owndev/Open-WebUI-Functions

Open-WebUI-Functions is a collection of custom pipelines, filters, and integrations designed to enhance Open WebUI. These functions enable seamless interactions with Azure AI, N8N, Google Gemini and other AI models, providing dynamic request handling, preprocessing, and automation.

What it solves

Open-WebUI-Functions provides a set of reusable Python functions to extend the capabilities of Open WebUI. It solves the problem of connecting Open WebUI to various external AI providers, automating workflows, and adding custom data processing logic without needing to modify the core Open WebUI codebase.

How it works

The project consists of Python-based pipelines and filters that can be pasted directly into the Open WebUI admin panel.

  • Pipelines act as intermediaries that connect Open WebUI to external AI models (like Azure AI, Google Gemini, and Infomaniak) or automation platforms (like N8N).
  • Filters allow for the preprocessing and post-processing of data, such as tracking token usage and response times or integrating search tools.
  • Security is handled via a built-in encryption mechanism that secures API keys using the WEBUI_SECRET_KEY environment variable.

Who it’s for

This is for administrators of Open WebUI instances who want to integrate professional AI services, implement automation via N8N, or monitor AI interaction performance.

Highlights

  • Broad Provider Support: Native integrations for Azure AI Foundry, Google Gemini (including thinking/reasoning and video generation via Veo), and Infomaniak.
  • N8N Integration: Connects AI chats to N8N webhooks for complex workflow automation with tool usage visibility.
  • Advanced Gemini Features: Supports multi-image history, configurable thinking budgets, and high-resolution image/video generation.
  • Azure AI RAG: Integration with Azure Search for enhanced document retrieval and rich citation cards.
  • Performance Tracking: A dedicated filter for measuring response times and token usage with optional Azure Log Analytics export.

Related

  • Project
    Amm1rr/WebAI-to-API

    WebAI‑to‑API is a self‑hosted bridge that runs Google Gemini (via web API or a Playwright‑driven browser) and exposes it through OpenAI‑compatible endpoints, with a local dashboard and Docker support.

  • Project
    Haervwe/open-webui-tools

    A comprehensive collection of 20+ tools, function pipes, and filters for Open WebUI that adds academic research, multi-modal generation, and autonomous agent capabilities.

  • Project
    Sophomoresty/gemini-web2api

    gemini‑web2api is a Python server that proxies Google Gemini’s private web API and presents it as an OpenAI‑compatible endpoint (`/v1/chat/completions`, `/v1/models`, etc.). It supports optional API‑key auth, streaming, function calling, image input, multiple Gemini model aliases, adjustable reasoning depth, and can run directly or inside Docker.

  • Project
    google-gemini/genai-processors

    A lightweight Python library for building modular, asynchronous, and composable AI pipelines that unify multimodal content processing and streaming.

  • Project
    yeahhe365/AMC-WebUI

    An all-in-one model console WebUI that prioritizes Google Gemini's native capabilities while supporting OpenAI-compatible APIs, featuring a local-first architecture for privacy.