[PR #191] [MERGED] Add Gemini Manifold Pipeline Safety Settings #351

New issue

Closed

opened 2026-10-18 21:05:15 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-18 21:05:15 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/open-webui/pipelines/pull/191
Author: @justinh-rahb
Created: 8/1/2024
Status: ✅ Merged
Merged: 8/1/2024
Merged by: @justinh-rahb

Base: main ← Head: gemini-permissive-safety

📝 Commits (1)

7b784bc Add permissive safety valve to Gemini Manifold

📊 Changes

1 file changed (+16 additions, -4 deletions)

View changed files

📝 examples/pipelines/providers/google_manifold_pipeline.py (+16 -4)

📄 Description

This PR introduces a new configurable option for the Gemini Manifold pipeline, providing users with greater flexibility in managing content safety settings:

Added a new valve USE_PERMISSIVE_SAFETY (default: false) to the pipeline configuration.
When enabled, this setting applies the most permissive safety thresholds across all harm categories.
Users can now toggle between permissive and default safety settings without code modifications.

Key benefits:

Reduces unexpected errors for benign prompts that might trigger overly cautious filters.
Allows advanced users to handle content moderation at the application level if desired.
Maintains the option to use Google's default safety settings.

This change aims to balance user freedom with responsible AI use, giving Open-WebUI users more control over their interaction with the Gemini models while preserving the option for stricter content filtering when needed.

Caution

Note: Users should be aware of and comply with Google's usage policies and any applicable regulations when adjusting these settings.

Addresses:

#177

Credit:

@rotemdan for the code snippet in #177

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/pipelines/pull/191 **Author:** [@justinh-rahb](https://github.com/justinh-rahb) **Created:** 8/1/2024 **Status:** ✅ Merged **Merged:** 8/1/2024 **Merged by:** [@justinh-rahb](https://github.com/justinh-rahb) **Base:** `main` ← **Head:** `gemini-permissive-safety` --- ### 📝 Commits (1) - [`7b784bc`](https://github.com/open-webui/pipelines/commit/7b784bcdfee0bb02159ba3f9a745eaa6b22f9e0d) Add permissive safety valve to Gemini Manifold ### 📊 Changes **1 file changed** (+16 additions, -4 deletions) <details> <summary>View changed files</summary> 📝 `examples/pipelines/providers/google_manifold_pipeline.py` (+16 -4) </details> ### 📄 Description This PR introduces a new configurable option for the Gemini Manifold pipeline, providing users with greater flexibility in managing content safety settings: 1. Added a new valve `USE_PERMISSIVE_SAFETY` (default: false) to the pipeline configuration. 2. When enabled, this setting applies the most permissive safety thresholds across all harm categories. 3. Users can now toggle between permissive and default safety settings without code modifications. #### Key benefits: - Reduces unexpected errors for benign prompts that might trigger overly cautious filters. - Allows advanced users to handle content moderation at the application level if desired. - Maintains the option to use Google's default safety settings. This change aims to balance user freedom with responsible AI use, giving Open-WebUI users more control over their interaction with the Gemini models while preserving the option for stricter content filtering when needed. > [!CAUTION] > ***Note: Users should be aware of and comply with Google's usage policies and any applicable regulations when adjusting these settings.*** #### Addresses: - #177 #### Credit: @rotemdan for the code snippet in #177 --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-18 21:05:15 +00:00