Use the new screenshots on the pages they belong to

The previous commit added the images but only four of them were referenced, so
the rest sat in the repository unused. Places each one on the page that
describes it: the workspace lists and the model editor, the notes list, the
chat rendering and history search, and the admin panes on the feature pages
that send readers there (documents, web search, images, audio, connections,
authentication, users, analytics, evaluations, sub-agents, code execution,
external tools, task models and database).

Author: Classic298

docs/features/administration/analytics/index.mdx

@@ -36,6 +36,8 @@ All analytics data is derived from the message history stored in your instance's
 2. Click your profile icon and open **Settings**
 3. Open the **Admin** section and select **Analytics**, listed under **Quality**
 
+![The analytics dashboard](/images/admin/admin-analytics.png)
+
 The dashboard is no longer a separate page. It opens in the settings window next to your personal settings, and the old `/admin/analytics` URL redirects there. If [`ENABLE_ADMIN_ANALYTICS`](/reference/env-configuration#enable_admin_analytics) is off, that URL redirects to the Admin Panel user list instead and the Analytics entry is not listed.
 
 ---

docs/features/administration/evaluation/index.mdx

@@ -7,6 +7,8 @@ title: "Evaluation"
 
 Meet **Alex**, a machine learning engineer at a mid-sized company. Alex knows there are numerous AI models out there (GPTs, LLaMA, and many more) but which one works best for the job at hand? They all sound impressive on paper, but Alex can’t just rely on public leaderboards. These models perform differently depending on the context, and some models may have been trained on the evaluation dataset (sneaky!). Plus, the way these models write can sometimes feel … off.
 
+![Evaluation and arena settings](/images/admin/admin-evaluations.png)
+
 That's where Open WebUI comes in. It gives Alex and their team an easy way to evaluate models based on their actual needs. No convoluted math. No heavy lifting. Just thumbs up or thumbs down while interacting with the models.
 
 ### TL;DR

docs/features/administration/index.mdx

@@ -32,6 +32,8 @@ Open WebUI gives administrators a full operational toolkit. Track which models y
 | 📢 **[Banners](./banners)** | Customizable system-wide announcements with dismissible notifications |
 | 🔔 **[Webhooks](./webhooks)** | Automated notifications for user sign-ups, chat completions, and external service integration |
 
+![Admin settings, General](/images/admin/admin-general.png)
+
 ---
 
 ## Analytics

docs/features/authentication-access/index.mdx

@@ -33,6 +33,8 @@ Open WebUI is multi-user from day one. Whether you're running a personal instanc
 | 📋 **[SCIM 2.0](./auth/scim)** | Automated user and group provisioning and deprovisioning from your IdP |
 | 🔐 **[API Keys](./api-keys)** | Programmatic access for scripts, bots, pipelines, and integrations |
 
+![Authentication settings in the admin panel](/images/admin/admin-authentication.png)
+
 ---
 
 ## How It Fits Together

docs/features/authentication-access/rbac/index.mdx

@@ -27,6 +27,8 @@ Avoid configuring management/master keys for general user traffic unless your de
     *   Understand the difference between Admins and Users.
     *   Learn about Admin limitations and security/privacy configurations.
 
+![The user list in the admin panel](/images/admin/users-list.png)
+
 *   [🔒 **Permissions**](./permissions.md)
     *   Explore the full list of available permission toggles.
     *   Understand granular controls for Chat, Workspace, and Features.

docs/features/chat-conversations/audio/index.mdx

@@ -19,6 +19,8 @@ import DocCardList from '@theme/DocCardList';
   style={{ width: '100%', margin: '0.25rem 0 1.75rem' }}
 />
 
+![Speech to text and text to speech settings](/images/admin/admin-audio.png)
+
 Talk to Open WebUI and have it talk back. Dictate with speech-to-text and hear responses with text-to-speech, across a range of engines and voices.
 
 <DocCardList />

docs/features/chat-conversations/chat-features/code-execution/python.md

@@ -9,6 +9,8 @@ title: "Python Code Execution"
 
 Open WebUI provides two ways to execute Python code:
 
+![Code execution settings](/images/admin/admin-code-execution.png)
+
 1. **Manual Code Execution**: Run Python code blocks generated by LLMs using a "Run" button in the browser (uses Pyodide/WebAssembly).
 2. **Code Interpreter**: An AI capability that allows models to automatically write and execute Python code as part of their response (uses Pyodide or Jupyter).
 

docs/features/chat-conversations/chat-features/history-search.mdx

@@ -11,6 +11,8 @@ Open WebUI provides a powerful system for managing and navigating your previous
 
 All your conversations are automatically saved in the **Sidebar**.
 
+![Searching chat history](/images/features/chat/history-search.png)
+
 *   **Persistence**: Chats are saved to the internal database (`webui.db`) and are available across all your devices.
 *   **Organization**: Chats are grouped by time period (Today, Yesterday, Previous 7 Days, etc.).
 *   **Unread Indicator**: Chats with new activity show an unread dot in the sidebar until you open them. A chat's three-dot menu has **Mark as unread** to put the dot back; a folder's menu, and the **Chats** section header's own menu, both have **Mark all as read** to clear a folder or your whole chat list in one go.

docs/features/chat-conversations/chat-features/index.mdx

@@ -23,6 +23,14 @@ Open WebUI provides a comprehensive set of chat features designed to enhance you
 
 - **[📁 Folders & Projects](./conversation-organization.md)**: Transform folders into powerful project workspaces with custom system prompts and attached knowledge bases.
 
+![The same response continued, with a rendered mermaid diagram and a task list](/images/features/chat/chat-rich-answer-2.png)
+
+![A response with a syntax-highlighted code block](/images/features/chat/chat-code-answer.png)
+
+![A response rendering LaTeX, a table and a mermaid diagram](/images/features/chat/chat-rich-answer.png)
+
+![A new chat with the model selector and prompt suggestions](/images/features/chat/new-chat-placeholder.png)
+
 - **[🔗 URL Parameters](./url-params.md)**: Configure chat sessions through URL parameters, enabling quick setup of models, tools, and other features.
 
 - **[⚙️ Chat Parameters](./chat-params.md)**: Control system prompts and advanced parameters at different levels (per-chat, per-account, or per-model), and fill placeholders in a shared system prompt with chat or user variables.

docs/features/chat-conversations/chat-features/subagents.mdx

@@ -15,6 +15,8 @@ Sub-agents are disabled by default. An administrator enables them with the [`ENA
 
 Delegation buys focus and parallelism:
 
+![Sub-agent settings](/images/admin/admin-subagents.png)
+
 - **A clean context per task.** The sub-agent gets the task and only the context handed to it, instead of the whole conversation, so a long chat does not dilute the work.
 - **Real parallelism.** When a model requests several delegations in one reply, they run at the same time rather than one after another.
 - **A short answer back.** Only the sub-agent's final result returns to the parent chat. The intermediate tool calls, searches and dead ends stay in the sub-agent's own chat.