Skip to content

Releases: Tencent/WeKnora

v0.2.1

08 Dec 11:57
@lyingbug lyingbug
v0.2.1
da904f4

Choose a tag to compare

View all tags
v0.2.1

[0.2.1] - 2025-12-08

🚀 New Features

  • NEW: Qdrant Vector Database Support
    • Full integration with Qdrant as retriever engine
    • Support for both vector similarity search and full-text keyword search
    • Dynamic collection creation based on embedding dimensions (e.g., weknora_embeddings_768)
    • Professional Chinese word segmentation using jieba for keyword queries

⚡ Infrastructure Improvements

  • IMPROVED: Docker Compose Profile Management
    • Added profiles for optional services: minio, qdrant, neo4j, jaeger, full
    • Enhanced dev.sh script with --minio, --qdrant, --neo4j, --jaeger, --full flags
    • Pinned Qdrant Docker image version to v1.16.2 for stability
  • IMPROVED: Database Migration System
    • Added automatic dirty state recovery for failed migrations
    • Added Neo4j connection retry mechanism with exponential backoff
    • Improved migration error handling and logging
  • IMPROVED: Retriever Engine Configuration
    • Retriever engines now auto-configured from RETRIEVE_DRIVER environment variable
    • No longer required to write retriever config during user registration
    • Added GetEffectiveEngines() method for dynamic engine resolution
    • Centralized engine mapping in types/tenant.go

🐛 Bug Fixes

  • FIXED: Qdrant keyword search returning empty results for Chinese queries
  • FIXED: Image URL validation logic simplified for better compatibility
Loading

v0.2.0

05 Dec 10:10
@begoniezhao begoniezhao
v0.2.0
9ef974e

Choose a tag to compare

View all tags
v0.2.0

WeKnora v0.2.0 Release Notes

Release Date: 2025-12-05

This is a major feature update introducing ReACT Agent mode, Model Management System, FAQ Knowledge Base, and more.

🚀 Major Features

ReACT Agent Mode

  • New ReACT Agent mode with built-in tools for knowledge base retrieval
  • Support for user-configured MCP tools and web search tools to access external services
  • Multiple iterations and reflection to provide comprehensive summary reports
  • Cross-knowledge base retrieval support, allowing selection of multiple knowledge bases

Model Management System

  • Centralized model configuration management
  • Added model selection in knowledge base settings page
  • Built-in model sharing functionality across multiple tenants
  • Tenants can use shared models but are restricted from editing or viewing model details

Multi-Type Knowledge Base Support

  • Support for creating FAQ and document knowledge base types
  • Folder import functionality
  • URL import functionality
  • Tag management system
  • Online knowledge entry capability

FAQ Knowledge Base

  • New FAQ-type knowledge base
  • Batch import and batch delete functionality
  • Online FAQ entry
  • Online FAQ testing capability

Conversation Strategy Configuration

  • Support for configuring Agent models and normal mode models
  • Configurable retrieval thresholds
  • Online Prompt configuration
  • Precise control over multi-turn conversation behavior and retrieval execution methods

Web Search Integration

  • Support for extensible web search engines
  • Built-in DuckDuckGo search engine

MCP Tool Integration

  • Support for extending Agent capabilities through MCP
  • Built-in uvx and npx MCP launcher tools
  • Support for three transport methods: Stdio, HTTP Streamable, and SSE

🎨 UI/UX Improvements

  • REDESIGNED: Conversation interface with Agent mode/normal mode switching
  • REDESIGNED: Login page UI
  • ENHANCED: Session list with time-ordered grouping
  • NEW: Quick Actions area with unified UI visual effects
  • IMPROVED: Knowledge base list cards displaying type, knowledge count, and build status
  • NEW: Breadcrumb navigation in FAQ and document list pages
  • REDESIGNED: Knowledge base settings page with separate configuration for type, models, chunking methods, and advanced settings
  • NEW: Global settings page for permissions configuration
  • ENHANCED: Conversation flow page with tool call execution process display

⚡ Infrastructure Upgrades

  • NEW: MQ-based async task management ensuring task integrity after service restart
  • NEW: Automatic database migration supporting schema and data migration during version upgrades
  • NEW: Fast development mode with docker-compose.dev.yml for quick development environment startup
  • IMPROVED: Log structure optimization
  • NEW: Event subscription and publishing mechanism

Full Changelog: CHANGELOG.md

Loading

v0.1.6

24 Nov 07:32
@begoniezhao begoniezhao
v0.1.6
3e08d3d

Choose a tag to compare

View all tags
v0.1.6

WeKnora v0.1.6 Release Notes

Release Date: 2025-11-24

🚀 New Features

Document Parser Enhancements

  • NEW: Added support for CSV, XLSX, and XLS file parsing
    • Enhanced document processing capabilities with spreadsheet support
    • Improved data extraction from tabular formats
  • NEW: Web page parser implementation
    • Added dedicated web content parsing class
    • Optimized image encoding support for web content
    • Enhanced dependency management for web parsing

Document Processing Improvements

  • NEW: Introduced MarkdownTableUtil for optimized table formatting
    • Reduced unnecessary whitespace in markdown tables
    • Improved table readability and consistency
  • NEW: Document model class implementation
    • Added structured document models for better type safety
    • Optimized configuration and parsing logic
  • UPGRADED: Enhanced document parser to Docx2Parser
    • Improved timeout handling
    • Better image processing logic
    • Optimized OCR backend management

🌍 Internationalization

  • NEW: Multi-language support (English and Russian)
    • Added vue-i18n dependency for internationalization
    • Replaced hardcoded messages with translation functions
    • Updated error messages, console outputs, and UI text
    • Enhanced multilingual documentation with knowledge graph and MCP configuration guides

🐛 Bug Fixes

  • FIXED: Menu component integration issues
  • FIXED: Darwin (macOS) system memory check regex error
    • Resolved empty output issue when checking memory usage on macOS
  • FIXED: Model availability check logic
    • Unified model checking logic across different interfaces
    • Added automatic ":latest" tag for models without specified versions
    • Prevented repeated model pull API calls due to false negatives
  • FIXED: Security vulnerability in Docker Compose configuration
    • Addressed writable filesystem service security issue

🔧 Refactoring & Optimization

  • REFACTORED: Parser logging and API check logic
    • Simplified exception handling
    • Improved error reporting and debugging
  • REFACTORED: Chunk processing
    • Removed unnecessary header handling
    • Updated example usage for better clarity
  • REFACTORED: Module organization
    • Reorganized docreader module files for better structure
    • Updated proto and client import paths
    • Adjusted Docker build configuration
    • Unified module import paths to absolute imports

📚 Documentation Updates

  • UPDATED: API Key acquisition documentation
    • Changed to web registration and account page retrieval method
  • UPDATED: Docker Compose startup configuration guide
    • Added comprehensive setup instructions
    • Adjusted docker-compose.yml configuration
  • UPDATED: Multilingual documentation
    • Added knowledge graph configuration guide
    • Enhanced MCP configuration documentation
    • Updated directory structure documentation
  • REMOVED: Deprecated hybrid search API documentation

🧹 Code Cleanup

  • REMOVED: Redundant Docker build parameters
  • UPDATED: .gitignore rules for better repository hygiene
  • OPTIMIZED: Import statements and type hints
  • CLEANED: Redundant logging and comments

🔄 CI/CD Improvements

  • ADDED: New trigger branches for CI/CD pipeline
  • ADDED: Concurrency control for build processes
  • ADDED: Disk space cleanup automation

👥 Contributors

Special thanks to all contributors who made this release possible:

Contributors

Galaxy, suroy, and 3 other contributors
Loading

v0.1.5

20 Oct 03:19
@begoniezhao begoniezhao
v0.1.5
ca704fa

Choose a tag to compare

View all tags
v0.1.5

概述

  • 本次合并包含若干功能增强、UI/UX 改进、安全修复与错误修复，覆盖后端服务、前端界面、镜像构建和部署脚本等模块。
  • 主要目标：多知识库支持、租户/账户增强、初始化流程优化、前端安全与体验改进，以及 DevOps 脚本和 Docker 镜像构建的健壮性提升。

Highlights

  • Multi-knowledgebase 支持与多数据源检索优化（前端与后端协同改进）。
  • 租户信息页与 API Key 管理功能增强（包括 API Key 生成与复制交互）。
  • 初始化向导（Initialization）结构优化并加入更完善的验证与多模态（VLM）配置校验。
  • 前端安全改进：修复 XSS、隐藏 UI 中的 API Key 等敏感信息。
  • Docker / CI：改进镜像构建脚本与跨平台检测，增强构建信息注入（VERSION / COMMIT / BUILD_TIME / GO_VERSION）。

功能与增强

  • 新增多知识库（Multi-knowledgebases）操作支持与管理（UI 与后端逻辑）。
  • 增强租户信息管理，新增租户页面与更友好的存储配额、使用率展示（参见 TenantInfo.vue）。
  • 初始化向导改进：更严格的表单验证、VLM/OpenAI 兼容 URL 校验及多模态文件上传预览与校验（参见 InitializationContent.vue）。
  • 后端：API Key 自动生成与更新逻辑（见 types.Tenant 与 tenantService.UpdateTenant）。

UI / UX

  • 重构设置页与初始化页面布局，优化按钮状态、加载与提示信息，上传/预览体验改进。
  • 菜单组件增强：多知识库切换与上传前校验逻辑（参见 menu.vue）。
  • 隐藏/保护敏感信息（例如 API Key）并增加复制交互提示（参见 TenantInfo.vue）。

安全修复

  • 修复前端潜在 XSS 漏洞并增强输入校验与内容安全策略。
  • UI 隐藏 API Key 并改进复制行为提示，提升信息泄露防护。

错误修复

  • 修复 OCR/AVX 支持相关问题与图像解析并发错误。
  • 修复前端路由/登录跳转问题与文件下载内容错误。
  • 修复 docreader 服务健康检查与模型预取问题。

DevOps / 构建

  • 改进镜像构建脚本，增强平台/架构检测（amd64 / arm64），并在构建时注入版本信息（见 get_version.sh 与 build_images.sh）。
  • Makefile 与构建流程完善，便于 CI 注入 LDFLAGS（参见 Makefile）。
  • 脚本与迁移工具（migrate）使用和文档完善（参见 migrate.sh）。

文档

  • 更新 README 与多语言文档（EN/CN/JA）与 release/CHANGELOG（详见 CHANGELOG.md 与 README.md）。
  • 补充 MCP server 使用说明与安装（见 mcp-server/INSTALL.md）。

开发者/内部 API 变更（可参考）

  • 新增/变更后端系统信息响应结构：handler.GetSystemInfoResponse。
  • 租户数据结构与 JSON 存储字段：types.Tenant。

What's Changed

New Contributors

Full Changelog: v0.1.3...v0.1.5

Contributors

lyingbug, xxx1111113, and 2 other contributors
Loading

v0.1.4

17 Sep 12:28
@lyingbug lyingbug
v0.1.4
211940b

Choose a tag to compare

View all tags
v0.1.4

🚀 Major Features

  • NEW: Multi-knowledgebases operation support
    • Added comprehensive multi-knowledgebase management functionality
    • Implemented multi-data source search engine configuration and optimization logic
    • Enhanced knowledge base switching and management in UI
  • NEW: Enhanced tenant information management
    • Added dedicated tenant information page
    • Improved user and tenant management capabilities

🎨 UI/UX Improvements

  • REDESIGNED: Settings page with improved layout and functionality
  • ENHANCED: Menu component with multi-knowledgebase support
  • IMPROVED: Initialization configuration page structure
  • OPTIMIZED: Login page and authentication flow

🔒 Security Fixes

  • FIXED: XSS attack vulnerabilities in thinking component
  • FIXED: Content Security Policy (CSP) errors
  • ENHANCED: Frontend security measures and input sanitization

🐛 Bug Fixes

  • FIXED: Login direct page navigation issues
  • FIXED: App LLM model check logic
  • FIXED: Version script functionality
  • FIXED: File download content errors
  • IMPROVED: Document content component display

🧹 Code Cleanup

  • REMOVED: Test data functionality and related APIs
  • SIMPLIFIED: Initialization configuration components
  • CLEANED: Redundant UI components and unused code

What's Changed

New Contributors

Full Changelog: v0.1.3...v0.1.4

Contributors

lyingbug, xxx1111113, and begoniezhao
Loading

v0.1.3

16 Sep 03:19
@lyingbug lyingbug
v0.1.3
5e22f96

Choose a tag to compare

View all tags
v0.1.3

What's Changed

🔒 Security Features

  • NEW: Added login authentication functionality to enhance system security
  • Implemented user authentication and authorization mechanisms
  • Added session management and access control
  • Fixed XSS attack vulnerabilities in frontend components

📚 Documentation Updates

  • Added security notices in all README files (English, Chinese, Japanese)
  • Updated deployment recommendations emphasizing internal/private network deployment
  • Enhanced security guidelines to prevent information leakage risks
  • Fixed documentation spelling issues

🛡️ Security Improvements

  • Hide API keys in UI for security purposes
  • Enhanced input sanitization and XSS protection
  • Added comprehensive security utilities

🐛 Bug Fixes

  • Fixed OCR AVX support issues
  • Improved frontend health check dependencies
  • Enhanced Docker binary downloads for target architecture
  • Fixed COS file service initialization parameters and URL processing logic

🚀 Features & Enhancements

  • Improved application and docreader log output
  • Enhanced frontend routing and authentication flow
  • Added comprehensive user management system
  • Improved initialization configuration handling

🛡️ Security Recommendations

  • Deploy WeKnora services in internal/private network environments
  • Avoid direct exposure to public internet
  • Configure proper firewall rules and access controls
  • Regular updates for security patches and improvements

Full Changelog: v0.1.2...v0.1.3

Contributors

lyingbug and begoniezhao
Loading

v0.1.2

10 Sep 12:36
@lyingbug lyingbug
v0.1.2
6598baa

Choose a tag to compare

View all tags
v0.1.2

主要更新

🐛 错误修复

  • 健康检查: 修复了文档读取器服务的健康检查实现
  • 查询处理: 改进了空查询的处理逻辑
  • OCR模型: 修复了Docker容器中OCR模型预加载的问题
  • 并发处理: 解决了图像解析器的并发错误
  • Makefile: 修复了Docker构建相关的问题

✨ 功能增强

  • 知识库管理: 增强了知识库列值更新方法
  • 端口配置: 新增支持修改监听端口配置

📚 文档更新

  • 添加了Markdown文件处理解析的文档说明
  • 完善了文档处理流程的说明

Full Changelog: v0.1.0...v0.1.2

Loading