feat: add ollama doc & update Ollama entrance URL

docs/.vitepress/en.ts

@@ -121,6 +121,10 @@ const side = {
           text: "ComfyUI",
           link: "/manual/use-cases/comfyui",
         },
+        {
+          text: "Ollama",
+          link: "/manual/use-cases/ollama",
+        },
         {
           text: "Open WebUI",
           link: "/manual/use-cases/openwebui",

docs/.vitepress/zh.ts

@@ -121,6 +121,10 @@ const side = {
           text: "ComfyUI",
           link: "/zh/manual/use-cases/comfyui",
         },
+        {
+          text: "Ollama 下载开源模型",
+          link: "/zh/manual/use-cases/ollama",
+        },
         {
           text: "Open WebUI",
           link: "/zh/manual/use-cases/openwebui",

docs/manual/use-cases/dify.md

@@ -7,8 +7,8 @@ Dify is an AI application development platform. It's one of the key open-source
 
 ## Before you begin
 To use local AI models on Dify, ensure you have:
-- Ollama installed and running in your Olares environment
-- Open WebUI installed with your preferred language models downloaded
+- [Ollama installed](ollama.md) and running in your Olares environment.
+- [Open WebUI installed](openwebui.md) with your preferred language models downloaded.
   :::tip
   For optimal performance, consider using lightweight yet powerful models like `gemma2` or `qwen`, which offer a good balance between speed and capability.
   :::
@@ -30,18 +30,14 @@ Install Dify from Market based on your role:
 
 ## Add Ollama as model provider
 
-1. Set up the Ollama access entrance:
-
-   a. Navigate to **Settings** > **Application** > **Ollama** > **Entrances**, and set the authentication level for Ollama to **Internal**. This configuration allows other applications to access Ollama services within the local network without authentication. 
+1. Navigate to **Settings** > **Application** > **Ollama** > **Entrances**, and set the authentication level for Ollama to **Internal**. This configuration allows other applications to access Ollama services within the local network without authentication. 
 
     ![Ollama entrance](/images/manual/use-cases/dify-ollama-entrance.png#bordered)
-
-   b. From the **Entrances** page, enter the **Set up endpoint** page to retrieve the default route ID for Ollama(`39975b9a`). Now you get the local access address for Ollama: `https://39975b9a.local.{your username}.olares.com`, for example, `https://39975b9a.local.kevin112.olares.com`.
 
 2. In Dify, navigate to **Settings** > **Model Provider**.
 3. Select Ollama as the model provider, with the following configurations:
     - **Model Name**: Enter the model name. For example: `gemma2`.
-    - **Base URL**: Enter Ollama's local address you get in step 1, for example, `https://39975b9a.local.kevin112.olares.com`.
+    - **Base URL**: Enter Ollama's local address: `https://39975b9a1.local.{username}.olares.com`. Replace `{username}` with the Olares Admin's local name. For example, `https://39975b9a1.local.marvin123.olares.com`.
 
      ![Add gemma2](/images/manual/use-cases/dify-add-gemma2.png#bordered){width=70%}
 

docs/manual/use-cases/index.md

@@ -11,5 +11,6 @@ While other guides tell you "what" and "how," these use cases reveal the full po
   { title: 'Perplexica', link: './perplexica.html', tags: ['ai']},
   { title: 'Dify', link: './dify.html', tags: ['ai']},
   { title: 'Hubble', link: 'https://blog.olares.xyz/running-farcaster-hubble-on-your-home-cloud/', tags: ['social network']},
+  { title: 'Ollama', link: './ollama.html', tags: ['ai']},
 ]" 
 />

docs/manual/use-cases/ollama.md

@@ -0,0 +1,82 @@
+---
+outline: [2, 3]
+description: Learn how to download and manage AI models locally using Ollama CLI within the Olares environment.
+---
+
+# Download and run AI models locally via Ollama
+Ollama is a lightweight platform that allows you to run open-source AI models like `deepseek-r1` and `gemma3` directly on your machine. Within Olares, you can integrate Ollama with graphical interfaces like Open WebUI to add more features and simplify interactions.
+
+This guide will show you how to set up and use Ollama CLI on Olares.
+
+## Before you begin
+Before you start, ensure that:
+- You have Olares admin privileges.
+
+## Install Ollama
+
+Directly install Ollama from the Market.
+
+Once installation is complete, you can access Ollama terminal from the Launchpad.
+
+![Ollama](/images/manual/use-cases/ollama.png#bordered)
+## Ollama CLI
+Ollama CLI allows you to manage and interact with AI models directly. Below are the key commands and their usage:
+
+### Download model
+:::tip Check Ollama library
+If you are unsure which model to download, check the [Ollama Library](https://ollama.com/library) to explore available models.
+:::
+To download a model, use the following command:
+```bash
+ollama pull [model]
+```
+
+### Run model
+:::tip
+If the specified model has not been downloaded yet, the `ollama run` command will automatically download it before running.
+:::
+
+To run a model, use the following command:
+```bash
+ollama run [model]
+```
+
+After running the command, you can enter queries directly into the CLI, and the model will generate responses.
+
+When you're finished interacting with the model, type:
+```bash
+/bye
+```
+This will exit the session and return you to the standard terminal interface.
+
+### Stop model
+To stop a model that is currently running, use the following command:
+```bash
+ollama stop [model]
+```
+
+### List models
+To view all models installed on your system, use:
+```bash
+ollama list
+```
+
+### Remove a model
+If you need to delete a model, you can use the following command:
+```bash
+ollama rm [model]
+```
+### Show information for a model
+To display detailed information about a model, use:
+```bash
+ollama show [model]
+```
+
+### List running models
+To see all currently running models, use:
+```bash
+ollama ps
+```
+
+## Learn more
+- [Learn how to run Ollama models with Open WebUI](openwebui.md)

docs/zh/manual/use-cases/dify.md

@@ -7,8 +7,8 @@ Dify 是一个 AI 应用开发平台。它是 Olares 集成的关键开源项目
 
 ## 开始之前
 要使用本地 AI 模型，请确保你的环境中已配置以下内容：
-- Olares 环境中已安装并运行 Ollama。
-- 已安装 Open WebUI，并下载了你偏好的语言模型。
+- Olares 环境中已安装并运行 [Ollama](ollama.md)。
+- 已安装 [Open WebUI](openwebui.md)，并下载了你偏好的语言模型。
   :::tip 提示
   建议使用 `gemma2` 或 `qwen` 等轻量但功能强大的模型，可在速度和性能间取得良好平衡。
   :::
@@ -30,17 +30,13 @@ Dify 是一个 AI 应用开发平台。它是 Olares 集成的关键开源项目
 
 ## 添加 Ollama 作为模型提供商
 
-1. 配置 Ollama 访问入口。
-
-   a. 进入**设置** > **应用** > **Ollama** > **入口**，设置 Ollama 的认证级别为“内部”。该设置允许其他应用在本地网络环境下可无需认证即可访问 Ollama 服务。
+1. 进入**设置** > **应用** > **Ollama** > **入口**，设置 Ollama 的认证级别为“内部”。该设置允许其他应用在本地网络环境下可无需认证即可访问 Ollama 服务。
 
    ![Ollama entrance](/images/zh/manual/use-cases/dify-ollama-entrance.png#bordered)
 
-   b. 点击**设置端点**页面，查看 Ollama 的默认路由 ID（`39975b9a`）。这样，我们便得到了 Ollama 的本地访问地址：`https://39975b9a.local.{你的本地名称}.olares.cn`, 如 `https://39975b9a.local.marvin123.olares.cn`。
-
 2. 在 Dify 的 模型提供者商配置页面，选择 Ollama 作为模型提供者商，并进行以下配置：
     - **模型名称**：填写模型名称，例如：`gemma2`。
-    - **基础 URL**：填入上一步获取的 Ollama 本地地址，如 `https://39975b9a.local.marvin123.olares.cn`。
+    - **基础 URL**：填入 Ollama 本地地址: `https://39975b9a1.local.{username}.olares.cn`。将 `{username}` 替换为 Olares 管理员的用户名。例如：`https://39975b9a1.local.marvin123.olares.com`。
 
     ![配置 Ollama](/images/zh/manual/use-cases/dify-add-gemma2.png#bordered){width=70%}
 

docs/zh/manual/use-cases/index.md

@@ -10,5 +10,6 @@ description: 了解 Olares 的多种实际应用场景，学习如何将其功
   { title: 'Open WebUI', link: './openwebui.html', tags: ['AI'] },
   { title: 'Perplexica', link: './perplexica.html', tags: ['AI']},
   { title: 'Dify', link: './dify.html', tags: ['AI']},
+  { title: 'Ollama', link: './ollama.html', tags: ['ai']},
 ]" 
 />

docs/zh/manual/use-cases/ollama.md

@@ -0,0 +1,82 @@
+---
+outline: [2, 3]
+description: 了解如何在 Olares 环境中使用 Ollama CLI 在本地下载和管理 AI 模型。
+---
+
+# 通过 Ollama 在本地运行 AI 模型
+Ollama 是一个轻量级平台，可以让你在本地机器上直接运行 `deepseek-r1` 和 `gemma3` 等开源 AI 模型。如果你更偏向于使用图形化界面，也可以在 Open WebUI 中管理 Ollama 模型，以添加更多功能并简化交互。
+
+本文档将介绍如何在 Olares 上设置和使用 Ollama CLI。
+
+## 开始之前
+请确保满足以下条件：
+- 当前登录账号为 Olares 管理员。
+
+## 安装 Ollama
+
+直接从应用市场安装 Ollama。
+
+安装完成后，可以从启动台访问 Ollama 终端。
+
+![Ollama](/images/manual/use-cases/ollama.png#bordered)
+## Ollama CLI
+Ollama CLI 让你可以直接管理和使用 AI 模型。以下是主要命令及其用法：
+
+### 下载模型
+:::tip 查看 Ollama 模型库
+如果不确定下载哪个模型，可以在 [Ollama Library](https://ollama.com/library) 浏览可用模型。
+:::
+使用以下命令下载模型：
+```bash
+ollama pull [model]
+```
+
+### 运行模型
+:::tip
+如果尚未下载指定的模型，ollama run 命令会在运行前自动下载该模型。
+:::
+
+使用以下命令运行模型：
+```bash
+ollama run [model]
+```
+
+运行命令后，直接在 CLI 中输入问题，模型会生成回答。
+
+完成交互后，输入：
+```bash
+/bye
+```
+这将退出会话并返回标准终端界面。
+
+### 停止模型
+要停止当前运行的模型，使用以下命令：
+```bash
+ollama stop [model]
+```
+
+### 列出模型
+要查看系统中已安装的所有模型，使用：
+```bash
+ollama list
+```
+
+### 删除模型
+如果需要删除模型，可以使用以下命令：
+```bash
+ollama rm [model]
+```
+### 显示模型信息
+要显示模型的详细信息，使用：
+```bash
+ollama show [model]
+```
+
+### 列出运行中的模型
+要查看所有当前运行的模型，使用：
+```bash
+ollama ps
+```
+
+## 了解更多
+- [了解如何通过 Open WebUI 运行 Ollama 模型](openwebui.md)