- Issue created by @gxleano
- Merge request !633Issue #3526710: Add AiUnsafePromptException exception into the IndexItems()... β (Merged) created by gxleano
- πͺπΈSpain gxleano CΓ‘ceres
After applying the changes everything works as expected.
At the end of the indexation we will get an error message pointing to the logs, where we could check which content has been flagged by moderation.
See evidences:
- π¬π§United Kingdom scott_euser
This seems sensible to do rather than allowing proceeding. I will try to give this a test in the next several days.
Somewhat related β¨ Allow skipping of moderations for some embeddings (controlled input) Active but I think both ultimately can go in.
-
scott_euser β
committed fddab040 on 1.1.x authored by
gxleano β
Issue #3526710 by gxleano: [Error] The Prompt is unsafe: The prompt was...
-
scott_euser β
committed fddab040 on 1.1.x authored by
gxleano β
-
scott_euser β
committed 0223cd4c on 1.2.x authored by
gxleano β
Issue #3526710 by gxleano: [Error] The Prompt is unsafe: The prompt was...
-
scott_euser β
committed 0223cd4c on 1.2.x authored by
gxleano β
-
scott_euser β
committed fddab040 on 1.2.x authored by
gxleano β
Issue #3526710 by gxleano: [Error] The Prompt is unsafe: The prompt was...
-
scott_euser β
committed fddab040 on 1.2.x authored by
gxleano β
Automatically closed - issue fixed for 2 weeks with no activity.
- π©πͺGermany marcus_johansson
kristen pol β credited marcus_johansson β .
- πΊπΈUnited States Kristen Pol Santa Cruz, CA, USA
crediting scott and marcus_johansson
- Status changed to Fixed
19 days ago 7:49am 7 August 2025 A side question guys, on what basis a content gets flagged? what prompt are we talking about here? I am getting this when using Pinecone to index
- π©πͺGermany marcus_johansson
@doxigo - If its openai, its the actual chunk. So if that has something that flags the OpenAI moderation.