Skip to content

fix(scores): support CORRECTION score data type #1713

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
hassiebp merged 1 commit into from
Jun 16, 2026
+30 −20
Merged

fix(scores): support CORRECTION score data type #1713

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 17 additions & 11 deletions langfuse/_client/client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1786,7 +1786,9 @@ def create_score(
trace_id: Optional[str] = None,
score_id: Optional[str] = None,
observation_id: Optional[str] = None,
data_type: Optional[Literal["CATEGORICAL", "TEXT"]] = "CATEGORICAL",
data_type: Optional[
Literal["CATEGORICAL", "TEXT", "CORRECTION"]
] = "CATEGORICAL",
comment: Optional[str] = None,
config_id: Optional[str] = None,
metadata: Optional[Any] = None,
Expand Down Expand Up @@ -1816,13 +1818,13 @@ def create_score(

Args:
name: Name of the score (e.g., "relevance", "accuracy")
value: Score value (can be numeric for NUMERIC/BOOLEAN types or string for CATEGORICAL/TEXT)
value: Score value (can be numeric for NUMERIC/BOOLEAN types or string for CATEGORICAL/TEXT/CORRECTION)
session_id: ID of the Langfuse session to associate the score with
dataset_run_id: ID of the Langfuse dataset run to associate the score with
trace_id: ID of the Langfuse trace to associate the score with
observation_id: Optional ID of the specific observation to score. Trace ID must be provided too.
score_id: Optional custom ID for the score (auto-generated if not provided)
data_type: Type of score (NUMERIC, BOOLEAN, CATEGORICAL, or TEXT)
data_type: Type of score (NUMERIC, BOOLEAN, CATEGORICAL, TEXT, or CORRECTION)
comment: Optional comment or explanation for the score
config_id: Optional ID of a score config defined in Langfuse
metadata: Optional metadata to be attached to the score
Expand Down Expand Up @@ -1946,7 +1948,9 @@ def score_current_span(
name: str,
value: str,
score_id: Optional[str] = None,
data_type: Optional[Literal["CATEGORICAL", "TEXT"]] = "CATEGORICAL",
data_type: Optional[
Literal["CATEGORICAL", "TEXT", "CORRECTION"]
] = "CATEGORICAL",
comment: Optional[str] = None,
config_id: Optional[str] = None,
metadata: Optional[Any] = None,
Expand All @@ -1970,9 +1974,9 @@ def score_current_span(

Args:
name: Name of the score (e.g., "relevance", "accuracy")
value: Score value (can be numeric for NUMERIC/BOOLEAN types or string for CATEGORICAL/TEXT)
value: Score value (can be numeric for NUMERIC/BOOLEAN types or string for CATEGORICAL/TEXT/CORRECTION)
score_id: Optional custom ID for the score (auto-generated if not provided)
data_type: Type of score (NUMERIC, BOOLEAN, CATEGORICAL, or TEXT)
data_type: Type of score (NUMERIC, BOOLEAN, CATEGORICAL, TEXT, or CORRECTION)
comment: Optional comment or explanation for the score
config_id: Optional ID of a score config defined in Langfuse
metadata: Optional metadata to be attached to the score
Expand Down Expand Up @@ -2010,7 +2014,7 @@ def score_current_span(
name=name,
value=cast(str, value),
score_id=score_id,
data_type=cast(Literal["CATEGORICAL", "TEXT"], data_type),
data_type=cast(Literal["CATEGORICAL", "TEXT", "CORRECTION"], data_type),
comment=comment,
config_id=config_id,
metadata=metadata,
Expand All @@ -2036,7 +2040,9 @@ def score_current_trace(
name: str,
value: str,
score_id: Optional[str] = None,
data_type: Optional[Literal["CATEGORICAL", "TEXT"]] = "CATEGORICAL",
data_type: Optional[
Literal["CATEGORICAL", "TEXT", "CORRECTION"]
] = "CATEGORICAL",
comment: Optional[str] = None,
config_id: Optional[str] = None,
metadata: Optional[Any] = None,
Expand All @@ -2061,9 +2067,9 @@ def score_current_trace(

Args:
name: Name of the score (e.g., "user_satisfaction", "overall_quality")
value: Score value (can be numeric for NUMERIC/BOOLEAN types or string for CATEGORICAL/TEXT)
value: Score value (can be numeric for NUMERIC/BOOLEAN types or string for CATEGORICAL/TEXT/CORRECTION)
score_id: Optional custom ID for the score (auto-generated if not provided)
data_type: Type of score (NUMERIC, BOOLEAN, CATEGORICAL, or TEXT)
data_type: Type of score (NUMERIC, BOOLEAN, CATEGORICAL, TEXT, or CORRECTION)
comment: Optional comment or explanation for the score
config_id: Optional ID of a score config defined in Langfuse
metadata: Optional metadata to be attached to the score
Expand Down Expand Up @@ -2099,7 +2105,7 @@ def score_current_trace(
name=name,
value=cast(str, value),
score_id=score_id,
data_type=cast(Literal["CATEGORICAL", "TEXT"], data_type),
data_type=cast(Literal["CATEGORICAL", "TEXT", "CORRECTION"], data_type),
comment=comment,
config_id=config_id,
metadata=metadata,
Expand Down
20 changes: 12 additions & 8 deletions langfuse/_client/span.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -308,7 +308,9 @@ def score(
value: str,
score_id: Optional[str] = None,
data_type: Optional[
Literal[ScoreDataType.CATEGORICAL, ScoreDataType.TEXT]
Literal[
ScoreDataType.CATEGORICAL, ScoreDataType.TEXT, ScoreDataType.CORRECTION
]
] = ScoreDataType.CATEGORICAL,
comment: Optional[str] = None,
config_id: Optional[str] = None,
Expand All @@ -335,9 +337,9 @@ def score(

Args:
name: Name of the score (e.g., "relevance", "accuracy")
value: Score value (numeric for NUMERIC/BOOLEAN, string for CATEGORICAL/TEXT)
value: Score value (numeric for NUMERIC/BOOLEAN, string for CATEGORICAL/TEXT/CORRECTION)
score_id: Optional custom ID for the score (auto-generated if not provided)
data_type: Type of score (NUMERIC, BOOLEAN, CATEGORICAL, or TEXT)
data_type: Type of score (NUMERIC, BOOLEAN, CATEGORICAL, TEXT, or CORRECTION)
comment: Optional comment or explanation for the score
config_id: Optional ID of a score config defined in Langfuse
timestamp: Optional timestamp for the score (defaults to current UTC time)
Expand All @@ -364,7 +366,7 @@ def score(
trace_id=self.trace_id,
observation_id=self.id,
score_id=score_id,
data_type=cast(Literal["CATEGORICAL", "TEXT"], data_type),
data_type=cast(Literal["CATEGORICAL", "TEXT", "CORRECTION"], data_type),
comment=comment,
config_id=config_id,
timestamp=timestamp,
Expand Down Expand Up @@ -395,7 +397,9 @@ def score_trace(
value: str,
score_id: Optional[str] = None,
data_type: Optional[
Literal[ScoreDataType.CATEGORICAL, ScoreDataType.TEXT]
Literal[
ScoreDataType.CATEGORICAL, ScoreDataType.TEXT, ScoreDataType.CORRECTION
]
] = ScoreDataType.CATEGORICAL,
comment: Optional[str] = None,
config_id: Optional[str] = None,
Expand Down Expand Up @@ -423,9 +427,9 @@ def score_trace(

Args:
name: Name of the score (e.g., "user_satisfaction", "overall_quality")
value: Score value (numeric for NUMERIC/BOOLEAN, string for CATEGORICAL/TEXT)
value: Score value (numeric for NUMERIC/BOOLEAN, string for CATEGORICAL/TEXT/CORRECTION)
score_id: Optional custom ID for the score (auto-generated if not provided)
data_type: Type of score (NUMERIC, BOOLEAN, CATEGORICAL, or TEXT)
data_type: Type of score (NUMERIC, BOOLEAN, CATEGORICAL, TEXT, or CORRECTION)
comment: Optional comment or explanation for the score
config_id: Optional ID of a score config defined in Langfuse
timestamp: Optional timestamp for the score (defaults to current UTC time)
Expand All @@ -451,7 +455,7 @@ def score_trace(
value=cast(str, value),
trace_id=self.trace_id,
score_id=score_id,
data_type=cast(Literal["CATEGORICAL", "TEXT"], data_type),
data_type=cast(Literal["CATEGORICAL", "TEXT", "CORRECTION"], data_type),
comment=comment,
config_id=config_id,
timestamp=timestamp,
Expand Down
2 changes: 1 addition & 1 deletion langfuse/types.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ def my_evaluator(*, output: str, **kwargs) -> Evaluation:

SpanLevel = Literal["DEBUG", "DEFAULT", "WARNING", "ERROR"]

ScoreDataType = Literal["NUMERIC", "CATEGORICAL", "BOOLEAN", "TEXT"]
ScoreDataType = Literal["NUMERIC", "CATEGORICAL", "BOOLEAN", "TEXT", "CORRECTION"]

# Text scores are not supported for evals and experiments
ExperimentScoreType = Literal["NUMERIC", "CATEGORICAL", "BOOLEAN"]
Expand Down