[Error] The Prompt is unsafe: The prompt was flagged by the moderation model, stop the indexation

Created on 27 May 2025, 8 days ago

Problem / Motivation

When indexing content from the Search API using VDB, if any content is flagged as unsafe, the entire indexing process is halted. This can disrupt operations and prevent the successful indexing of valid, safe content.

Proposed Resolution

Rather than stopping the indexing process entirely when unsafe content is encountered, the system should simply skip the unsafe content and continue indexing the remaining valid items.

🐛 Bug report
Status

Active

Version

1.1

Component

AI Search

Created by

🇪🇸Spain gxleano Cáceres

Live updates comments and jobs are added and updated live.
Sign in to follow issues

Merge Requests

Comments & Activities

Production build 0.71.5 2024