Span annotations can be an extremely valuable basis for improving your application. The Phoenix client provides useful ways to pull down spans and their associated annotations.
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.