Merge pull request #236 from tokk-nv/dev/openwebui

Add Open WebUI page and adjust the Ollama page

docs/tutorial_ollama.md

@@ -1,6 +1,10 @@
 # Tutorial - Ollama
 
-[Ollama](https://github.com/ollama/ollama){:target="_blank"} is a popular LLM tool that's easy to get started with, and includes a built-in [model library](https://ollama.com/library){:target="_blank"} of pre-quantized weights that will automatically be downloaded and run using llama.cpp underneath for inference.  The [ollama container](https://github.com/dusty-nv/jetson-containers/tree/dev/packages/llm/ollama){:target="_blank"} was compiled with CUDA support.
+[Ollama](https://ollama.com){:target="_blank"} is a popular open-source tool that allows users to easily run a large language models (LLMs) locally on their own computer, serving as an accessible entry point to LLMs for many.
+
+It now offers out-of-the-box support for the Jetson platform with CUDA support, enabling Jetson users to seamlessly install Ollama with a single command and start using it immediately.
+
+In this tutorial, we introduce two installation methods: (1) the default native installation using the official Ollama installer, and (2) the Docker container method, which allows users to avoid making changes to their existing system.
 
 <img src="https://github.com/dusty-nv/jetson-containers/blob/docs/docs/images/ollama_cli.gif?raw=true" width="750px"></img>
 
@@ -29,6 +33,15 @@
         - `7GB` for `ollama` container image
         - Space for models (`>5GB`)
 		 
+
+## (1) Native Install
+
+```bash
+curl -fsSL https://ollama.com/install.sh | sh 
+```
+
+## (2) Docker container for `ollama` using `jetson-containers`
+
 ```
 # models cached under jetson-containers/data
 jetson-containers run --name ollama $(autotag ollama)
@@ -39,8 +52,6 @@ docker run --runtime nvidia --rm --network=host -v ~/ollama:/ollama -e OLLAMA_MO
 
 Running either of these will start the local Ollama server as a daemon in the background.  It will save the models it downloads under your mounted `jetson-containers/data/models/ollama` directory (or another directory that you override with `OLLAMA_MODELS`)
 
-## Ollama Client
-
 Start the Ollama command-line chat client with your desired [model](https://ollama.com/library){:target="_blank"} (for example: `llama3`, `phi3`, `mistral`)
 
 ```

docs/tutorial_openwebui.md

@@ -0,0 +1,49 @@
+# Tutorial - Open WebUI
+
+[Open WebUI](https://github.com/ollama/ollama){:target="_blank"} is a versatile, browser-based interface for running and managing large language models (LLMs) locally, offering Jetson developers an intuitive platform to experiment with LLMs on their devices.
+
+It can work with Ollama as a backend as well as other backend that is compatible with OpenAI, which can also run well on Jetson.
+
+![alt text](<images/open_webui_on_desktop.png>)
+
+## Ollama Server
+
+!!! abstract "What you need"
+
+    1. One of the following Jetson devices:
+
+        <span class="blobDarkGreen4">Jetson AGX Orin (64GB)</span>
+        <span class="blobDarkGreen5">Jetson AGX Orin (32GB)</span>
+        <span class="blobLightGreen3">Jetson Orin NX (16GB)</span>
+        <span class="blobLightGreen3">Jetson Orin Nano (8GB)</span>
+	   
+    2. Running one of the following versions of [JetPack](https://developer.nvidia.com/embedded/jetpack){:target="_blank"}:
+
+        <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
+        <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
+
+    3. Sufficient storage space (preferably with NVMe SSD).
+
+        - `7GB` for `open-webui` container image
+		 
+```
+sudo docker run -d --network=host \
+    -v ${HOME}/open-webui:/app/backend/data \
+    -e OLLAMA_BASE_URL=http://127.0.0.1:11434 \
+    --name open-webui \
+    --restart always \ 
+    ghcr.io/open-webui/open-webui:main
+```
+
+## Ollama backend
+
+If you <a href="./tutorial_ollama.html">have installed Ollama</a>, you can just run the Open WebUI docker container without installing any other things.
+
+```
+sudo docker run -d --network=host \
+    -v ${HOME}/open-webui:/app/backend/data \
+    -e OLLAMA_BASE_URL=http://127.0.0.1:11434 \
+    --name open-webui \
+    --restart always \ 
+    ghcr.io/open-webui/open-webui:main
+```

mkdocs.yml

@@ -87,7 +87,8 @@ nav:
     - Agent Studio: agent_studio.md
     - Text (LLM):
       - text-generation-webui: tutorial_text-generation.md 
-      - ollama: tutorial_ollama.md
+      - Ollama: tutorial_ollama.md
+      - Open WebUI: tutorial_openwebui.md
       - llamaspeak: tutorial_llamaspeak.md
       - NanoLLM: tutorial_nano-llm.md
       - TensorRT-LLM  🆕: tensorrt_llm.md