Skip to main content

​
Scores

Add numeric, boolean, or categorical scores to any trace.

​
Create Scores

import os
import time
import uuid
from upsonic import Agent, Task
from upsonic.integrations.langfuse import Langfuse

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

# Run the agent and get the trace ID
result = agent.do("What is the weather in Paris?", return_output=True)
trace_id = result.trace_id
time.sleep(8)  # wait for trace ingestion

# Numeric score (0-1)
langfuse.score(trace_id, "quality", 0.95)

# Boolean score
langfuse.score(trace_id, "factual", 1, data_type="BOOLEAN", comment="Correct answer")

# Categorical score
langfuse.score(trace_id, "sentiment", "positive", data_type="CATEGORICAL")

# Score with all parameters
score_id = str(uuid.uuid4())
langfuse.score(
    trace_id,
    "completeness",
    0.9,
    data_type="NUMERIC",
    score_id=score_id,
    metadata={"reviewer": "dogan", "round": 1},
    environment="production",
    comment="Thorough answer",
)

langfuse.shutdown()
Langfuse trace detail with numeric, boolean, and categorical scores

​
Upsert a Score

Pass the same score_id to update an existing score: 
import os
import time
import uuid
from upsonic import Agent, Task
from upsonic.integrations.langfuse import Langfuse

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

result = agent.do("What is 2 + 2?", return_output=True)
trace_id = result.trace_id
time.sleep(8)

score_id = str(uuid.uuid4())
langfuse.score(trace_id, "completeness", 0.9, score_id=score_id, comment="First review")

# Update the same score by passing the same score_id
langfuse.score(trace_id, "completeness", 0.75, score_id=score_id, comment="Revised after re-read")

langfuse.shutdown()

​
Query Scores

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

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

result = agent.do("Hello!", return_output=True)
trace_id = result.trace_id
time.sleep(8)

langfuse.score(trace_id, "quality", 0.95)
time.sleep(10)  # Langfuse ingestion is eventually consistent; allow enough time before querying by trace_id

# By trace
scores = langfuse.get_scores(trace_id=trace_id)
print(f"Scores for trace: {len(scores['data'])}")

# By name and date
quality_scores = langfuse.get_scores(name="quality", from_timestamp="2026-03-01T00:00:00Z")

# By source and limit
api_scores = langfuse.get_scores(source="API", limit=5)

# By data type
bool_scores = langfuse.get_scores(data_type="BOOLEAN", name="factual")

langfuse.shutdown()

​
Delete a Score

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

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

result = agent.do("Hello!", return_output=True)
trace_id = result.trace_id
time.sleep(8)

score = langfuse.score(trace_id, "quality", 0.5)
time.sleep(2)

langfuse.delete_score(score["id"])
print("Score deleted")

langfuse.shutdown()