flutter_gen_ai_chat_ui 2.3.0 copy "flutter_gen_ai_chat_ui: ^2.3.0" to clipboard
flutter_gen_ai_chat_ui: ^2.3.0 copied to clipboard

High-performance Flutter UI kit for AI chat: streaming markdown, code highlighting, theming, and customizable integration hooks for major LLMs.

Flutter Gen AI Chat UI #

pub package License: MIT

A modern, minimalistic chat UI kit designed specifically for AI applications built with Flutter. Create beautiful interfaces for ChatGPT, Google Gemini, Anthropic Claude, Llama, and other LLM-powered chatbots with features like streaming responses, markdown support, code highlighting, and extensive customization options.

Perfect for building AI assistants, customer support bots, knowledge base chatbots, language tutors, and any conversational AI application.

Development Status: This package is under active development. You may encounter breaking changes with each update as we improve the API and add new features. Please check the CHANGELOG before updating to a new version.

Table of Contents #

Dark Mode
Dark Mode
Chat Demo
Chat Demo

Features #

Core Features #

  • 🎨 Dark/light mode with adaptive theming
  • 💫 Word-by-word streaming with animations (like ChatGPT and Claude)
  • 📝 Enhanced markdown support with code highlighting for technical content
  • 🎤 Optional speech-to-text integration
  • 📱 Responsive layout with customizable width
  • 🌐 RTL language support for global applications
  • ⚡ High performance message handling for large conversations
  • 📊 Improved pagination support for message history

AI-Specific Features #

  • 👋 Customizable welcome message similar to ChatGPT and other AI assistants
  • ❓ Example questions component for user guidance
  • 💬 Persistent example questions for better user experience
  • 🔄 AI typing indicators like modern chatbot interfaces
  • 📜 Streaming markdown rendering for code and rich content

UI Components #

  • 💬 Customizable message bubbles with modern design options
  • ⌨️ Multiple input field styles (minimal, glassmorphic, custom)
  • 🔄 Loading indicators with shimmer effects
  • ⬇️ Smart scroll management for chat history
  • 🎨 Enhanced theme customization to match your brand
  • 📝 Better code block styling for developers

This UI kit works seamlessly with:

  • OpenAI (ChatGPT, GPT-4)
  • Google (Gemini, PaLM)
  • Anthropic (Claude)
  • Mistral AI
  • Llama 2/3
  • Cohere
  • And any custom AI/LLM API

Installation #

Add this to your package's pubspec.yaml file:

dependencies:
  flutter_gen_ai_chat_ui: ^2.1.2

Then run:

flutter pub get

⚠️ Important: This package is under active development. We recommend pinning to a specific version in your pubspec.yaml to avoid unexpected breaking changes when you update. Always check the CHANGELOG before upgrading.

Compatibility Note: Version 2.1.2 removes permission_handler and several other unused dependencies, significantly reducing the package footprint and eliminating SDK conflicts. Speech-to-text functionality is fully optional and must be implemented by the app developer. See the Compatibility Guide for implementation details.

Basic Usage #

import 'package:flutter_gen_ai_chat_ui/flutter_gen_ai_chat_ui.dart';

class ChatScreen extends StatefulWidget {
  @override
  _ChatScreenState createState() => _ChatScreenState();
}

class _ChatScreenState extends State<ChatScreen> {
  final _controller = ChatMessagesController();
  final _currentUser = ChatUser(id: 'user', firstName: 'User');
  final _aiUser = ChatUser(id: 'ai', firstName: 'AI Assistant');
  bool _isLoading = false;

  @override
  Widget build(BuildContext context) {
    return Scaffold(
      appBar: AppBar(title: Text('AI Chat')),
      body: AiChatWidget(
        // Required parameters
        currentUser: _currentUser,
        aiUser: _aiUser,
        controller: _controller,
        onSendMessage: _handleSendMessage,
        
        // Optional parameters
        loadingConfig: LoadingConfig(isLoading: _isLoading),
        inputOptions: InputOptions(
          hintText: 'Ask me anything...',
          sendOnEnter: true,
        ),
        welcomeMessageConfig: WelcomeMessageConfig(
          title: 'Welcome to AI Chat',
          questionsSectionTitle: 'Try asking me:',
        ),
        exampleQuestions: [
          ExampleQuestion(question: "What can you help me with?"),
          ExampleQuestion(question: "Tell me about your features"),
        ],
      ),
    );
  }

  Future<void> _handleSendMessage(ChatMessage message) async {
    setState(() => _isLoading = true);
    
    try {
      // Your AI service logic here
      await Future.delayed(Duration(seconds: 1)); // Simulating API call
      
      // Add AI response
      _controller.addMessage(ChatMessage(
        text: "This is a response to: ${message.text}",
        user: _aiUser,
        createdAt: DateTime.now(),
      ));
    } finally {
      setState(() => _isLoading = false);
    }
  }
}

Configuration Options #

AiChatWidget Parameters #

Required Parameters

AiChatWidget(
  // Required parameters
  currentUser: ChatUser(...),  // The current user
  aiUser: ChatUser(...),       // The AI assistant
  controller: ChatMessagesController(),  // Message controller
  onSendMessage: (message) {   // Message handler
    // Handle user messages here
  },
  
  // ... optional parameters
)

Optional Parameters

AiChatWidget(
  // ... required parameters
  
  // Message display options
  messages: [],                // Optional list of messages (if not using controller)
  messageOptions: MessageOptions(...),  // Message bubble styling
  messageListOptions: MessageListOptions(...),  // Message list behavior
  
  // Input field customization
  inputOptions: InputOptions(...),  // Input field styling and behavior
  readOnly: false,             // Whether the chat is read-only
  
  // AI-specific features
  exampleQuestions: [          // Suggested questions for users
    ExampleQuestion(question: 'What is AI?'),
  ],
  persistentExampleQuestions: true,  // Keep questions visible after welcome
  enableAnimation: true,       // Enable message animations
  enableMarkdownStreaming: true,  // Enable streaming text
  streamingDuration: Duration(milliseconds: 30),  // Stream speed
  welcomeMessageConfig: WelcomeMessageConfig(...),  // Welcome message styling
  
  // Loading states
  loadingConfig: LoadingConfig(  // Loading configuration
    isLoading: false,
    showCenteredIndicator: true,
  ),
  
  // Pagination
  paginationConfig: PaginationConfig(  // Pagination configuration
    enabled: true,
    reverseOrder: true,  // Newest messages at bottom
  ),
  
  // Layout
  maxWidth: 800,             // Maximum width
  padding: EdgeInsets.all(16),  // Overall padding
  
  // Scroll behavior
  scrollBehaviorConfig: ScrollBehaviorConfig(
    // Control auto-scrolling behavior
    autoScrollBehavior: AutoScrollBehavior.onUserMessageOnly,
    // Scroll to first message of a response instead of the last (for long responses)
    scrollToFirstResponseMessage: true,
  ),
)

Input Field Customization #

The package offers multiple ways to style the input field:

Default Input

InputOptions(
  // Basic properties
  sendOnEnter: true,
  
  // Styling
  textStyle: TextStyle(...),
  decoration: InputDecoration(...),
)

Minimal Input

InputOptions.minimal(
  hintText: 'Ask a question...',
  textColor: Colors.black,
  hintColor: Colors.grey,
  backgroundColor: Colors.white,
  borderRadius: 24.0,
)

Glassmorphic (Frosted Glass) Input

InputOptions.glassmorphic(
  colors: [Colors.blue.withOpacityCompat(0.2), Colors.purple.withOpacityCompat(0.2)],
  borderRadius: 24.0,
  blurStrength: 10.0,
  hintText: 'Ask me anything...',
  textColor: Colors.white,
)

Custom Input

InputOptions.custom(
  decoration: yourCustomDecoration,
  textStyle: yourCustomTextStyle,
  sendButtonBuilder: (onSend) => CustomSendButton(onSend: onSend),
)

Always-Visible Send Button Without Focus Issues (version 2.0.4+)

The send button is now hardcoded to always be visible by design, regardless of text content. This removes the need for an explicit setting and ensures a consistent experience across the package.

By default:

  • The send button is always shown regardless of text input
  • Focus is maintained when tapping outside the input field
  • The keyboard's send button is disabled by default to prevent focus issues
// Configure input options to ensure a consistent typing experience
InputOptions(
  // Prevent losing focus when tapping outside
  unfocusOnTapOutside: false,
  
  // Use newline for Enter key to prevent keyboard focus issues
  textInputAction: TextInputAction.newline,
)

Scroll Behavior Configuration #

Control how the chat widget scrolls when new messages are added:

// Default configuration with manual parameters
ScrollBehaviorConfig(
  // When to auto-scroll (one of: always, onNewMessage, onUserMessageOnly, never)
  autoScrollBehavior: AutoScrollBehavior.onUserMessageOnly,
  
  // Fix for long responses: scroll to first message of response instead of the last message
  // This prevents the top part of long AI responses from being pushed out of view
  scrollToFirstResponseMessage: true,
  
  // Customize animation
  scrollAnimationDuration: Duration(milliseconds: 300),
  scrollAnimationCurve: Curves.easeOut,
)

// Or use convenient preset configurations:
ScrollBehaviorConfig.smooth() // Smooth easeInOutCubic curve
ScrollBehaviorConfig.bouncy() // Bouncy elasticOut curve
ScrollBehaviorConfig.fast()   // Quick scrolling with minimal animation
ScrollBehaviorConfig.decelerate() // Starts fast, slows down
ScrollBehaviorConfig.accelerate() // Starts slow, speeds up

Use Case: Preventing Long Responses from Auto-Scrolling

When an AI returns a long response in multiple parts, scrollToFirstResponseMessage ensures users see the beginning of the response rather than being automatically scrolled to the end. This is crucial for readability, especially with complex information.

For optimal scroll behavior with long responses:

  1. Mark the first message in a response with 'isStartOfResponse': true
  2. Link related messages in a chain using a shared 'responseId' property
  3. Set scrollToFirstResponseMessage: true in your configuration

For optimal scroll behavior with long responses:

  1. Mark the first message in a response with 'isStartOfResponse': true
  2. Link related messages in a chain using a shared 'responseId' property
  3. Set scrollToFirstResponseMessage: true in your configuration

Message Bubble Customization #

MessageOptions(
  // Basic options
  showTime: true,
  showUserName: true,
  
  // Styling
  bubbleStyle: BubbleStyle(
    userBubbleColor: Colors.blue.withOpacityCompat(0.1),
    aiBubbleColor: Colors.white,
    userNameColor: Colors.blue.shade700,
    aiNameColor: Colors.purple.shade700,
    bottomLeftRadius: 22,
    bottomRightRadius: 22,
    enableShadow: true,
  ),
)
34
likes
140
points
280
downloads

Publisher

verified publisherdilacode.com

Weekly Downloads

High-performance Flutter UI kit for AI chat: streaming markdown, code highlighting, theming, and customizable integration hooks for major LLMs.

Repository (GitHub)
View/report issues

Documentation

Documentation
API reference

License

MIT (license)

Dependencies

flutter, flutter_markdown, flutter_streaming_text_markdown, google_fonts, shimmer

More

Packages that depend on flutter_gen_ai_chat_ui