Skip to main content
The Web UI is Page Assist’s full-featured interface that provides a complete control center for managing your AI conversations, settings, and data. It offers more screen space and advanced features compared to the sidebar.

Opening the Web UI

Access the Web UI in multiple ways:
Press Ctrl+Shift+L (Windows/Linux) or Cmd+Shift+L (Mac) to open the Web UI in a new tab.

Interface Overview

The Web UI consists of several key areas:

Main Chat Area

The central workspace where conversations take place:
  • Message Display: Full conversation history with formatted responses
  • Code Blocks: Syntax highlighting and copy buttons
  • Markdown Support: Rich text rendering for better readability
  • Image Previews: Inline image display for vision-enabled models
  • Message Actions: Copy, edit, regenerate, or delete individual messages
Located on the left side (toggle with Ctrl+B):
  • Chat History: Browse and search through past conversations
  • New Chat: Create new conversation threads
  • Folders/Organization: Group related chats together
  • Search: Find specific conversations quickly

Input Area

At the bottom of the chat interface:
  • Text Input: Multi-line text area with auto-resize
  • Attachment Options: Upload images, documents, or files
  • Mode Toggles: Quick access to chat modes (webpage, search, knowledge base, vision)
  • Model Selector: Switch AI models on the fly
  • Submit Options: Send with Enter or Ctrl+Enter (configurable)

Settings Panel

Comprehensive configuration options:
1

General Settings

  • Wide screen mode for larger displays
  • Resume last chat on opening
  • Restore last used model for previous chats
  • Generate titles using AI
2

Model Settings

Configure AI models from various providers:
  • Ollama (local models)
  • OpenAI (GPT-4, GPT-3.5)
  • Anthropic (Claude)
  • Google (Gemini)
  • Custom API endpoints
3

RAG Settings

Configure Retrieval Augmented Generation:
  • Embedding model selection
  • Chunk size and overlap
  • Number of retrieved documents
  • Splitting strategy
4

Prompt Management

Create and manage custom prompts:
  • System prompts
  • Quick prompts
  • Copilot prompts

Key Features

Chat Management

Manage unlimited conversations simultaneously:
  • Each chat maintains its own context and history
  • Switch between chats without losing progress
  • Organize chats with custom titles
  • Export or delete conversations as needed
Full conversation history with:
  • Automatic saving to local storage
  • Search and filter capabilities
  • Export to markdown or JSON
  • Import previous conversations
Edit and refine your conversations:
  • Edit previous messages and regenerate responses
  • Delete individual messages
  • Copy message content
  • View message metadata (tokens, model, timestamp)

Advanced Features

Wide Screen Mode

For larger displays, enable wide mode for better readability:
  1. Go to Settings → General Settings
  2. Enable “Enable wide screen mode”
  3. The interface expands to utilize more screen space
Wide mode is recommended for screens 1920px or wider.

Resume Last Chat

Automatically continue where you left off:
  1. Go to Settings → General Settings
  2. Enable “Resume the last chat when opening the Web UI”
  3. Your most recent conversation loads automatically on startup

Model Restoration

Restore the specific model used in each chat:
  1. Go to Settings → General Settings
  2. Enable “Restore last used model for previous chats”
  3. When switching between old chats, the model automatically changes to match

AI Title Generation

Automatically generate descriptive titles for conversations:
  1. Go to Settings → General Settings
  2. Enable “Generate Title using AI”
  3. New chats automatically receive contextual titles based on content

Keyboard Shortcuts

Boost your productivity with keyboard shortcuts:
ActionShortcutDescription
Open Web UICtrl+Shift+LOpen in new tab
New ChatCtrl+Shift+OStart new conversation
Toggle SidebarCtrl+BShow/hide chat history
Focus InputShift+EscJump to message input
Toggle Chat ModeCtrl+ESwitch chat modes
Keyboard shortcuts can be customized in your browser’s extension management page.

Settings and Configuration

Managing Models

The Web UI provides comprehensive model management:
Configure local Ollama models:
  1. Go to Settings → Ollama Settings
  2. Enter your Ollama server URL (default: http://localhost:11434)
  3. Click “Fetch Models” to load available models
  4. Configure default models for chat, embedding, and vision

Knowledge Base Management

Upload and manage your documents:
  1. Go to Settings → Manage Knowledge
  2. Click “Add New Knowledge”
  3. Upload files (PDF, DOCX, TXT, CSV, MD)
  4. Wait for processing and embedding generation
  5. Select knowledge bases to use in conversations
See Knowledge Base for detailed information.

Prompt Library

Create reusable prompts:
  1. Go to Settings → Manage Prompts
  2. Choose prompt type:
    • System Prompts: Set conversation context
    • Quick Prompts: Reusable templates
    • Copilot Prompts: Context menu actions
  3. Create and save your prompts
See Prompts for more details.

Data Management

Export and Backup

1

Export Conversations

  • Right-click on any chat in history
  • Select “Export” to save as JSON or Markdown
  • Choose location and save
2

Export All Data

  • Go to Settings → About
  • Use backup/export options
  • Save all conversations, settings, and knowledge bases
3

Import Data

  • Go to Settings → About
  • Select “Import Data”
  • Choose your backup file
  • Confirm import

Privacy and Storage

All data is stored locally in your browser. Page Assist does not send data to external servers except to your configured AI providers.
  • Chat History: IndexedDB (browser database)
  • Knowledge Base: Browser local storage + embeddings
  • Settings: Chrome storage API
  • Vector Data: Indexed in browser memory
Clearing browser data will delete all conversations and settings. Always backup important data.

Tips and Best Practices

Organization: Use AI-generated titles to keep your chat history organized and searchable.
Model Switching: Different models excel at different tasks. Use GPT-4 for complex reasoning, Claude for long-form content, and local Ollama models for privacy.
Wide Mode: Enable wide mode when working with code or long documents for better readability.

Troubleshooting

  1. Check if the extension is enabled
  2. Try the keyboard shortcut Ctrl+Shift+L
  3. Click the extension icon and select “Open Web UI”
  4. Check browser console for errors
  1. Check browser storage settings
  2. Ensure you haven’t cleared browser data
  3. Try refreshing the page
  4. Check IndexedDB in browser DevTools
  1. Grant storage permissions to the extension
  2. Check if you’re in private/incognito mode
  3. Try restarting the browser
  4. Verify storage quota isn’t exceeded

Next Steps

Internet Search

Add real-time web search to your conversations

Knowledge Base

Upload and chat with your documents

Prompts

Create custom prompts and templates

Vision

Analyze images with vision-capable models

Build docs developers (and LLMs) love