Releases: refly-ai/refly
Releases · refly-ai/refly
v0.4.1
v0.4.1 Release Notes
🎯 Summary
🚀 Experience the power of next-generation AI creation with Refly v0.4.1! This game-changing update revolutionizes how you interact with AI through:
- 🧠 Smarter AI Interactions: Dramatically enhanced Q&A capabilities across all modes, delivering more accurate and insightful responses
- 🎨 Visual Innovation: Create and share beautiful visualizations with multi-component support for SVG, Mermaid, and HTML
- 💻 Code Component Revolution: A complete replacement for yourware.so with real-time previews and one-click deployment
- 📋 Enhanced Canvas Experience: New intuitive ways to create and organize your AI workspace
- 🌐 Social Creation: Share your AI creations, code components, and canvases with the community
- 🔄 Seamless Collaboration: One-click sharing of visualizations, components, and entire workspaces
- ⚡️ Performance Boost: Core optimizations for a smoother, more reliable experience
This release transforms Refly into your ultimate AI creative companion, making it more intuitive, powerful, and enjoyable to use than ever before. Join our growing community of creators and start sharing your AI-powered innovations today!
🌟 New Features
Enhanced AI Capabilities
- 🧠 Greatly Improved Q&A Experience
- Optimized basic Q&A, web search, and knowledge base search results
- Enhanced concept explanations with visual demonstrations
- Removed memo content truncation limits for better context understanding
Visualization & Component Features
- 🎨 Multi-Component Visualization
- Support for multiple SVG, Mermaid, and HTML components in a single response
- Easy switching between preview and code views
- Quick component creation for secondary development or fine-tuning
- One-click download or copy to clipboard for SVG and Mermaid diagrams
- Reference code sharing available at 👉 https://refly.ai/share/code/cod-w24oreikpvkdrt2qyl1h1w96
Code Component Generation
- 💻 Advanced Code Component System
- Complete replacement for https://www.yourware.so/
- Real-time rendering of modified code components
- One-click deployment of web pages, SVG, and Mermaid diagrams
- Multiple component support on canvas with sharing capabilities
- Integration with https://ui.shadcn.com/ and Tailwind for React components
- HTML components with https://tailwindcss.com/ support
Canvas Improvements
- 📋 Enhanced Node Organization
- New AI question card creation methods
- Component creation through card drag-and-drop
- Right-click and double-click node menu support
- Quick creation of AI question cards, website cards, and memos
- Full-screen display shortcuts for AI responses and code components
- Customizable node group names and background colors
- Canvas example available at 👉 https://refly.ai/share/canvas/can-ufho0vka7pgxtin1g8hxgjc0
Additional Features
-
📝 Canvas Management
- Support for canvas duplication
- Efficient batch node copying and experimentation
-
💳 Subscription Management
- Support for plan upgrades (e.g., Plus to Max)
- Contact developer required for upgrades (in-product upgrade coming soon)
💫 Core Improvements
- 🔧 Technical Optimizations
- Fixed vertical scrolling issues with preview cards
- Resolved connection line loss problems
- Fixed canvas existence verification after Q&A or canvas creation
- Improved loading experience for complex canvases
- Fixed node connection alignment issues after group dragging
- Added memo text color customization with sharing support
- Enhanced landing page with WeChat group access and improved display
v0.4.0
v0.4.0 Release Notes
🦹 Summary
🎉 Refly's strongest update ever! Brand new code component generation/one-click prototype restoration, canvas sharing, custom prompt functionality, greatly improved search speed, and doubled file upload capacity. Building a more powerful AI creation engine to take your creative work efficiency to the next level!
☄️ Improvements for Self-Deployment
- Local support for using Ollama with complete tutorial
- Greatly optimized login experience for local deployment
- Removed subscription and unrelated login components from local deployment, providing a cleaner local deployment experience
- Support for reverse proxy capabilities, painless deployment on cloud services
- Support for local deployment to display and process static resources, including images, files, and other capabilities
- Support for convenient switching of file processing parsers, including pdfjs and marker
- Support for displaying local execution error stacks for easy debugging and problem feedback
🌟 New Features
- Official launch of Code Artifacts (#546)
- Added "Code Artifacts" skill, supporting AI-generated code components with real-time preview of running results
- Support for generation, display, download, and sharing of various mainstream code types including svg, mermaid, html, react
- svg, mermaid, etc. support direct download as images or copying to clipboard for quick sharing
- Code can be used as context for follow-up questions and modifications, or manually modified and optimized with preview of final results
- Mermaid diagrams in Markdown also support image download operation buttons
- Canvas Sharing and Copying (#536, #544, #547)
- All canvases can be shared as public links, viewable in read-only mode
- Support for one-click copying of canvases shared by others, with subsequent modifications and adjustments possible
- Canvas supports export as images
- We welcome everyone to submit canvas use cases, which we will later showcase as official examples with attribution to all Refly users
- Support for Custom Prompts (#533, #539)
- Added "Custom Prompt" skill, allowing arbitrary configuration of system prompts, Temperature, Top P, and other parameters
- Custom prompt execution results support adjusting system prompts and other parameters for re-running
- Support for cloning custom prompt nodes for questions and modifying system prompts before execution
- Custom prompts support follow-up questions with already set prompts, eliminating the need for frequent additions
- Web and Knowledge Base Search Optimization (#523, #533, #538)
- Optimized query preprocessing logic, supporting questions with any canvas context
- Adjusted result generation logic to prioritize answering questions rather than simply referencing search results
- Improved skill execution speed, greatly reducing search freezes or failures
- Enhanced intent understanding capability, significantly optimizing usability for complex questions
- Question Links Support Automatic Parsing (#535, #545)
- Directly paste website links in the input box to ask questions and get answers without importing resources
- After results are generated, you can view link webpage content and import it to the knowledge base with one click
- Supports all skills
- Brand New Website Nodes and Code Nodes (#546)
- Support for adding and rendering custom websites in the canvas, such as Bilibili videos, Medium articles, Github repositories, etc.
- Support for one-click follow-up questions to AI for content summarization of website nodes
- Code nodes can preview SVG, HTML, React, Mermaid, HTML capabilities and support code modifications
- Code nodes can be selected as context with Artifact skills for iterative code optimization
- File Upload Limit Adjustments (#524)
- Significantly increased file upload limits for paid users
- Plus users can upload up to 10MB, Pro users up to 20MB, Max users up to 30MB
- Limits will be gradually relaxed depending on operational conditions
- Support for Custom Node Connection Lines (#522, #529)
- Now you can directly draw lines from free nodes to connect other nodes
- Any connection line can be deleted
- Comments can be written for connection lines
- For AI question nodes, connecting context nodes to question nodes automatically adds context to the question box
- Professional Website Preview Capabilities (#548)
- Support for landing pages to display images/titles and descriptions in social networks
- Support for automatically generating preview images based on canvas status, optimizing canvas listing page display
- Support for Displaying Inference Model Thinking Process (#520, #534)
- Support for streaming display of thinking chains for Claude 3.7 Sonnet Thinking and DeepSeek R1
- Support for collapsing thinking chains
💫 Core Problem Optimization
- Account settings support avatar modification (#556)
- Compact mode turned on by default and automatically maintained in subsequent questions
- Fixed issue of selected skills being lost when re-running skills (#532)
- Fixed lag and even crash issues in canvas due to nested duplicate contexts (#552)
- Memo nodes support text color modification menu (#553)
- Node preview cards support title modification
- Document editor supplemented with multilingual translation (#543)
- Optimized the issue of model names being compressed when too long at the bottom of answer nodes
- Optimized the effect of automatically generating names for empty canvases (#537)
- Fixed collapsing mode follow-up issue; after setting global node collapse or expansion, subsequent nodes all follow this configuration (#546)
- Support for default canvas without automatic layout, fixing node layout chaos issues
- Removed dark mode processing (#531)
v0.3.0
v0.3.0 Changelog
🦹 Summary
🎉 Major Refly update! Comprehensive upgrades include enhanced knowledge base file processing (supporting 7+ mainstream formats), AI multimodal interaction (supporting multiple image inputs), new DeepSeek R1 chain-of-thought visualization, and improved canvas editing (with undo/redo). Experience smoother and more efficient knowledge management and content creation!
🌟 New Features
- 📚 Official File Upload Support for Knowledge Base (#492, #496, #499)
- Support for 7+ mainstream formats, including PDF, DOCX, RTF, TXT, MD, HTML, and EPUB
- File extension-based icons for better visual identification
- File download capability
- 🖼️ Multimodal AI Query Support (#468, #475)
- Multiple image upload support for queries (drag & drop to input box, click to upload, or direct canvas drag & drop)
- Compatible with various image formats: JPG, PNG, JPEG, WEBP, GIF, TIFF, BMP
- Access to images from entire query history
- Full-screen image preview with rotation, zoom in/out, and download options
- 🤖 AI Capability Updates (#474)
- DeepSeek R1 chain-of-thought process visualization
- Other models can now query based on DeepSeek R1's chain-of-thought process
- Improved performance for AI web search and knowledge base search with DeepSeek R1
- 🔌 Browser Extension Enhancements
- 🎨 Canvas Core Features Update
- Undo/Redo functionality with keyboard shortcut support (#501)
- Memo node color palette with 10+ preset colors for better canvas aesthetics (#482)
- Improved notification display for node deletion and other operations
- AI node title editing and complete prompt display (#497)
- Automatic canvas naming and AI-generated canvas name suggestions (#504)
- 🚀 Resource and AI Response Node Improvements
- 📝 Knowledge Base Operation Updates
- Default actions for empty content: add resource/create document (#481)
💫 Core Issue Fixes
- 🔧 Fixed compact mode failure caused by node stretching
- 🔍 Resolved issue where clicking 'Copy' on AI node code blocks included the 'Copy' text in clipboard
- 🖱️ Hidden node menu during drag operations
- ⚙️ Fixed context and model configuration loss during rerun