Files

copilot-swe-agent[bot] 3950846fa9 Add MkDocs documentation portal with Material theme and CI/CD workflow

Co-authored-by: Fu-Jie <33599649+Fu-Jie@users.noreply.github.com>

2025-12-29 10:03:23 +00:00

2.9 KiB

Raw Blame History

Gemini Manifold

Pipe v1.0.0

Integration pipeline for Google's Gemini models with full streaming support.

Overview

The Gemini Manifold pipe provides seamless integration with Google's Gemini AI models. It exposes Gemini models as selectable options in OpenWebUI, allowing you to use them just like any other model.

Features

:material-google: Full Gemini Support: Access all Gemini model variants
:material-stream: Streaming: Real-time response streaming
:material-image: Multimodal: Support for images and text
:material-shield: Error Handling: Robust error management
:material-tune: Configurable: Customize model parameters

Installation

Download the plugin file: gemini_manifold.py
Upload to OpenWebUI: Admin Panel → Settings → Functions
Configure your Gemini API key
Select Gemini models from the model dropdown

Configuration

Option	Type	Required	Description
`GEMINI_API_KEY`	string	Yes	Your Google AI Studio API key
`DEFAULT_MODEL`	string	No	Default Gemini model to use
`TEMPERATURE`	float	No	Response temperature (0-1)
`MAX_TOKENS`	integer	No	Maximum response tokens

Available Models

When configured, the following models become available:

gemini-pro - Text-only model
gemini-pro-vision - Multimodal model
gemini-1.5-pro - Latest Pro model
gemini-1.5-flash - Fast response model

Usage

After installation, go to any chat
Open the model selector dropdown
Look for models prefixed with your pipe name
Select a Gemini model
Start chatting!

Getting an API Key

Visit Google AI Studio
Create a new API key
Copy the key and paste it in the plugin configuration

!!! warning "API Key Security" Keep your API key secure. Never share it publicly or commit it to version control.

Companion Filter

For enhanced functionality, consider installing the Gemini Manifold Companion filter.

Requirements

!!! note "Prerequisites" - OpenWebUI v0.3.0 or later - Valid Gemini API key - Internet access to Google AI APIs

Troubleshooting

??? question "Models not appearing?" Ensure your API key is correctly configured and the plugin is enabled.

??? question "API errors?" Check your API key validity and quota limits in Google AI Studio.

??? question "Slow responses?" Consider using gemini-1.5-flash for faster response times.

Source Code

:fontawesome-brands-github: View on GitHub{ .md-button }

2.9 KiB Raw Blame History