[NEW][vane][1.1.20]rebrand Perplexica

vane/Chart.yaml

@@ -0,0 +1,6 @@
+apiVersion: v2
+appVersion: '1.12.0'
+description: Vane - An open-source AI-powered search engine alternative to Perplexity AI
+name: vane
+type: application
+version: '1.1.20'

vane/OlaresManifest.yaml

@@ -0,0 +1,200 @@
+olaresManifest.version: '0.11.0'
+olaresManifest.type: app
+metadata:
+  name: vane
+  icon: https://app.cdn.olares.com/appstore/vane/icon.png
+  description: Vane (previously Perplexica) is an AI-powered answering engine.
+  appid: vane
+  title: Vane
+  version: '1.1.20'
+  categories:
+  - Productivity_v112
+  - Utilities_v112
+  - Productivity
+entrances:
+- authLevel: private
+  host: vaneingress
+  icon: https://app.cdn.olares.com/appstore/vane/icon.png
+  name: vane
+  openMethod: window
+  port: 8080
+  title: Vane
+spec:
+  versionName: '1.12.0'
+  promoteImage:
+    - https://app.cdn.olares.com/appstore/vane/1.webp
+    - https://app.cdn.olares.com/appstore/vane/2.webp
+    - https://app.cdn.olares.com/appstore/vane/3.webp
+    - https://app.cdn.olares.com/appstore/vane/4.webp
+  fullDescription: |
+    Vane (Previously Perplexica) is a privacy-focused AI answering engine that runs entirely on your own hardware. It combines knowledge from the vast internet with support for local LLMs (Ollama) and cloud providers (OpenAI, Claude, Groq), delivering accurate answers with cited sources while keeping your searches completely private.
+
+    Features
+    - Support for all major AI providers - Use local LLMs through Ollama or connect to OpenAI, Anthropic Claude, Google Gemini, Groq, and more. Mix and match models based on your needs.
+    - Smart search modes - Choose Speed Mode when you need quick answers, Balanced Mode for everyday searches, or Quality Mode for deep research.
+    - Pick your sources - Search the web, discussions, or academic papers. More sources and integrations are in progress.
+    - Widgets - Helpful UI cards that show up when relevant, like weather, calculations, stock prices, and other quick lookups.
+    - Web search powered by SearxNG - Access multiple search engines while keeping your identity private. Support for Tavily and Exa coming soon for even better results.
+    - Image and video search - Find visual content alongside text results. Search isn't limited to just articles anymore.
+    - File uploads - Upload documents and ask questions about them. PDFs, text files, images - Vane understands them all.
+    - Search specific domains - Limit your search to specific websites when you know where to look. Perfect for technical documentation or research papers.
+    - Smart suggestions - Get intelligent search suggestions as you type, helping you formulate better queries.
+    - Discover - Browse interesting articles and trending content throughout the day. Stay informed without even searching.
+    - Search history - Every search is saved locally so you can revisit your discoveries anytime. Your research is never lost.
+    - More coming soon - We're actively developing new features based on community feedback. Join our Discord to help shape Vane's future!
+
+  upgradeDescription: |
+    Upgrade app version to 1.12.0
+
+    This is a major release featuring a complete architectural overhaul. We've removed Langchain in favor of a custom implementation for low-level control over streaming, generation, and provider-specific features.
+
+    What's Changed
+
+    General Updates:
+    - Renamed providers to connections for better UX
+    - Fixed SearxNG build and startup errors
+    - Added new agents DIR, migrated suggestions, video and audio agents
+    - Added message and chunk types for better type safety
+    - Added code block rendering with syntax highlighting
+    - Added version number and GitHub link in settings
+    - Various UI improvements with animations via Framer Motion
+
+    Langchain Removal & Custom Provider System:
+    - Removed Langchain and implemented custom base and provider classes
+    - Implemented function calling with partial streaming
+
+    New Session Manager:
+    - Added session manager with automatic stream reconnection
+    - Sessions can be restored via ID if page refreshes or stream disconnects
+
+    Widgets:
+    - Added widgets for weather information, stock market data, and mathematical calculations
+
+    Query Classification & Researcher with Actions:
+    - Each query is now classified before research begins
+    - Researcher uses actions with tool calling for web search, scraping, specific website search, discussion search, file uploads search, etc.
+
+    Deep Research Mode (Beta):
+    - Added quality search mode where the LLM reasons iteratively over collected data
+    - Allows deeper exploration of topics and preparing detailed reports
+
+    Updated Research Modes:
+    - Balanced Mode: Now forces the LLM to reason with limited maximum actions
+    - Speed Mode: Runs without any reasoning for fast responses
+
+    Block & JSON Patch Based Streaming:
+    - Each step of the LLM is now streamed for real-time visibility
+
+    New Upload Manager & Enhanced File Search:
+    - Added upload manager supporting PDF, DOCX, and text files
+    - Enhanced file search with RRF (Reciprocal Rank Fusion) for better retrieval quality
+
+    Redesigned Source System:
+    - Focus modes removed and replaced with 3 sources: web, academic, and discussions
+    - Sources can be toggled individually or used all together
+
+    Full release note at: https://github.com/ItzCrazyKns/Vane/releases/tag/v1.12.0
+
+  developer: ItzCrazyKns
+  website: https://github.com/ItzCrazyKns/Vane?tab=readme-ov-file#readme-ov-file
+  sourceCode: https://github.com/ItzCrazyKns/Vane
+  submitter: Olares
+  locale:
+  - en-US
+  - zh-CN
+  doc: https://github.com/ItzCrazyKns/Vane?tab=readme-ov-file#readme-ov-file
+  license:
+  - text: MIT
+    url: https://github.com/ItzCrazyKns/Vane?tab=readme-ov-file#MIT-1-ov-file
+  limitedCpu: 4.5
+  limitedDisk: 50Gi
+  limitedMemory: 4.5Gi
+  requiredCpu: 50m
+  requiredDisk: 50Mi
+  requiredMemory: 1000Mi
+  supportArch:
+  - amd64
+  - arm64
+permission:
+  appData: true
+  appCache: true
+middleware:
+  postgres:
+    username: vane
+    password: vane
+    databases:
+    - name: vane
+      distributed: true
+options:
+  apiTimeout: 0  
+  dependencies:
+  - name: olares
+    version: '>=1.12.3-0'
+    type: system
+  - name: ollamav2
+    type: application
+    version: '>=1.0.0'
+  - name: searxngv2
+    type: application
+    version: '>=1.0.0'
+envs:
+  - envName: OPENAI_APIKEY
+    required: false
+    applyOnChange: true
+    valueFrom:
+      envName: OLARES_USER_OPENAI_APIKEY
+  - envName: CUSTOM_OPENAI_URL
+    required: false
+    applyOnChange: true
+    valueFrom:
+      envName: OLARES_USER_CUSTOM_OPENAI_SERVICE      
+  - envName: CUSTOM_OPENAI_APIKEY
+    applyOnChange: true    
+    required: false
+    valueFrom:
+      envName: OLARES_USER_CUSTOM_OPENAI_APIKEY
+  - envName: CUSTOM_OPENAI_MODEL_NAME
+    required: false
+    type: string
+    editable: true
+    applyOnChange: true
+  - envName: GROQ_APIKEY
+    required: false
+    type: password
+    editable: true
+    applyOnChange: true
+  - envName: ANTHROPIC_APIKEY
+    required: false
+    type: password
+    editable: true
+    applyOnChange: true
+  - envName: GEMINI_APIKEY
+    required: false
+    type: password
+    editable: true
+    applyOnChange: true
+  - envName: SEARXNG_API_URL
+    required: false
+    type: url
+    editable: true
+    applyOnChange: true
+    description: "SearxNG API URL"
+  - envName: OLLAMA_CONNECTION_NAME
+    required: false
+    type: string
+    editable: true
+    applyOnChange: true
+    default: "Ollama"
+    description: "Ollama connection name"
+  - envName: OLLAMA_API_KEY
+    required: false
+    type: password
+    editable: true
+    applyOnChange: true
+    description: "Ollama API key (usually not required, leave empty)"
+  - envName: OLLAMA_MODEL
+    required: false
+    type: string
+    editable: true
+    applyOnChange: true
+    description: "Ollama model name"

vane/i18n/en-US/OlaresManifest.yaml

@@ -0,0 +1,72 @@
+metadata:
+  title: Vane
+  description: Vane (previously Perplexica) is an AI-powered answering engine.
+spec:
+  fullDescription: |
+    Vane (Previously Perplexica) is a privacy-focused AI answering engine that runs entirely on your own hardware. It combines knowledge from the vast internet with support for local LLMs (Ollama) and cloud providers (OpenAI, Claude, Groq), delivering accurate answers with cited sources while keeping your searches completely private.
+
+    Features
+    - Support for all major AI providers - Use local LLMs through Ollama or connect to OpenAI, Anthropic Claude, Google Gemini, Groq, and more. Mix and match models based on your needs.
+    - Smart search modes - Choose Speed Mode when you need quick answers, Balanced Mode for everyday searches, or Quality Mode for deep research.
+    - Pick your sources - Search the web, discussions, or academic papers. More sources and integrations are in progress.
+    - Widgets - Helpful UI cards that show up when relevant, like weather, calculations, stock prices, and other quick lookups.
+    - Web search powered by SearxNG - Access multiple search engines while keeping your identity private. Support for Tavily and Exa coming soon for even better results.
+    - Image and video search - Find visual content alongside text results. Search isn't limited to just articles anymore.
+    - File uploads - Upload documents and ask questions about them. PDFs, text files, images - Vane understands them all.
+    - Search specific domains - Limit your search to specific websites when you know where to look. Perfect for technical documentation or research papers.
+    - Smart suggestions - Get intelligent search suggestions as you type, helping you formulate better queries.
+    - Discover - Browse interesting articles and trending content throughout the day. Stay informed without even searching.
+    - Search history - Every search is saved locally so you can revisit your discoveries anytime. Your research is never lost.
+    - More coming soon - We're actively developing new features based on community feedback. Join our Discord to help shape Vane's future!
+
+  upgradeDescription: |
+    Upgrade app version to 1.12.0
+
+    This is a major release featuring a complete architectural overhaul. We've removed Langchain in favor of a custom implementation for low-level control over streaming, generation, and provider-specific features.
+
+    What's Changed
+
+    General Updates:
+    - Renamed providers to connections for better UX
+    - Fixed SearxNG build and startup errors
+    - Added new agents DIR, migrated suggestions, video and audio agents
+    - Added message and chunk types for better type safety
+    - Added code block rendering with syntax highlighting
+    - Added version number and GitHub link in settings
+    - Various UI improvements with animations via Framer Motion
+
+    Langchain Removal & Custom Provider System:
+    - Removed Langchain and implemented custom base and provider classes
+    - Implemented function calling with partial streaming
+
+    New Session Manager:
+    - Added session manager with automatic stream reconnection
+    - Sessions can be restored via ID if page refreshes or stream disconnects
+
+    Widgets:
+    - Added widgets for weather information, stock market data, and mathematical calculations
+
+    Query Classification & Researcher with Actions:
+    - Each query is now classified before research begins
+    - Researcher uses actions with tool calling for web search, scraping, specific website search, discussion search, file uploads search, etc.
+
+    Deep Research Mode (Beta):
+    - Added quality search mode where the LLM reasons iteratively over collected data
+    - Allows deeper exploration of topics and preparing detailed reports
+
+    Updated Research Modes:
+    - Balanced Mode: Now forces the LLM to reason with limited maximum actions
+    - Speed Mode: Runs without any reasoning for fast responses
+
+    Block & JSON Patch Based Streaming:
+    - Each step of the LLM is now streamed for real-time visibility
+
+    New Upload Manager & Enhanced File Search:
+    - Added upload manager supporting PDF, DOCX, and text files
+    - Enhanced file search with RRF (Reciprocal Rank Fusion) for better retrieval quality
+
+    Redesigned Source System:
+    - Focus modes removed and replaced with 3 sources: web, academic, and discussions
+    - Sources can be toggled individually or used all together
+
+    Full release note at: https://github.com/ItzCrazyKns/Vane/releases/tag/v1.12.0

vane/i18n/zh-CN/OlaresManifest.yaml

@@ -0,0 +1,72 @@
+metadata:
+  description: Vane（原名 Perplexica）是一款 AI 驱动的智能问答引擎。
+  title: Vane
+spec:
+  fullDescription: |
+    Vane（原名 Perplexica）是一款注重隐私的 AI 问答引擎，能够在您的本地硬件上完全本地运行。它结合了来自互联网的丰富知识，并支持本地 LLM（Ollama）及云端提供商（如 OpenAI、Claude、Groq 等），为您提供带有可靠引用来源的精准答案，同时保证搜索过程中的隐私安全。
+
+    主要特性
+    - 支持主流 AI 提供商：可通过 Ollama 使用本地大模型，或连接 OpenAI、Anthropic Claude、Google Gemini、Groq 等云产品，根据需要自由切换和组合模型
+    - 智能搜索模式：支持速度模式（快速回复）、平衡模式（日常搜索）和质量模式（深度研究），满足不同场景需求
+    - 灵活选择信息源：可从网络、论坛、学术论文中检索信息，更多数据源及集成正在开发中
+    - 小部件功能：在需要时展示便捷的 UI 卡片，如天气、计算、股价等实用信息
+    - SearxNG 驱动的网络搜索：使用多引擎保障隐私，未来还将支持 Tavily 和 Exa，进一步提升搜索结果
+    - 图片与视频搜索：可同时检索并展示多媒体内容，搜索不再局限于文章
+    - 文件上传：支持上传文档并进行问答，识别 PDF、文本、图片等多种格式
+    - 针对特定站点搜索：可限定在特定网站查找内容，非常适合查阅技术文档或学术资料
+    - 智能建议：输入时自动补全和建议搜索内容，提升提问效率
+    - 发现功能：随时浏览文章和热点内容，无需主动检索也能获取新知
+    - 搜索历史：所有查询本地保存，可随时回溯，研究成果永不丢失
+    - 更多功能持续推进中：我们根据社区反馈积极开发新功能，欢迎加入 Discord 影响 Vane 的未来！
+
+  upgradeDescription: |
+    升级应用版本至 1.12.0
+
+    这是一个重大版本更新，包含完整的架构重构。我们移除了 Langchain，采用自定义实现以获得对流式传输、生成和特定提供商功能的底层控制。
+
+    更新内容：
+
+    常规更新：
+    - 将提供商重命名为连接以改善用户体验
+    - 修复了 SearxNG 构建和启动错误
+    - 添加了新的 agents DIR，迁移了建议、视频和音频代理
+    - 添加了消息和块类型以提高类型安全性
+    - 添加了带语法高亮的代码块渲染
+    - 在设置中添加了版本号和 GitHub 链接
+    - 通过 Framer Motion 进行了各种 UI 改进和动画
+
+    Langchain 移除和自定义提供商系统：
+    - 移除了 Langchain 并实现了自定义基类和提供商类
+    - 实现了带部分流式传输的函数调用
+
+    新的会话管理器：
+    - 添加了带自动流重连的会话管理器
+    - 如果页面刷新或流断开，可以通过 ID 恢复会话
+
+    小部件：
+    - 添加了天气信息、股票市场数据和数学计算的小部件
+
+    查询分类和带操作的研究器：
+    - 现在每个查询在研究开始前都会被分类
+    - 研究器使用带工具调用的操作，用于网络搜索、抓取、特定网站搜索、讨论搜索、文件上传搜索等
+
+    深度研究模式（Beta）：
+    - 添加了质量搜索模式，LLM 迭代推理收集的数据
+    - 允许更深入地探索主题并准备详细报告
+
+    更新的研究模式：
+    - 平衡模式：现在强制 LLM 进行推理，但限制最大操作数以控制令牌使用
+    - 速度模式：无任何推理运行以获得快速响应
+
+    基于块和 JSON Patch 的流式传输：
+    - LLM 的每一步现在都被流式传输，以提供实时可见性
+
+    新的上传管理器和增强的文件搜索：
+    - 添加了支持 PDF、DOCX 和文本文件的上传管理器
+    - 使用 RRF（倒数排名融合）增强文件搜索以提高检索质量
+
+    重新设计的源系统：
+    - 移除了焦点模式，替换为 3 个源：网络、学术和讨论
+    - 源可以单独切换或一起使用
+
+    完整发布说明请参阅：https://github.com/ItzCrazyKns/Vane/releases/tag/v1.12.0

vane/owners

@@ -0,0 +1,9 @@
+owners:
+- 'LittleLollipop'
+- 'TShentu'
+- 'hysyeah'
+- 'pengpeng'
+- 'harveyff'
+- 'zdf-org'
+- 'ItzCrazyKns'
+- 'kaki-admin'