Add Arize tracing samples - #365
Open
DABH wants to merge 2 commits into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds
arize_tracing/, a sample that sends Temporal workflow traces to Arize Phoenix (self-hosted, one container) or Arize AX through the OpenTelemetry plugin, using the OpenInference conventions Arize renders. Companion to the Langfuse sample and to Arize's own Temporal guide.Two scenarios share one telemetry module.
ticket_triage/keeps LLM calls in activities with the OpenInference OpenAI instrumentation, a custom span in workflow code, and a human approval via update.ticket_triage_agents/runs the same flow on the OpenAI Agents SDK throughOpenAIAgentsPlugin(use_otel_instrumentation=True). A small span processor gives Temporal's spans an OpenInference kind, sets the Arize session to the workflow ID, and records the activity attempt number.verify_trace.pychecks a trace through the Phoenix REST API: tree shape with span kinds, enrichment attributes, LLM token usage, activity attempts, and no duplicates. The README runbook reproduces replay stress, worker restart, activity retry, worker crash mid-activity, and reset; each was verified against Phoenix.Tests run without Phoenix, Docker, or an API key, including under the time-skipping environment. Screenshots were taken with mocked LLM calls.