Exporting Annotated Spans

This information can be used to:

build new LLM judges
form the basis for new datasets
help identify ideas for improving your application

Pulling Spans#

from phoenix.client import Clientclient = Client()spans = client.spans.get_spans_dataframe(    project_identifier="default",  # you can also pass a project id)

If you only want the spans that contain a specific annotation, you can pass in a query that filters on annotation names, scores, or labels.

from phoenix.client import Clientfrom phoenix.client.types.spans import SpanQueryclient = Client()query = SpanQuery().where("annotations['correctness']")spans = client.spans.get_spans_dataframe(    query=query,    project_identifier="default",  # you can also pass a project id)

The queries can also filter by annotation scores and labels.

from phoenix.client import Clientfrom phoenix.client.types.spans import SpanQueryclient = Client()query = SpanQuery().where("annotations['correctness'].score == 1")# query = SpanQuery().where("annotations['correctness'].label == 'correct'")spans = client.spans.get_spans_dataframe(    query=query,    project_identifier="default",  # you can also pass a project id)

To filter spans by trace-level annotations (annotations attached to the trace rather than an individual span), use trace_annotations in place of annotations. Spans are returned when the trace they belong to carries a matching annotation.

from phoenix.client import Clientfrom phoenix.client.types.spans import SpanQueryclient = Client()query = SpanQuery().where("trace_annotations['quality'].score >= 0.5")# query = SpanQuery().where("trace_annotations['quality'].label == 'good'")spans = client.spans.get_spans_dataframe(    query=query,    project_identifier="default",  # you can also pass a project id)

This spans dataframe can be used to pull associated annotations.

annotations = client.spans.get_span_annotations_dataframe(    spans_dataframe=spans,    project_identifier="default",)

Instead of an input dataframe, you can also pass in a list of ids:

annotations = client.spans.get_span_annotations_dataframe(    span_ids=list(spans.index),    project_identifier="default",)

The annotations and spans dataframes can be easily joined to produce a one-row-per-annotation dataframe that can be used to analyze the annotations!

annotations.join(spans, how="left")