashboard you can now filter costs by:
# - feature: 'document_qa', 'chat', 'summarization'
# - user_id: to see which users are your most expensive
# - model: to compare gpt-4o vs gpt-4o-mini costs
# - date range: to see daily/weekly/monthly trends

from langfuse.decorators import observe, langfuse_context

@observe()
def generate_response(query: str) -> dict:
    answer = rag_pipeline(query)
    # Get the current trace ID to link feedback later
    trace_id = langfuse_context.get_current_trace_id()
    return {'answer': answer, 'trace_id': trace_id}

# Later, when user submits feedback:
def record_user_feedback(trace_id: str, score: int, comment: str):
    langfuse.score(
        trace_id=trace_id,
        name='user_satisfaction',  # score name
        value=score,               # 1 (thumbs up) or 0 (thumbs down)
        comment=comment,
        data_type='BOOLEAN'
    )

# Now in Langfuse: filter traces where user_satisfaction = 0
# to find the exact prompts and contexts that users rated negatively

from langfuse import Langfuse

langfuse = Langfuse()

def auto_score_traces():
    # Get recent unscored traces
    traces = langfuse.fetch_traces(tags=['production'], limit=50)
    
    for trace in traces.data:
        question = trace.input.get('query', '')
        answer = trace.output.get('answer', '') if trace.output else ''
        
        if not question or not answer:
            continue
        
        # LLM-as-judge scoring
        score = evaluate_relevance(question, answer)  # returns 0.0-1.0
        
        langfuse.score(
            trace_id=trace.id,
            name='auto_relevance',
            value=score,
            data_type='NUMERIC',
            comment='Automated relevance score from LLM judge'
        )

# Run this as a scheduled job every hour

from langfuse import Langfuse

langfuse = Langfuse()

# Fetch the current production prompt by name
# The prompt lives in Langfuse UI, not in your code
prompt = langfuse.get_prompt('rag-system-prompt', version='production')

# Use it in your pipeline
messages = [
    {'role': 'system', 'content': prompt.compile(context_limit=4000)},
    {'role': 'user', 'content': query}
]

response = openai_client.chat.completions.create(model='gpt-4o', messages=messages)

# The trace is automatically linked to the prompt version
# In Langfuse you can filter: show me traces using prompt v3 vs v4
# and compare their quality scores

# Self-host Langfuse with Docker Compose
# docker-compose.yml (simplified)
# version: '3'
# services:
#   langfuse:
#     image: langfuse/langfuse:2
#     ports:
#       - '3000:3000'
#     environment:
#       - DATABASE_URL=postgresql://langfuse:password@postgres/langfuse
#       - NEXTAUTH_SECRET=your-random-secret
#       - SALT=your-random-salt
#   postgres:
#     image: postgres:15
#     environment:
#       - POSTGRES_DB=langfuse
#       - POSTGRES_PASSWORD=password

# After docker-compose up, point your SDK to:
langfuse = Langfuse(
    public_key='pk-lf-your-key',
    secret_key='sk-lf-your-key',
    host='http://localhost:3000'  # your self-hosted instance
)

from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.trace.export import BatchSpanProcessor

# Configure OTel to send to Langfuse OTLP endpoint
exporter = OTLPSpanExporter(
    endpoint='https://cloud.langfuse.com/api/public/otel/v1/traces',
    headers={
        'Authorization': 'Basic ' + base64.b64encode(b'pk-lf-xxx:sk-lf-xxx').decode()
    }
)

provider = TracerProvider()
provider.add_span_processor(BatchSpanProcessor(exporter))
trace.set_tracer_provider(provider)

# Now create spans as usual - they appear in Langfuse automatically
tracer = trace.get_tracer('my-llm-app')
with tracer.start_as_current_span('rag-query') as span:
    span.set_attribute('llm.model', 'gpt-4o')
    span.set_attribute('llm.prompt_tokens', 500)
    result = rag_pipeline(query)