Langfuse

export LANGFUSE_PUBLIC_KEY=pk-lf-...
export LANGFUSE_SECRET_KEY=sk-lf-...

from upsonic import Agent, Task
from upsonic.integrations.langfuse import Langfuse

langfuse = Langfuse()
agent = Agent("anthropic/claude-sonnet-4-6", instrument=langfuse)

task = Task(description="What is 2 + 2?")
agent.print_do(task)

langfuse.shutdown()

from upsonic import Agent, Task
from upsonic.integrations.langfuse import Langfuse
from upsonic.tools import tool

@tool
def get_weather(city: str) -> str:
    """Get the current weather for a city."""
    return f"Sunny in {city}, 22°C"

langfuse = Langfuse(
    public_key="pk-lf-abc123",
    secret_key="sk-lf-xyz789",
    region="us",                  # "eu" (default) or "us"
    service_name="my-agent",
    include_content=True,         # include prompts/responses (default)
)

agent = Agent(
    "anthropic/claude-sonnet-4-6",
    instrument=langfuse,
    session_id="chat-session-001",
    user_id="user@example.com",
    tools=[get_weather],
)

task = Task(description="What is the weather in Paris?")
agent.print_do(task)

langfuse.shutdown()

import asyncio
from upsonic import Agent, Task
from upsonic.integrations.langfuse import Langfuse
from upsonic.eval import AccuracyEvaluator

langfuse = Langfuse()

agent = Agent("anthropic/claude-sonnet-4-6", instrument=langfuse)
judge = Agent("anthropic/claude-sonnet-4-6")

evaluator = AccuracyEvaluator(
    judge_agent=judge,
    agent_under_test=agent,
    query="What is the capital of France?",
    expected_output="Paris",
    langfuse=langfuse,
    langfuse_dataset_name="my-eval-dataset",  # optional, default: "accuracy-eval"
    langfuse_run_name="run-v1",               # optional, default: auto-generated
)

result = asyncio.run(evaluator.run())
print(f"Score: {result.average_score}/10")

langfuse.shutdown()

import asyncio
from upsonic import Agent
from upsonic.integrations.langfuse import Langfuse
from upsonic.eval import AccuracyEvaluator

langfuse = Langfuse()
agent = Agent("anthropic/claude-sonnet-4-6", instrument=langfuse)
judge = Agent("anthropic/claude-sonnet-4-6")

evaluator = AccuracyEvaluator(
    judge_agent=judge,
    agent_under_test=agent,
    query="What is 10 + 5? Reply with just the number.",
    expected_output="15",
    num_iterations=3,
    langfuse=langfuse,
    langfuse_dataset_name="math-eval",
)

result = asyncio.run(evaluator.run())
print(f"Average score: {result.average_score}/10")
print(f"Iterations: {len(result.evaluation_scores)}")

langfuse.shutdown()