add inbuilt functionality to choose which safety model to use prior to calling an LLM model #2397

New Issue

2025-11-11T15:06:22-06:00

GiteaMirror commented

2025-11-11 15:06:22 -06:00

Originally created by @arjunkrishna on GitHub (Oct 16, 2024).

Feature Request

Important: Before submitting a feature request, please check whether a similar issue or feature request has already been posted in the Issues or Discussions section. It's likely we're already tracking it. In case of uncertainty, initiate a discussion post first. This helps us all to efficiently focus on improving the project.

Let's collaborate respectfully. If you bring negativity, please understand our capacity to engage may be limited. If you're open to learning and communicating constructively, we're more than happy to assist you. Remember, Open WebUI is a volunteer-driven project maintained by a single maintainer, supported by our amazing contributors who also manage full-time jobs. We respect your time; please respect ours. If you have an issue, We highly encourage you to submit a pull request or to fork the project. We actively work to prevent contributor burnout to preserve the quality and continuity of Open WebUI.

Is your feature request related to a problem? Please describe.
no

Describe the solution you'd like
like we have an option to choose which embedding model to choose in openwebui, it would be nice to add a section to choose which safety model (shieldgemma/llaam-guard3) to run prior and post input and output of chosen llm model. based on the result of the output of safety model, openwebui chooses to submit/show the query/answer.

Describe alternatives you've considered
pipeline can be added to solve this issue, but an inbuild solution would be simpler for end user

Additional context
Add any other context or screenshots about the feature request here.

Originally created by @arjunkrishna on GitHub (Oct 16, 2024). # Feature Request **Important: Before submitting a feature request, please check whether a similar issue or feature request has already been posted in the Issues or Discussions section. It's likely we're already tracking it. In case of uncertainty, initiate a discussion post first. This helps us all to efficiently focus on improving the project.** **Let's collaborate respectfully. If you bring negativity, please understand our capacity to engage may be limited. If you're open to learning and communicating constructively, we're more than happy to assist you. Remember, Open WebUI is a volunteer-driven project maintained by a single maintainer, supported by our amazing contributors who also manage full-time jobs. We respect your time; please respect ours. If you have an issue, We highly encourage you to submit a pull request or to fork the project. We actively work to prevent contributor burnout to preserve the quality and continuity of Open WebUI.** **Is your feature request related to a problem? Please describe.** no **Describe the solution you'd like** like we have an option to choose which embedding model to choose in openwebui, it would be nice to add a section to choose which safety model (shieldgemma/llaam-guard3) to run prior and post input and output of chosen llm model. based on the result of the output of safety model, openwebui chooses to submit/show the query/answer. **Describe alternatives you've considered** pipeline can be added to solve this issue, but an inbuild solution would be simpler for end user **Additional context** Add any other context or screenshots about the feature request here.

GiteaMirror closed this issue