Functions

在OpwenWebUI中显示DeepSeek R1模型的思维链（仅支持0.5.6及以上版本） / Display the reasoning chain of the DeepSeek R1 model in OpwenWebUI(Only supports versions 0.5.6 and above)

Use Deepseek Reasoner & Chat with Realtime Preview of the Thinking Process

OBSOLETE: Please use: https://openwebui.com/f/owndev/azure_ai

The thought process used to enhance LLMs reasoning capabilities. Adapted from https://github.com/richards199999/Thinking-Claude. It supports the soft insertion of your own new system prompt (it is recommended not to be too long), with a maximum of two system prompts coexisting as the constitution of LLM.

Simple formatter that transforms <think> labels into collapsible "💭 Thought for X seconds" panels.

ReAct agent using existing tools, with streaming and citations. Implemented with LangGraph. Supports LangFuse optionally. Works with both OpenAI and Ollama. Now with model whitelist parameter.

在OpwenWebUI中显示DeepSeek R1模型的思维链，支持官方API和硅基流动的API

Scale Ollama GPU use based on response failures. Reduces GPU layers in use when OpenWebUI receives a crash from Ollama.

在OpwenWebUI中显示DeepSeek R1模型的思维链（仅支持0.5.6及以上版本），修复新版本template输出缺少开头think标签问题 / Display the reasoning chain of the DeepSeek R1 model in OpwenWebUI(Only supports versions 0.5.6 and above), Fix the issue of the new version template output missing the starting <think> tag

在OpwenWebUI中显示DeepSeek R1模型的思维链（仅支持0.5.6及以上版本） / Display the reasoning chain of the DeepSeek R1 model in OpwenWebUI(Only supports versions 0.5.6 and above)

Creates a button to instantly unload Ollama model(s) that are running in vRAM.

DeepSeek-Gemini Vision integrates Deepseek with Gemini for advanced image processing. Gemini handles image analysis, while DeepSeek ensures precise results.

Output formatter for DeepSeek R1 [Deprecated because Open WebUI officially supports think tag as of v0.5.5]

Deepseek v2.5 API both for chat and coding *** NOT SUPPORT IMAGE INPUT ***

DeepSeek-Gemini Vision integrates Deepseek with Gemini for advanced image processing. Gemini handles image analysis, while DeepSeek ensures precise results.

Unlimited DeepSeek R1 - Easy Install - Feb 3 2025

Use Deepseek R1 with Realtime Preview of the Thinking Process for Volcengine

Currently, DeepSeek V3 Pipeline API does not support image file analysis. However, this feature may be added in the future. Please stay tuned for updates from our development team.

开箱即用，无配置项，修复 deepseek-r1 深度思考

适配nvidia官方推出的nmi微模型中的r1模型深度思考过程展示。

Multi-API reasoning effort pipeline for deepseek-r1 models with OpenAI/Ollama support. Compatible with open-webui +v0.5.x

DeepSeek Pipeline

In OpenWebUI, displays the thought chain of the DeepSeek R1 model and Bocha searchs (version 0.5.6 or higher)

In OpenWebUI, displays the thought chain of the DeepSeek R1 model and searchs (version 0.5.6 or higher)

支持 DeepSeek API

Unloads all models from VRAM using Ollama's REST API.

Fix miss rendering "Thinking" block on SiliconFlow API. <think> block healing, add additional '\n' for middleware processing of Open WebUI. Inspired by zgccrui/deepseek_r1.

在OpwenWebUI中显示DeepSeek R1模型的思维链（仅支持0.5.6及以上版本），修复新版本template输出缺少开头think标签问题，修复联网搜索和生成标题出错的问题，通过添加处理非流式传输时不添加<think>标签来实现。 / Display the reasoning chain of the DeepSeek R1 model in OpwenWebUI(Only supports versions 0.5.6 and above), Fix the issue of the new version template output missing the starting <think> tag, resolve errors in online search and title generation, and achieve this by adding processing to not include the <think> tag during non-streaming transmission.

removes the think tag

在OpwenWebUI中显示DeepSeek R1模型的思维链（仅支持0.5.6及以上版本） / Display the reasoning chain of the DeepSeek R1 model in OpwenWebUI(Only supports versions 0.5.6 and above)

Adapted code from @zgccrui

You can use DeepSeek R1 or QwQ 32B for cheap and fast thinking, and use stronger and more expensive models like Claude 3.7 Sonnet for final summarization output, to achieve a better balance between inference cost and performance.

Automatically saves important User or Assistant text as memories, this code is ment to work with dockerized deployments of open webui (v0.5.20), you must have Ollama installed and running local models for this to work. Update the valves with necessary ports, api's if you choose, ect: if you get errors this function has really good debugging so just look at your docker logs.

Unleash precision in coding and problem-solving with the CodeMaster Reasoning Pipe. This advanced manifold excels in both coding tasks and general queries through a powerful three-phase process: initial reasoning breaks down the problem, a configurable chain-of-thought refines solutions with iterative depth, and a final synthesis delivers polished code or concise answers. Optimized for OpenAI and Ollama APIs, it supports multiple reasoning models, adjustable iteration counts, and optional reasoning trace visibility. Perfect for developers and thinkers seeking top-tier AI-driven accuracy and clarity.

You can use DeepSeek R1 or QwQ 32B for cheap and fast thinking, and use stronger and more expensive models like Claude 3.7 Sonnet for final summarization output, to achieve a better balance between inference cost and performance.

This Filter function modifies the request payload for Google Gemini models to disable content safety filters. It adds the 'safety_settings' parameter to the request body with all harm categories set to 'BLOCK_NONE'. This is intended for use cases where Gemini's default filtering is overly restrictive. Use responsibly. Note: This function identifies Gemini models by checking if the model ID starts with 'google/gemini'. This might need adjustment depending on how your specific backend (e.g., OpenRouter, Ollama with LiteLLM Proxy) names the Gemini models.

流式输出阿里云百链平台 deepseek r1 思维链 / To display the Chain of Thoughts of Deepseek R1 from Aliyun Bailian with Streaming display

DeepSeek r1 思考过滤

Display the reasoning chain of the DeepSeek R1 model in OpwenWebUI

DeepSeek Pipe supports both chat and code modes, and it operates asynchronously, meaning it types out text as the tokens are received.

Provide enhanced cross-API visual routing capabilities to offer visual abilities for AI that does not support multimodality, facilitating the sending of images when conversing with DeepSeek-R1 and solving compatibility issues when switching models between different APIs.|提供增强的跨API视觉路由能力，为不支持多模态的AI提供视觉能力，方便与DeepSeek-R1对话时发送图片，解决不同API之间切换模型的兼容性问题

在OpwenWebUI中显示DeepSeek R1模型的思维链 - 仅支持0.5.6及以上版本，同时兼顾reasoning_content与<think>模式

By novagrid.ai

Deepseek's COT + Claude

Work around/Fix for 500: Ollama: 500, message='Internal Server Error', url='http://host.docker.internal:11434/api/chat '

Ollama Content Moderation Filter based on LLamaGuard3 or ShieldGemma

DeepSeek manifold

在 OpenWebUI 添加 DeepSeek R1 的思维链、接入博查联网搜索（根据需要自动开启），并优化搜索输出质量 (仅支持0.5.6及以上版本)

Enhances Ollama API facade interactions by providing additional metadata including id, session_id, and chat_id for seamless integration with applications requiring rich context information.

Allow thinking block for SiliconFlow API.

在OpwenWebUI中显示DeepSeek R1模型的思维链（仅支持0.5.6及以上版本） / Display the reasoning chain of the DeepSeek R1 model in OpwenWebUI(Only supports versions 0.5.6 and above)

DeepSeek offers advanced reasoning and chat capabilities, supporting structured responses and AI-driven analysis for enhanced conversations.

This advanced Think-Respond pipe elevates AI reasoning by chaining structured, step-by-step analysis with refined response generation. Designed to mimic sophisticated reasoning models like R1, it breaks down queries into multiple reasoning paths, critiques them for accuracy, and synthesizes the best insights into a concise, logical answer. Supporting both OpenAI and Ollama APIs, it offers flexible model selection, adjustable thinking time, and an optional trace of the reasoning process. Ideal for users seeking deeper, more reliable AI-driven solutions.

Pipe model to wake on lan your Ollama server before sending a query. Uses https://github.com/rix1337/WakeOnLAN-API

Llama Vision Pipe - Ollama Integration

Model: DeepSeek-R1-Distill-Qwen-32B

在OpwenWebUI中显示DeepSeek R1模型的思维链（仅支持0.5.6及以上版本） / Display the reasoning chain of the DeepSeek R1 model in OpwenWebUI(Only supports versions 0.5.6 and above)

deepseek based on aliyun bailian platform

Asynchronous request processing

This function is deprecated. Please use another function in my profile.