Skip to content

Fix minor grammar/style errors in offline-mode.mdx #1264

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Classic298 merged 3 commits into from
May 21, 2026
+10 −10
Merged

Fix minor grammar/style errors in offline-mode.mdx #1264

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
33ba662
Update Cloudflare Tunnel docs links and steps
thatrobotdev May 19, 2026
d287116
Merge pull request #1259 from thatrobotdev/patch1
tjbck May 19, 2026
b9457a5
Fix minor grammar/style errors in offline-mode.mdx
thatrobotdev May 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions docs/reference/https/cloudflare-tunnel.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ The simplest path. Everything configured through the Cloudflare dashboard.

### 1. Create the tunnel

1. Go to [**Zero Trust → Networks → Tunnels**](https://one.dash.cloudflare.com/networks/tunnels)
1. Go to [**Zero Trust → Networks → Connectors**](https://dash.cloudflare.com/?to=/:account/one/networks/connectors)
2. Click **Create a tunnel** → select **Cloudflared**
3. Name it (e.g., `open-webui`)
4. Follow the install instructions to run the connector on your machine
Expand Down Expand Up @@ -189,7 +189,7 @@ volumes:
open-webui:
```

Get your tunnel token from the [Cloudflare dashboard](https://one.dash.cloudflare.com/networks/tunnels) → select your tunnel → **Configure** → copy the token from the install command.
Get your tunnel token from the [Cloudflare dashboard](https://dash.cloudflare.com/) → Go to [**Networking → Tunnels**] → Select your tunnel → Select **Add a replica** → Copy the install command. The token starts with `eyJ...`.

:::tip
No `ports` needed on the `open-webui` service. `cloudflared` connects to it via Docker's internal network. To use this, change the service URL in your tunnel config to `http://open-webui:8080`.
Expand All @@ -201,9 +201,9 @@ No `ports` needed on the `open-webui` service. `cloudflared` connects to it via

Cloudflare Zero Trust lets you gate access behind authentication without touching Open WebUI:

1. Go to [**Zero Trust → Access → Applications**](https://one.dash.cloudflare.com/access/apps)
2. **Add an application** → Self-hosted
3. Set the domain to `chat.your-domain.com`
1. Go to [**Zero Trust → Access controls → Applications**](https://dash.cloudflare.com/?to=/:account/one/access-controls/apps)
2. **Create new application** → Self-hosted and private
3. Set the public hostname to `chat.your-domain.com`
4. Create an **Access Policy** (e.g., allow only `@your-company.com` emails)

Users see a Cloudflare login page before reaching Open WebUI.
Expand All @@ -218,5 +218,5 @@ Users see a Cloudflare login page before reaching Open WebUI.
| Start tunnel | `cloudflared tunnel run open-webui` |
| Add DNS | `cloudflared tunnel route dns open-webui chat.your-domain.com` |
| Install as service | `sudo cloudflared service install` |
| Dashboard | [one.dash.cloudflare.com/networks/tunnels](https://one.dash.cloudflare.com/networks/tunnels) |
| Dashboard | [https://dash.cloudflare.com/?to=/:account/one/networks/connectors](https://dash.cloudflare.com/?to=/:account/one/networks/connectors) |
| Set CORS origin | `CORS_ALLOW_ORIGIN=https://chat.your-domain.com` |
8 changes: 4 additions & 4 deletions docs/tutorials/maintenance/offline-mode.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ This tutorial is a community contribution and is not supported by the Open WebUI

If you want to run Open WebUI in offline mode, you have to consider your installation approach and adjust your desired features accordingly. In this guide, we will go over the different ways of achieving a mostly similar setup to the online version.

## What means offline mode?
## What does offline mode mean?

The offline mode of Open WebUI lets you run the application without the need for an active internet connection. This allows you to create an 'air-gapped' environment for your LLMs and tools (a fully 'air-gapped' environment requires isolating the instance from the internet).

Expand Down Expand Up @@ -47,7 +47,7 @@ Offline mode requires setting multiple environment variables to fully disconnect
**Optional but Recommended:**

- `RAG_EMBEDDING_MODEL_AUTO_UPDATE=false` - Prevents automatic updates of embedding models
- `RAG_RERANKING_MODEL_AUTO_UPDATE=false` - Prevents automatic updates of reranking models
- `RAG_RERANKING_MODEL_AUTO_UPDATE=false` - Prevents automatic updates of reranking models
- `WHISPER_MODEL_AUTO_UPDATE=false` - Prevents automatic updates of Whisper models

Apply these environment variables depending on your deployment method.
Expand All @@ -73,7 +73,7 @@ Consider if you need to start the application offline from the beginning of your

### I: Speech-To-Text

The local `whisper` installation does not include the model by default. In this regard, you can follow the [guide](/features/chat-conversations/audio/speech-to-text/stt-config) only partially if you want to use an external model/provider. To use the local `whisper` application, you must first download the model of your choice (e.g. [Huggingface - Systran](https://huggingface.co/Systran)).
The local `whisper` installation does not include the model by default. In this regard, you can follow the [guide](/features/chat-conversations/audio/speech-to-text/stt-config) only partially if you want to use an external model/provider. To use the local `whisper` application, you must first download the model of your choice (e.g. [Hugging Face - Systran](https://huggingface.co/Systran)).

```python
from faster_whisper import WhisperModel
Expand All @@ -96,7 +96,7 @@ The default local transformer can already handle the text-to-speech function. If

### I: Embedding Model

For various purposes, you will need an embedding model (e.g. [RAG](/features/chat-conversations/rag)). You will first have to download such a model of your choice (e.g. [Huggingface - sentence-transformers](https://huggingface.co/sentence-transformers)).
For various purposes, you will need an embedding model (e.g. [RAG](/features/chat-conversations/rag)). You will first have to download such a model of your choice (e.g. [Hugging Face - sentence-transformers](https://huggingface.co/sentence-transformers)).

```python
from huggingface_hub import snapshot_download
Expand Down
Loading