Open WebUI retweeted
Healthcare data is sensitive, so sending it to a cloud AI service isn't always an option.
In this tutorial, Lakshmi shows you how to build a local healthcare AI assistant with MedGemma, Ollama, and Open WebUI.
You'll run the model on your own machine, chat with a medically al images, and more.
freecodecamp.org/news/build-you…
In this tutorial, Lakshmi shows you how to build a local healthcare AI assistant with MedGemma, Ollama, and Open WebUI.
You'll run the model on your own machine, chat with a medically al images, and more.
freecodecamp.org/news/build-you…
14
95
657
31,939
Self-host Open WebUI today, for free:
pip install open-webui
open-webui serve
You'll need Python 3.11 or 3.12. Or use the one-line Docker command in the guide.
View the source: github.com/open-webui/ope…
Get started, and tell us what you build: openwebui.com
pip install open-webui
open-webui serve
You'll need Python 3.11 or 3.12. Or use the one-line Docker command in the guide.
View the source: github.com/open-webui/ope…
Get started, and tell us what you build: openwebui.com
0
0
8
797
Already running Open WebUI? Update as soon as you can. v0.13.0 includes security fixes and a database migration, so back up first. A few changes need a decision.
Read the post: openwebui.com/blog/v0-13-0-y…
Read the post: openwebui.com/blog/v0-13-0-y…
1
0
5
884
Bring your team in.
Comment on the exact words of a chat or note, and the teammate you mention lands on that passage. An admin turns on Comments first.
Comment on the exact words of a chat or note, and the teammate you mention lands on that passage. An admin turns on Comments first.
1
0
5
674
Let small models take the simple questions.
Put a large model in charge, and it can hand research, coding, and review to sub-agents on other models. They're off by default, and they have no limits unless you set them.
Put a large model in charge, and it can hand research, coding, and review to sub-agents on other models. They're off by default, and they have no limits unless you set them.
1
0
7
720
Make every tool call wait for you.
Turn on approvals, and desktop and browser actions stop until you click Allow. An admin turns on Tool Permissions first, and the default is Full access.
Turn on approvals, and desktop and browser actions stop until you click Allow. An admin turns on Tool Permissions first, and the default is Full access.
1
0
7
787
Review what it changed.
Changes land in a Git panel as the model works. Open any diff, then commit, push, and work with pull requests without leaving the chat.
Changes land in a Git panel as the model works. Open any diff, then commit, push, and work with pull requests without leaving the chat.
1
0
8
1,097
It tests its own work in a browser.
In a tab beside your chat, it builds a page, opens it, and checks it. In Chrome mode, you share one session. On sites you don't control, use Docker, keep Ask for approval on, and stay signed out of accounts you care about.
In a tab beside your chat, it builds a page, opens it, and checks it. In Chrome mode, you share one session. On sites you don't control, use Docker, keep Ask for approval on, and stay signed out of accounts you care about.
1
0
10
1,660
Introducing Open WebUI v0.13.0: your model gets a computer. With Open Terminal connected, it opens apps on a real desktop, tests its work in a real browser, and leaves its changes in Git for you to review. All self-hosted, and you can watch it work or take the mouse.
20
43
565
230,878
More local compute. Put it to work.
We’re an early access partner for @NVIDIARTXSpark.
Build agents in Open WebUI that work with your files, run code, and return results on infrastructure you control.
Get started: openwebui.com/blog/open-webu…
We’re an early access partner for @NVIDIARTXSpark.
Build agents in Open WebUI that work with your files, run code, and return results on infrastructure you control.
Get started: openwebui.com/blog/open-webu…
5
0
18
1,894
Open WebUI retweeted
OpenWebUI × SearXNGで無料のDeepResearch。
同時に2~4クエリ同時検索して、それを繰り返すから、実質DeepResearch。
同時に2~4クエリ同時検索して、それを繰り返すから、実質DeepResearch。
0
1
2
353
Open WebUI retweeted
社内だけで使える「自社専用のChatGPT」、作れるって知っていますか？💬
✅ Open WebUIでできること
✅ 業務で役立つ4つの機能
✅ 導入のおおまかな流れ
✅ つまずいたときの確認ポイント
▶ 続きはブログで
harmonic-society.co.jp/open-webui-set…
#OpenWebUI #ローカルLLM
✅ Open WebUIでできること
✅ 業務で役立つ4つの機能
✅ 導入のおおまかな流れ
✅ つまずいたときの確認ポイント
▶ 続きはブログで
harmonic-society.co.jp/open-webui-set…
#OpenWebUI #ローカルLLM
0
1
1
289
Open WebUI retweeted
やばすぎｗｗｗ
自分のサーバーで使うAIチャット基盤「Open WebUI」がv0.12.3を公開。チームの会話を探して、資料の気になる一文をAIに渡す流れがかなり便利に。
🔎 自分のチャット、自分に共有されたチャット、チャンネル、DM、ノートをまとめて検索。種類やフォルダで絞り込める
👥 る
📄 ターミナルのファイルブラウザで文章を選んで「Ask or edit…」。選択部分とファイルを添えてAIに質問・編集を頼める
☁️ Google Driveのファイル選択は、選んだファイルだけにアクセスする方式へ。利用環境でのDrive連携設定は必要
利用にはOpen WebUIの設置・更新と、使うAIモデルの接続設定が必要。共有チャットの編集や回答の再生成は、返信が許可された共有フォルダ内で編集権限がある人が対象。
「あの話、AIの会話？DM？ノート？」で迷子になってた人、ようやく捜索本部を閉じられるｗ
#AI #OpenWebUI
自分のサーバーで使うAIチャット基盤「Open WebUI」がv0.12.3を公開。チームの会話を探して、資料の気になる一文をAIに渡す流れがかなり便利に。
🔎 自分のチャット、自分に共有されたチャット、チャンネル、DM、ノートをまとめて検索。種類やフォルダで絞り込める
👥 る
📄 ターミナルのファイルブラウザで文章を選んで「Ask or edit…」。選択部分とファイルを添えてAIに質問・編集を頼める
☁️ Google Driveのファイル選択は、選んだファイルだけにアクセスする方式へ。利用環境でのDrive連携設定は必要
利用にはOpen WebUIの設置・更新と、使うAIモデルの接続設定が必要。共有チャットの編集や回答の再生成は、返信が許可された共有フォルダ内で編集権限がある人が対象。
「あの話、AIの会話？DM？ノート？」で迷子になってた人、ようやく捜索本部を閉じられるｗ
#AI #OpenWebUI
0
1
2
325
localhost:tokyo
Introducing our new event series: Localhost Lounge. First stop: Tokyo, with @FabCafe
Local AI + talks from Tokyo’s creative, research & startup communities.
Nov 11 · 6–9pm JST
Request to join: luma.com/ox9lohvz
Introducing our new event series: Localhost Lounge. First stop: Tokyo, with @FabCafe
Local AI + talks from Tokyo’s creative, research & startup communities.
Nov 11 · 6–9pm JST
Request to join: luma.com/ox9lohvz
6
4
93
3,247,716
Open WebUI retweeted
What if you could run your own private ChatGPT at home?
Learn from @Tailscale how to build a local AI setup with Ollama and Open WebUI, then access it securely from anywhere: hackernoon.com/self-host-a-lo…
Learn from @Tailscale how to build a local AI setup with Ollama and Open WebUI, then access it securely from anywhere: hackernoon.com/self-host-a-lo…
14
19
235
1,359,394
Open WebUI retweeted
Build a private AI lab with Proxmox, NixOS, an NVIDIA GPU, Ollama, and Open WebUI, with automated deployment and secure remote access through Tailscale.
#selfhostedllms #localailabsetup...Show more
#selfhostedllms #localailabsetup...Show more
1
2
3
1,102
Understood, and thanks for the detail. Are you on the latest version (0.12.0)? Any files or logs you can share from that chat would help us reproduce the compaction issue.
0
0
0
41
This shouldn't happen. Can you share your Open WebUI version, model and backend, and context length? If you're on the desktop app, please try the Docker version. Any relevant files or logs, feel free to DM us and we'll investigate.
1
0
1
414
