PAIR-code/what-if-tool

Error message handling when remote model fails

Open

#84 opened on May 5, 2020

View on GitHub
 (0 comments) (0 reactions) (1 assignee)HTML (843 stars) (158 forks)batch import
enhancementgood first issue

Description

When a TF serving model returns a failure instead of a prediction, pass the failure string to the front-end for display instead of the generic http error we see now.

Contributor guide

Tech stack
tensorflowhtmljavascript
Domain
frontendbackend
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
blocked
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Basic knowledge of TensorFlow ServingFamiliarity with the What If Tool codebase
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40
Research direction
Investigate the backend code that communicates with TF Serving to identify where model failures occur. Look for error handling in the frontend that currently shows generic HTTP errors. Consider how to forward the failure string from the backend response to the frontend display. The issue is assigned to a user (no PR linked), so contacting the assignee to check status may be necessary. Relevant files likely include server side prediction handler and front end error message component.