Chatting with LLMs in Open WebUI

Overview

Open WebUI is a self-hosted, browser-based interface that provides a familiar chatbot experience while acting as a frontend for one or more AI model servers. Instead of being tied to one provider, Open WebUI can connect to any backend that exposes an OpenAI-compatible API, so you can swap models and capabilities without switching UIs.

In this playbook, we use Lemonade as the backend because it exposes a unified OpenAI-compatible endpoint supporting multiple modalities:

• Large Language Models (LLMs) for text generation
• Vision models for image understanding
• Stable Diffusion for image generation
• Audio transcription models for speech-to-text

This setup enables you to explore the complete multimodal workflow end-to-end.

What You’ll Learn

By the end, you’ll be able to:

• Connect Open WebUI to a local OpenAI-compatible backend (Lemonade)
• Chat with a local LLM from your browser
• Upload an image and ask a vision model questions about it
• Generate images from text prompts using Stable Diffusion models (SDXL-Turbo / SDXL)
• Understand the mental model so you can use other backends (Ollama, vLLM, llama.cpp server, etc.)

Core Concepts (Mental Model)

The Three Components

Why “OpenAI-compatible API” matters

Open WebUI is built around standard OpenAI-style endpoints, like:

• Chat: /chat/completions
• Models list: /models
• Image generation: /images/generations
• Audio transcription: /audio/transcriptions

Lemonade exposes these under http://localhost:13305/api/v1/...

If a backend supports those endpoints, Open WebUI can talk to it with minimal setup. That’s why we can switch backends without changing our workflow.

Two services, two ports

Throughout this playbook you’ll work with two separate services:

Lemonade runs the models; Open WebUI is the interface you interact with. Use the Lemonade GUI to download your models first, then use them from Open WebUI.

Setting the Memory Configuration

sudo apt install pipx
pipx ensurepath

pipx install amd-debug-tools

amd-ttm

amd-ttm --set <NUM>

One-Time Setup

This playbook needs Lemonade running as the backend and, on Linux, a container engine (Podman) to run Open WebUI. Set these up before installing Open WebUI.

msiexec /i lemonade-server-minimal.msi /qn

sudo add-apt-repository ppa:lemonade-team/stable
sudo apt install lemonade-server

yay -S lemonade-server

lemonade --version

lemonade version x.y.z

msiexec /i lemonade-server-minimal.msi /qn

sudo add-apt-repository ppa:lemonade-team/stable
sudo apt install lemonade-server

yay -S lemonade-server

lemonade --version

lemonade version x.y.z

sudo apt update && sudo apt install -y podman docker-compose-plugin podman-compose

podman --version
podman-compose --version

sudo systemctl enable --now podman.socket

sudo podman run --rm docker.io/library/hello-world

Downloading Models in Lemonade

Before installing Open WebUI, make sure the models you want to use are downloaded and ready in Lemonade.

1. Open the Lemonade GUI at http://localhost:13305.
2. Browse the available models and download the ones you want to use (e.g., an LLM for chat, a vision model, and/or a Stable Diffusion model for image generation).
3. Confirm the API is reachable by visiting http://localhost:13305/api/v1/models in your browser — you should see your downloaded models listed.

Models must be downloaded in Lemonade (localhost:13305) before they can appear in Open WebUI (localhost:8080). If a model isn’t showing up in Open WebUI later, come back here and check Lemonade first.

Installing Open WebUI

winget install Python.Python.3.12

py -3.12 --version

mkdir openwebui
cd openwebui
py -3.12 -m venv openwebui-venv
.\openwebui-venv\Scripts\activate
pip install open-webui beautifulsoup4

podman compose up -d

Starting Open WebUI Server

open-webui serve

• In a browser, navigate to http://localhost:8080.
• Open WebUI will ask you to create a local administrator account. Once you are signed in, you will see the chat interface.

Connecting Open WebUI to Lemonade

Now that both services are running — Lemonade on localhost:13305 and Open WebUI on localhost:8080 — connect them so Open WebUI can use Lemonade’s models.

In Open WebUI:

1. Click the user profile icon in the top-right corner, then select Settings.

   

2. In the Settings panel, click Admin Settings at the bottom-left.

   

3. In the Admin Settings sidebar, click Connections (or navigate directly to http://localhost:8080/admin/settings/connections).

   

4. Under OpenAI API, add a new connection:

   • Base URL: http://localhost:13305/api/v1
   • API Key: - (a single dash works for local)

   

5. Ensure that under “Manage OpenAI API Connections”, only http://localhost:13305/api/v1 is enabled. Disable any other connections (e.g., the default OpenAI one).

   

6. Click Save.

7. (Recommended) Disable automatic generation features to keep Open WebUI responsive with local LLMs. Go to Admin Settings → Settings → Interface and turn off:

   • Title Generation
   • Follow Up Generation
   • Tags Generation

   

8. Click Save, then return to http://localhost:8080.

9. Click the model dropdown — you should see the models you downloaded from Lemonade.

Main Activities

Now, you’re all set up. Let’s look at three interesting things to do.

Activity 1: Chat with a Local LLM

This validates that Open WebUI can send requests to Lemonade using the OpenAI-compatible chat endpoint.

Activity 2: Upload an Image and Ask Questions (Vision)

This requires a model that supports image input (a Vision or Multimodal model).

1. Click the filter icon, select “By Category,” then choose a model from the Vision section (e.g., Qwen3.5-4B-GGUF)

   

2. Click the + button in the message box and upload an image

3. Ask something that forces true image understanding: Do you think this is a well-designed GUI?

   

4. The model answers based on the image content, not generic text.

This demonstrates that Open WebUI can send multimodal requests (text + image) through the backend (Lemonade) to a vision model.

Troubleshooting

”No models show up in Open WebUI”

• First, check Lemonade: open http://localhost:13305/api/v1/models in a browser and confirm your models are listed and downloaded
• Then, check the Open WebUI connection: go to Admin Settings → Connections at http://localhost:8080/admin/settings/connections and verify the Base URL is http://localhost:13305/api/v1

”This model does not support chat completion” error message

• You selected an image model (SDXL-Turbo / SDXL-Base-1.0) in the chat model dropdown.
• Fix: select an LLM for chat, and use the Image toggle + Images settings for generation.

Image generation errors/timeouts

• Start with SDXL-Turbo first (fast, fewer steps)
• Once working, switch the image model to SDXL-Base-1.0 for quality

Next Steps

You now have a working ‘local AI stack’, a single UI controlling multiple model types through a standard API.

Here are three expansions that unlock entirely new workflows:

1. Speech-to-Text with Whisper

Try turning audio into text using a Whisper model, then feed it into an LLM for summarization, action items, or rewriting. This is the foundation for meeting notes and voice-driven assistants.

2. Python Coding inside Open WebUI

Use Open WebUI’s built-in code execution experience to run Python snippets, inspect outputs, and iterate faster—without leaving the UI. Reference

3. HTML Rendering inside Open WebUI

Render HTML outputs directly in the interface. This is surprisingly powerful for building quick prototypes, formatted reports, and interactive snippets. Reference

References

• Open WebUI (GitHub)
• Lemonade (GitHub)
• Lemonade Server docs
• Lemonade Server CLI
• Lemonade ↔ Open WebUI integration guide
• Lemonade Server API spec (endpoints)
• Video walkthrough (Lemonade)
• Video walkthrough (Open WebUI + Lemonade)