- Added infinite scroll functionality to load older messages when the user scrolls near the top of the chat.
- Implemented pagination state management to track loading status and available messages.
- Enhanced ChatMessage component with React.memo for performance optimization during streaming.
- Updated database interactions to support paginated message retrieval, improving efficiency in loading chat history.
- Added speculative search functionality to enhance query processing by detecting when a web search may be needed based on user input patterns.
- Integrated commands for managing embeddings, including downloading models, checking availability, calculating relevance scores, generating embeddings, and pruning context.
- Optimized chat streaming by buffering tokens to reduce overhead and improve responsiveness.
- Implemented lazy initialization for the headless browser to conserve memory until needed.
- Enhanced web scraping capabilities with a static scraping method for faster content retrieval.
- Added search match navigation to allow users to cycle through search results in chat sessions.
- Implemented highlighting of search terms in chat messages for better visibility.
- Updated sidebar to display match counts for sessions based on search results.
- Enhanced session search logic in the database to include match counts for improved user experience.
- Refactored chat message component to support dynamic highlighting of search terms.
- Added a new TitleBar component to enhance the UI consistency across chat, settings, and tasks pages.
- Updated layout structure to support responsive design and improve user experience.
- Adjusted container styles to ensure proper overflow handling and visual appeal.
- Enhanced Tauri configuration for improved window dimensions and capabilities.
- Updated global styles to improve layout and prevent overflow in chat and settings pages.
- Introduced new sidebar chat item styles for better truncation and overflow handling.
- Enhanced settings page layout for improved responsiveness and user experience.
- Added icons to category selection in chat input for better visual representation.
- Refactored task management UI for improved accessibility and usability.
- Added search capability to the chat interface, allowing users to find sessions by title or message content.
- Integrated debounce logic for search input to enhance performance and user experience.
- Updated the sidebar to include a search input field and loading indicator during search operations.
- Implemented full-text search in the database for efficient session retrieval based on user queries.
- Enhanced session management by filtering out orphan sessions during search results.
- Introduced adaptive timeout logic for web searches and chat streaming, improving responsiveness and efficiency.
- Updated `smartSearchRag` method to support timeout adjustments based on search rounds.
- Enhanced `executeProgressiveSearch` to utilize adaptive timeouts and improve search result handling.
- Added new utility functions for calculating adaptive timeouts based on rounds and attempts.
- Integrated event listeners for chat session management, improving user experience during chat interactions.
- Refactored chat message handling to accommodate new streaming and timeout features.
- Added custom scrollbar styles for sources display to improve aesthetics and usability.
- Introduced animations for reasoning steps to enhance user experience during chat interactions.
- Refactored chat page to group thinking messages, improving message handling and display.
- Updated sources display component for better favicon handling and user interaction.
- Added custom scrollbar styles for improved aesthetics and usability across the interface.
- Implemented responsive adjustments for chat sidebar and input components to enhance mobile experience.
- Integrated tooltip components in select elements for better user guidance and information display.
- Updated chat input and message components for improved styling and functionality.
- Enhanced settings page with semantic query expansion options and improved model selection UI.
- Refactored sidebar list to include better date formatting and tooltip support for session titles.
- Introduced GPU stats monitoring in the system panel for better hardware insights.
- Added `emoji-regex` and `remove-accents` packages to improve text processing capabilities.
- Implemented automatic Ollama startup in the chat page for better user experience.
- Enhanced setup page to include GPU selection based on hardware specifications.
- Updated chat input to support real-time validation and improved user feedback.
- Refactored message handling in chat to incorporate new processing features.
Add metadata-first search approach followed by targeted scraping of top URLs. Includes:
- New `smartSearchRag` method in web search service
- Metadata-only search endpoint in Tauri backend
- Bulk URL scraping capability
- Payload content override in chat messages
- Added state management for web context and sources to improve debugging capabilities in chat.
- Implemented a debug view for displaying extracted context and sources used in chat responses.
- Refactored message handling to incorporate web context into user messages, enhancing response accuracy.
- Updated UI components to support new debugging features and improve user interaction.
- Integrated useRouter for navigation in chat and settings pages, improving user experience.
- Added detailed debug logging for web context generation and chat payloads to assist in troubleshooting.
- Updated settings page to include a hardware dashboard and enhanced sources configuration management.
- Implemented auto-start feature for the application and improved task management with new scheduled task options.
- Refined user interface components for better accessibility and usability across chat and settings pages.
- Added new Radix UI components including checkbox, label, popover, slider, switch, and tooltip to improve UI interactions.
- Integrated react-syntax-highlighter for better code rendering in chat messages.
- Updated package.json and pnpm-lock.yaml to include new dependencies and ensure compatibility.
- Enhanced chat input to support web search toggling, improving user experience during message composition.
- Implemented auto-saving of chat sessions and improved session management features.
- Refactored chat message rendering to clean up metadata and improve display quality.
- Added support for rendering markdown in chat messages using ReactMarkdown with custom renderers.
- Integrated a default format prompt for the chat system, improving user experience by initializing with a predefined prompt.
- Updated the prompt generator to handle model selection more robustly, including loading states and fallback options for model selection.
- Enhanced UI components for better accessibility and user feedback during prompt generation.
- Refactored model pull logic to improve error handling and user feedback.
- Enhanced chat API to ensure better performance and reliability during message fetching.
- Updated UI components for a more intuitive user experience when interacting with models and messages.
- Deleted .gitignore, biome.json, next.config.ts, package.json, pnpm-lock.yaml, pnpm-workspace.yaml, postcss.config.mjs, README.md, and various API, component, and utility files to clean up the codebase.
- Removed unused database files and migration scripts to streamline the project structure.
- Eliminated obsolete hooks and services to enhance maintainability and reduce clutter.
- Add catalog metadata lookup for better error messages with hints (e.g., for missing manifests or tags)
- Persist downloaded model references in saved remote models for future reuse
- Replace searchRemoteModels import with getSavedRemoteModels in search route
- Enhance pull progress UI to display download bytes, digest, and fallback message when data is unavailable
- Improve error payload with model details, URL, and tags count to guide users toward valid tags or models
- Add pagination support to /api/conversations/[id]/messages with limit and before query params, returning hasMore and cursor for efficient message fetching
- Enhance /api/ollama/chat by adding non-blocking Ollama availability check and conditionally disabling debug logging in production环境下Featured
Replace hardcoded list of popular models with dynamic catalog from getCatalogModels().
Enable searching by model name or description and include model descriptions in results. Improves discoverability and maintains up-to-date model list without manual updates. Database files updated accordingly.
Add `ensureOllamaAvailable` function to lib/ollama.ts for checking and waiting for Ollama server health with configurable timeout.
Integrate the check in GET /api/ollama/models route with 3s timeout to prevent UI blocking, and in POST /api/ollama/pull route with 20s timeout to ensure availability before pulling models.
Update ChatContainer to always render ModelDropdown for better UX when no model is selected.
Removed dependencies on MCPCacheRepository and PulseMCPService from MCP routes to simplify installation and listing logic, avoiding reliance on potentially stale cached data and streamlining the codebase. Updated available-for-chat filter to include MCPs without explicit status.
Add support for Model Context Protocol (MCP) tools in the Ollama chat API. Detect model capabilities to use native tools or prompt engineering. Handle tool calls, execute them via MCPExecutor, and inject results back into the conversation for seamless tool-assisted responses. This enhances chat functionality by enabling external tool integration.
- Support installing MCP servers from GitHub repos by converting 'github:user/repo' to 'git+https://github.com/user/repo.git' to avoid SSH issues and improve npm compatibility
- Display available tools in MCPCard with badges, showing up to 6 tools and total count for better visibility of server capabilities
- Remove unused onViewDetails prop and make uninstall button full-width for improved UI consistency
- Add /mcp-servers/ to .gitignore for MCP server installations
- Extend mcp_installations table with status, logs, and validation fields
- Refactor MCP install route to support custom configs, enable logs, and async installation
- Improve MCPSyncService with promise-based syncing to prevent concurrent operations
This update improves MCP management by adding robust installation tracking, custom configuration support, and better error handling for a more reliable user experience.
- Updated imports to use PulseMCPSearchParams and PulseMCPService instead of DeepNLP equivalents
- Replaced DeepNLP API calls with PulseMCP API endpoints and parameters
- Modified cached MCP transformation to manual mapping for PulseMCP data format
- Enhanced error handling and retry logic in server tools retrieval
- Added PulseMCP API base URL constant for centralized configuration
This change switches the underlying MCP provider from DeepNLP to PulseMCP, ensuring compatibility with the new API while maintaining existing functionality for MCP listing and tool retrieval.
Add comprehensive CSS styles for the MCP Marketplace interface, including card hover effects, responsive grid layout, modal backdrop blur, category badges, rating stars, install buttons, and loading animations. Also include custom scrollbar styling for the model selector to enhance user experience and visual consistency.
- Update .gitignore to exclude database files, extensions, and .cursor directory
- Enhance chat streaming API with safe enqueue and close functions to prevent errors
- Integrate ConversationSidebar component into ClientHome for better UI
- Add dependencies like better-sqlite3 and esbuild packages for database functionality
This commit introduces database persistence for conversations, improves error handling in streaming responses, and adds a sidebar for managing chats, enhancing overall app robustness and user experience.
Updated README.md from a detailed OllaHub project description to the standard Next.js getting started template, likely to initialize or reset the project as a Next.js application.
