Span

class opik.api_objects.span.Span(id: str, trace_id: str, project_name: str, message_streamer: Streamer, parent_span_id: str | None = None)

Bases: object

__init__(id: str, trace_id: str, project_name: str, message_streamer: Streamer, parent_span_id: str | None = None)

A Span object. This object should not be created directly, instead use the span method of a Trace (opik.Opik.span()) or another Span (opik.Span.span()).

end(end_time: datetime | None = None, metadata: Dict[str, Any] | None = None, input: Dict[str, Any] | None = None, output: Dict[str, Any] | None = None, tags: List[str] | None = None, usage: UsageDict | None = None) → None

End the span and update its attributes.

This method is similar to the update method, but it automatically computes the end time if not provided.

Parameters:

• end_time – The end time of the span. If not provided, the current time will be used.

• metadata – Additional metadata to be associated with the span.

• input – The input data for the span.

• output – The output data for the span.

• tags – A list of tags to be associated with the span.

• usage – Usage information for the span.

Returns:

None

update(end_time: datetime | None = None, metadata: Dict[str, Any] | None = None, input: Dict[str, Any] | None = None, output: Dict[str, Any] | None = None, tags: List[str] | None = None, usage: UsageDict | None = None, model: str | None = None, provider: str | None = None) → None

Update the span attributes.

Parameters:

• end_time – The end time of the span.

• metadata – Additional metadata to be associated with the span.

• input – The input data for the span.

• output – The output data for the span.

• tags – A list of tags to be associated with the span.

• usage – Usage information for the span.

• model – The name of LLM.

• provider – The provider of LLM.

Returns:

None

span(id: str | None = None, name: str | None = None, type: Literal['general', 'tool', 'llm'] = 'general', start_time: datetime | None = None, end_time: datetime | None = None, metadata: Dict[str, Any] | None = None, input: Dict[str, Any] | None = None, output: Dict[str, Any] | None = None, tags: List[str] | None = None, usage: UsageDict | None = None, model: str | None = None, provider: str | None = None) → Span

Create a new child span within the current span.

Parameters:

• id – The ID of the span, should be in UUIDv7 format. If not provided, a new ID will be generated.

• name – The name of the span.

• type – The type of the span. Defaults to “general”.

• start_time – The start time of the span. If not provided, current time will be used.

• end_time – The end time of the span.

• metadata – Additional metadata to be associated with the span.

• input – The input data for the span.

• output – The output data for the span.

• tags – A list of tags to be associated with the span.

• usage – Usage information for the span.

• model – The name of LLM (in this case type parameter should be == llm)

• provider – The provider of LLM.

Returns:

The created child span object.

Return type:

Span

log_feedback_score(name: str, value: float, category_name: str | None = None, reason: str | None = None) → None

Log a feedback score for the span.

Parameters:

• name – The name of the feedback score.

• value – The value of the feedback score.

• category_name – The category name for the feedback score.

• reason – The reason for the feedback score.

Returns:

None

get_distributed_trace_headers() → DistributedTraceHeadersDict

Returns headers dictionary to be passed into tracked function on remote node.