diff --git a/README.md b/README.md index cb30776..0e2fdb3 100644 --- a/README.md +++ b/README.md @@ -681,6 +681,18 @@ AI驱动的开源代码知识库与文档协作平台，支持多模型、多数 0.4.1 • [官网链接](https://next-ai-drawio.jiang.jp/) + + + + +Open-Notebook +
Open Notebook + + +📝 私有的、多模型的Google Notebook LM替代方案，支持多模态内容和AI播客生成 + +1.2.4 • [官网链接](https://www.open-notebook.ai/) + diff --git a/apps/open-notebook/1.2.4/data.yml b/apps/open-notebook/1.2.4/data.yml new file mode 100644 index 0000000..fed6d06 --- /dev/null +++ b/apps/open-notebook/1.2.4/data.yml @@ -0,0 +1,26 @@ +additionalProperties: + formFields: + - default: "8502" + envKey: PANEL_APP_PORT_HTTP + required: true + type: number + labelEn: Port + labelZh: 端口 + edit: true + rule: paramPort + - default: "5055" + envKey: PANEL_APP_PORT_API + required: true + type: number + labelEn: API Port + labelZh: API端口 + edit: true + rule: paramPort + - default: "8000" + envKey: PANEL_APP_PORT_DB + required: true + type: number + labelEn: Database Port + labelZh: 数据库端口 + edit: true + rule: paramPort diff --git a/apps/open-notebook/1.2.4/docker-compose.yml b/apps/open-notebook/1.2.4/docker-compose.yml new file mode 100644 index 0000000..c2aea5d --- /dev/null +++ b/apps/open-notebook/1.2.4/docker-compose.yml @@ -0,0 +1,38 @@ +services: + open_notebook: + image: lfnovo/open_notebook:1.2.4 + ports: + - ${PANEL_APP_PORT_HTTP}:8502 + - ${PANEL_APP_PORT_API}:5055 + env_file: + - ./docker.env + depends_on: + - surrealdb + volumes: + - ./notebook_data:/app/data + restart: always + container_name: ${CONTAINER_NAME} + networks: + - 1panel-network + labels: + createdBy: Apps + surrealdb: + image: surrealdb/surrealdb:v2 + volumes: + - ./surreal_data:/mydata + environment: + - SURREAL_EXPERIMENTAL_GRAPHQL=true + ports: + - ${PANEL_APP_PORT_DB}:8000 + command: start --log info --user root --pass root rocksdb:/mydata/mydatabase.db + pull_policy: always + user: root + restart: always + container_name: ${CONTAINER_NAME}-surrealdb + networks: + - 1panel-network + labels: + createdBy: Apps +networks: + 1panel-network: + external: true diff --git a/apps/open-notebook/1.2.4/docker.env b/apps/open-notebook/1.2.4/docker.env new file mode 100644 index 0000000..6f1d1da --- /dev/null +++ b/apps/open-notebook/1.2.4/docker.env @@ -0,0 +1,259 @@ + +# API CONFIGURATION +# URL where the API can be accessed by the browser +# This setting allows the frontend to connect to the API at runtime (no rebuild needed!) +# +# IMPORTANT: Do NOT include /api at the end - it will be added automatically! +# +# Common scenarios: +# - Docker on localhost: http://localhost:5055 (default, works for most cases) +# - Docker on LAN/remote server: http://192.168.1.100:5055 or http://your-server-ip:5055 +# - Behind reverse proxy with custom domain: https://your-domain.com +# - Behind reverse proxy with subdomain: https://api.your-domain.com +# +# Examples for reverse proxy users: +# - API_URL=https://notebook.example.com (frontend will call https://notebook.example.com/api/*) +# - API_URL=https://api.example.com (frontend will call https://api.example.com/api/*) +# +# Note: If not set, the system will auto-detect based on the incoming request. +# Only set this if you need to override the auto-detection (e.g., reverse proxy scenarios). +API_URL=http://localhost:5055 + +# INTERNAL API URL (Server-Side) +# URL where Next.js server-side should proxy API requests (via rewrites) +# This is DIFFERENT from API_URL which is used by the browser client +# +# INTERNAL_API_URL is used by Next.js rewrites to forward /api/* requests to the FastAPI backend +# API_URL is used by the browser to know where to make API calls +# +# Default: http://localhost:5055 (single-container deployment - both services on same host) +# Override for multi-container: INTERNAL_API_URL=http://api-service:5055 +# +# Common scenarios: +# - Single container (default): Don't set - defaults to http://localhost:5055 +# - Multi-container Docker Compose: INTERNAL_API_URL=http://api:5055 (use service name) +# - Kubernetes/advanced networking: INTERNAL_API_URL=http://api-service.namespace.svc.cluster.local:5055 +# +# Why two variables? +# - API_URL: External/public URL that browsers use (can be https://your-domain.com) +# - INTERNAL_API_URL: Internal container networking URL (usually http://localhost:5055 or service name) +# +# INTERNAL_API_URL=http://localhost:5055 + +# API CLIENT TIMEOUT (in seconds) +# Controls how long the frontend/Streamlit UI waits for API responses +# Increase this if you're using slow AI providers or hardware (Ollama on CPU, remote LM Studio, etc.) +# Default: 300 seconds (5 minutes) - sufficient for most transformation/insight operations +# +# Common scenarios: +# - Fast cloud APIs (OpenAI, Anthropic): 300 seconds is more than enough +# - Local Ollama on GPU: 300 seconds should work fine +# - Local Ollama on CPU: Consider 600 seconds (10 minutes) or more +# - Remote LM Studio over slow network: Consider 900 seconds (15 minutes) +# - Very large documents: May need 900+ seconds +# +# API_CLIENT_TIMEOUT=300 + +# ESPERANTO LLM TIMEOUT (in seconds) +# Controls the timeout for AI model API calls at the Esperanto library level +# This is separate from API_CLIENT_TIMEOUT and applies to the actual LLM provider requests +# Only increase this if you're experiencing timeouts during model inference itself +# Default: 60 seconds (built into Esperanto) +# +# Important: This should generally be LOWER than API_CLIENT_TIMEOUT to allow proper error handling +# +# Common scenarios: +# - Fast cloud APIs (OpenAI, Anthropic, Groq): 60 seconds is sufficient +# - Local Ollama with small models: 120-180 seconds may help +# - Local Ollama with large models on CPU: 300+ seconds +# - Remote or self-hosted LLMs: 180-300 seconds depending on hardware +# +# Note: If transformations complete but you see timeout errors, increase API_CLIENT_TIMEOUT first. +# Only increase ESPERANTO_LLM_TIMEOUT if the model itself is timing out during inference. +# +# ESPERANTO_LLM_TIMEOUT=60 + +# SSL VERIFICATION CONFIGURATION +# Configure SSL certificate verification for local AI providers (Ollama, LM Studio, etc.) +# behind reverse proxies with self-signed certificates +# +# Option 1: Custom CA Bundle (recommended for self-signed certs) +# Point to your CA certificate file to verify SSL while using custom certificates +# ESPERANTO_SSL_CA_BUNDLE=/path/to/your/ca-bundle.pem +# +# Option 2: Disable SSL Verification (development only) +# WARNING: Disabling SSL verification exposes you to man-in-the-middle attacks +# Only use in trusted development/testing environments +# ESPERANTO_SSL_VERIFY=false + +# SECURITY +# Set this to protect your Open Notebook instance with a password (for public hosting) +# OPEN_NOTEBOOK_PASSWORD= + +# OPENAI +# OPENAI_API_KEY= + + +# ANTHROPIC +# ANTHROPIC_API_KEY= + +# GEMINI +# this is the best model for long context and podcast generation +# GOOGLE_API_KEY= +# GEMINI_API_BASE_URL= # Optional: Override default endpoint (for Vertex AI, proxies, etc.) + +# VERTEXAI +# VERTEX_PROJECT=my-google-cloud-project-name +# GOOGLE_APPLICATION_CREDENTIALS=./google-credentials.json +# VERTEX_LOCATION=us-east5 + +# MISTRAL +# MISTRAL_API_KEY= + +# DEEPSEEK +# DEEPSEEK_API_KEY= + +# OLLAMA +# OLLAMA_API_BASE="http://10.20.30.20:11434" + +# OPEN ROUTER +# OPENROUTER_BASE_URL="https://openrouter.ai/api/v1" +# OPENROUTER_API_KEY= + +# GROQ +# GROQ_API_KEY= + +# XAI +# XAI_API_KEY= + +# ELEVENLABS +# Used only by the podcast feature +# ELEVENLABS_API_KEY= + +# TTS BATCH SIZE +# Controls concurrent TTS requests for podcast generation (default: 5) +# Lower values reduce provider load but increase generation time +# Recommended: OpenAI=5, ElevenLabs=2, Google=4, Custom=1 +# TTS_BATCH_SIZE=2 + +# VOYAGE AI +# VOYAGE_API_KEY= + +# OPENAI COMPATIBLE ENDPOINTS +# Generic configuration (applies to all modalities: language, embedding, STT, TTS) +# OPENAI_COMPATIBLE_BASE_URL=http://localhost:1234/v1 +# OPENAI_COMPATIBLE_API_KEY= + +# Mode-specific configuration (overrides generic if set) +# Use these when you want different endpoints for different capabilities +# OPENAI_COMPATIBLE_BASE_URL_LLM=http://localhost:1234/v1 +# OPENAI_COMPATIBLE_API_KEY_LLM= +# OPENAI_COMPATIBLE_BASE_URL_EMBEDDING=http://localhost:8080/v1 +# OPENAI_COMPATIBLE_API_KEY_EMBEDDING= +# OPENAI_COMPATIBLE_BASE_URL_STT=http://localhost:9000/v1 +# OPENAI_COMPATIBLE_API_KEY_STT= +# OPENAI_COMPATIBLE_BASE_URL_TTS=http://localhost:9000/v1 +# OPENAI_COMPATIBLE_API_KEY_TTS= + +# AZURE OPENAI +# Generic configuration (applies to all modalities: language, embedding, STT, TTS) +# AZURE_OPENAI_API_KEY= +# AZURE_OPENAI_ENDPOINT= +# AZURE_OPENAI_API_VERSION=2024-12-01-preview + +# Mode-specific configuration (overrides generic if set) +# Use these when you want different deployments for different AI capabilities +# AZURE_OPENAI_API_KEY_LLM= +# AZURE_OPENAI_ENDPOINT_LLM= +# AZURE_OPENAI_API_VERSION_LLM= + +# AZURE_OPENAI_API_KEY_EMBEDDING= +# AZURE_OPENAI_ENDPOINT_EMBEDDING= +# AZURE_OPENAI_API_VERSION_EMBEDDING= + +# AZURE_OPENAI_API_KEY_STT= +# AZURE_OPENAI_ENDPOINT_STT= +# AZURE_OPENAI_API_VERSION_STT= + +# AZURE_OPENAI_API_KEY_TTS= +# AZURE_OPENAI_ENDPOINT_TTS= +# AZURE_OPENAI_API_VERSION_TTS= + +# USE THIS IF YOU WANT TO DEBUG THE APP ON LANGSMITH +# LANGCHAIN_TRACING_V2=true +# LANGCHAIN_ENDPOINT="https://api.smith.langchain.com" +# LANGCHAIN_API_KEY= +# LANGCHAIN_PROJECT="Open Notebook" + +# CONNECTION DETAILS FOR YOUR SURREAL DB +# New format (preferred) - WebSocket URL +SURREAL_URL="ws://surrealdb/rpc:8000" +SURREAL_USER="root" +SURREAL_PASSWORD="root" +SURREAL_NAMESPACE="open_notebook" +SURREAL_DATABASE="staging" + +# RETRY CONFIGURATION (surreal-commands v1.2.0+) +# Global defaults for all background commands unless explicitly overridden at command level +# These settings help commands automatically recover from transient failures like: +# - Database transaction conflicts during concurrent operations +# - Network timeouts when calling external APIs +# - Rate limits from LLM/embedding providers +# - Temporary resource unavailability + +# Enable/disable retry globally (default: true) +# Set to false to disable retries for all commands (useful for debugging) +SURREAL_COMMANDS_RETRY_ENABLED=true + +# Maximum retry attempts before giving up (default: 3) +# Database operations use 5 attempts (defined per-command) +# API calls use 3 attempts (defined per-command) +SURREAL_COMMANDS_RETRY_MAX_ATTEMPTS=3 + +# Wait strategy between retry attempts (default: exponential_jitter) +# Options: exponential_jitter, exponential, fixed, random +# - exponential_jitter: Recommended - prevents thundering herd during DB conflicts +# - exponential: Good for API rate limits (predictable backoff) +# - fixed: Use for quick recovery scenarios +# - random: Use when you want unpredictable retry timing +SURREAL_COMMANDS_RETRY_WAIT_STRATEGY=exponential_jitter + +# Minimum wait time between retries in seconds (default: 1) +# Database conflicts: 1 second (fast retry for transient issues) +# API rate limits: 5 seconds (wait for quota reset) +SURREAL_COMMANDS_RETRY_WAIT_MIN=1 + +# Maximum wait time between retries in seconds (default: 30) +# Database conflicts: 30 seconds maximum +# API rate limits: 120 seconds maximum (defined per-command) +# Total retry time won't exceed max_attempts * wait_max +SURREAL_COMMANDS_RETRY_WAIT_MAX=30 + +# WORKER CONCURRENCY +# Maximum number of concurrent tasks in the worker pool (default: 5) +# This affects the likelihood of database transaction conflicts during batch operations +# +# Tuning guidelines based on deployment size: +# - Resource-constrained (low CPU/memory): 1-2 workers +# Reduces conflicts and resource usage, but slower processing +# +# - Normal deployment (balanced): 5 workers (RECOMMENDED) +# Good balance between throughput and conflict rate +# Retry logic handles occasional conflicts gracefully +# +# - Large instances (high CPU/memory): 10-20 workers +# Higher throughput but more frequent DB conflicts +# Relies heavily on retry logic with jittered backoff +# +# Note: Higher concurrency increases vectorization speed but also increases +# SurrealDB transaction conflicts. The retry logic with exponential-jitter +# backoff ensures operations complete successfully even at high concurrency. +SURREAL_COMMANDS_MAX_TASKS=5 + +# OPEN_NOTEBOOK_PASSWORD= + +# FIRECRAWL - Get a key at https://firecrawl.dev/ +FIRECRAWL_API_KEY= + +# JINA - Get a key at https://jina.ai/ +JINA_API_KEY= \ No newline at end of file diff --git a/apps/open-notebook/README.md b/apps/open-notebook/README.md new file mode 100644 index 0000000..b0b065a --- /dev/null +++ b/apps/open-notebook/README.md @@ -0,0 +1,124 @@ +# Open Notebook + +一个私有的、多模型的、100% 本地的、功能完整的 Google Notebook LM 替代方案 + +在人工智能主导的世界中，拥有思考🧠和获取新知识💡的能力，不应该成为少数人的特权，也不应该被限制在单一提供商。 + +![](https://img.shields.io/badge/Copyright-arch3rPro-ff9800?style=flat&logo=github&logoColor=white) + +![](https://cdn.jsdelivr.net/gh/xiaoY233/PicList@main/public/assets/open-notebook.png) + +**Open Notebook 赋能您：** +- 🔒 **控制您的数据** - 保持您的研究私密和安全 +- 🤖 **选择您的AI模型** - 支持16+个提供商，包括OpenAI、Anthropic、Ollama、LM Studio等 +- 📚 **组织多模态内容** - PDF、视频、音频、网页等 +- 🎙️ **生成专业播客** - 高级多说话人播客生成 +- 🔍 **智能搜索** - 对所有内容进行全文和向量搜索 +- 💬 **上下文聊天** - AI对话由您的研究驱动 + +在 [https://www.open-notebook.ai](https://www.open-notebook.ai) 了解我们项目的更多信息 + +## 🆚 Open Notebook vs Google Notebook LM + +| 功能 | Open Notebook | Google Notebook LM | 优势 | +|---------|---------------|--------------------|-----------| +| **隐私和控制** | 自托管，您的数据 | 仅限谷歌云 | 完全的数据主权 | +| **AI提供商选择** | 16+提供商（OpenAI、Anthropic、Ollama、LM Studio等） | 仅谷歌模型 | 灵活性和成本优化 | +| **播客说话人** | 1-4个说话人，支持自定义配置 | 仅2个说话人 | 极致的灵活性 | +| **上下文控制** | 3个细粒度级别 | 全有或全无 | 隐私和性能调优 | +| **内容转换** | 自定义和内置 | 有限选项 | 无限的处理能力 | +| **API访问** | 完整REST API | 无API | 完整自动化 | +| **部署** | Docker、云端或本地 | 仅谷歌托管 | 随处部署 | +| **引用** | 带源的完整引用 | 基本引用 | 研究完整性 | +| **定制** | 开源，完全可定制 | 封闭系统 | 无限扩展性 | +| **成本** | 仅支付AI使用费 | 每月订阅+使用量 | 透明可控 | + +**为什么选择Open Notebook？** +- 🔒 **隐私优先**: 您的敏感研究保持完全私密 +- 💰 **成本控制**: 选择更便宜的AI提供商或使用Ollama本地运行 +- 🎙️ **更好的播客**: 完整脚本控制和多说话人灵活性，优于有限的2说话人深度分析格式 +- 🔧 **无限定制**: 根据需要修改、扩展和集成 +- 🌐 **无供应商锁定**: 切换提供商、随处部署、拥有您的数据 + +### Open Notebook 工作原理 + +``` +┌─────────────────────────────────────────────────────────┐ +│ 您的浏览器 │ +│ 访问地址: http://您的服务器IP:8502 │ +└────────────────┬────────────────────────────────────────┘ + │ + ▼ + ┌───────────────┐ + │ 端口 8502 │ ← Next.js 前端（您看到的界面） + │ 前端 │ 同时在内部代理API请求！ + └───────┬───────┘ + │ 代理 /api/* 请求 ↓ + ▼ + ┌───────────────┐ + │ 端口 5055 │ ← FastAPI 后端（处理请求） + │ API │ + └───────┬───────┘ + │ + ▼ + ┌───────────────┐ + │ SurrealDB │ ← 数据库（内部，自动配置） + │ (端口 8000) │ + └───────────────┘ +``` + +**关键要点:** +- **v1.1+**: Next.js自动代理 `/api/*` 请求到后端，简化反向代理设置 +- 您的浏览器从端口8502加载前端 +- 前端需要知道在哪里找到API - 远程访问时，设置：`API_URL=http://您的服务器IP:5055` +- **使用反向代理？** 现在您只需要代理到端口8502！请参阅[反向代理指南](docs/deployment/reverse-proxy.md) + +## 提供商支持矩阵 + +感谢 [Esperanto](https://github.com/lfnovo/esperanto) 库，我们开箱即用地支持这些提供商！ + +| 提供商 | LLM支持 | 嵌入支持 | 语音转文本 | 文本转语音 | +|--------------|-------------|------------------|----------------|----------------| +| OpenAI | ✅ | ✅ | ✅ | ✅ | +| Anthropic | ✅ | ❌ | ❌ | ❌ | +| Groq | ✅ | ❌ | ✅ | ❌ | +| Google (GenAI) | ✅ | ✅ | ❌ | ✅ | +| Vertex AI | ✅ | ✅ | ❌ | ✅ | +| Ollama | ✅ | ✅ | ❌ | ❌ | +| Perplexity | ✅ | ❌ | ❌ | ❌ | +| ElevenLabs | ❌ | ❌ | ✅ | ✅ | +| Azure OpenAI | ✅ | ✅ | ❌ | ❌ | +| Mistral | ✅ | ✅ | ❌ | ❌ | +| DeepSeek | ✅ | ❌ | ❌ | ❌ | +| Voyage | ❌ | ✅ | ❌ | ❌ | +| xAI | ✅ | ❌ | ❌ | ❌ | +| OpenRouter | ✅ | ❌ | ❌ | ❌ | +| OpenAI 兼容* | ✅ | ❌ | ❌ | ❌ | + +*支持LM Studio和任何OpenAI兼容端点 + +## ✨ 主要功能 + +### 核心能力 +- **🔒 隐私优先**: 您的数据保持在您的控制下 - 无云依赖 +- **🎯 多笔记本组织**: 无缝管理多个研究项目 +- **📚 通用内容支持**: PDF、视频、音频、网页、Office文档等 +- **🤖 多模型AI支持**: 16+提供商，包括OpenAI、Anthropic、Ollama、Google、LM Studio等 +- **🎙️ 专业播客生成**: 带有剧集配置的高级多说话人播客 +- **🔍 智能搜索**: 对所有内容进行全文和向量搜索 +- **💬 上下文感知聊天**: AI对话由您的研究材料驱动 +- **📝 AI辅助笔记**: 生成洞察或手动写笔记 + +### 高级功能 +- **⚡ 推理模型支持**: 对DeepSeek-R1和Qwen3等思考模型的完整支持 +- **🔧 内容转换**: 强大的可自定义操作，用于总结和提取洞察 +- **🌐 完整REST API**: 自定义集成的完整程序化访问 [![API文档](https://img.shields.io/badge/API-文档-blue?style=flat-square)](http://localhost:5055/docs) +- **🔐 可选密码保护**: 通过身份验证保护公共部署 +- **📊 细粒度上下文控制**: 选择与AI模型分享的确切内容 +- **📎 引用**: 获取带有正确源引用的答案 + +### 三栏界面 +1. **源**: 管理所有研究材料 +2. **笔记**: 创建手动或AI生成的笔记 +3. **聊天**: 使用您的内容作为上下文与AI对话 + diff --git a/apps/open-notebook/README_en.md b/apps/open-notebook/README_en.md new file mode 100644 index 0000000..5b8f7a3 --- /dev/null +++ b/apps/open-notebook/README_en.md @@ -0,0 +1,129 @@ +# Open Notebook + +A private, multi-model, 100% local, full-featured alternative to Notebook LM + +In a world dominated by Artificial Intelligence, having the ability to think 🧠 and acquire new knowledge 💡, is a skill that should not be a privilege for a few, nor restricted to a single provider. + +![](https://img.shields.io/badge/Copyright-arch3rPro-ff9800?style=flat&logo=github&logoColor=white) + +![](https://cdn.jsdelivr.net/gh/xiaoY233/PicList@main/public/assets/open-notebook.png) + +**Open Notebook empowers you to:** +- 🔒 **Control your data** - Keep your research private and secure +- 🤖 **Choose your AI models** - Support for 16+ providers including OpenAI, Anthropic, Ollama, LM Studio, and more +- 📚 **Organize multi-modal content** - PDFs, videos, audio, web pages, and more +- 🎙️ **Generate professional podcasts** - Advanced multi-speaker podcast generation +- 🔍 **Search intelligently** - Full-text and vector search across all your content +- 💬 **Chat with context** - AI conversations powered by your research + +Learn more about our project at [https://www.open-notebook.ai](https://www.open-notebook.ai) + +## 🆚 Open Notebook vs Google Notebook LM + +| Feature | Open Notebook | Google Notebook LM | Advantage | +|---------|---------------|--------------------|-----------| +| **Privacy & Control** | Self-hosted, your data | Google cloud only | Complete data sovereignty | +| **AI Provider Choice** | 16+ providers (OpenAI, Anthropic, Ollama, LM Studio, etc.) | Google models only | Flexibility and cost optimization | +| **Podcast Speakers** | 1-4 speakers with custom profiles | 2 speakers only | Extreme flexibility | +| **Context Control** | 3 granular levels | All-or-nothing | Privacy and performance tuning | +| **Content Transformations** | Custom and built-in | Limited options | Unlimited processing power | +| **API Access** | Full REST API | No API | Complete automation | +| **Deployment** | Docker, cloud, or local | Google hosted only | Deploy anywhere | +| **Citations** | Comprehensive with sources | Basic references | Research integrity | +| **Customization** | Open source, fully customizable | Closed system | Unlimited extensibility | +| **Cost** | Pay only for AI usage | Monthly subscription + usage | Transparent and controllable | + +**Why Choose Open Notebook?** +- 🔒 **Privacy First**: Your sensitive research stays completely private +- 💰 **Cost Control**: Choose cheaper AI providers or run locally with Ollama +- 🎙️ **Better Podcasts**: Full script control and multi-speaker flexibility vs limited 2-speaker deep-dive format +- 🔧 **Unlimited Customization**: Modify, extend, and integrate as needed +- 🌐 **No Vendor Lock-in**: Switch providers, deploy anywhere, own your data + + +### How Open Notebook Works + +``` +┌─────────────────────────────────────────────────────────┐ +│ Your Browser │ +│ Access: http://your-server-ip:8502 │ +└────────────────┬────────────────────────────────────────┘ + │ + ▼ + ┌───────────────┐ + │ Port 8502 │ ← Next.js Frontend (what you see) + │ Frontend │ Also proxies API requests internally! + └───────┬───────┘ + │ proxies /api/* requests ↓ + ▼ + ┌───────────────┐ + │ Port 5055 │ ← FastAPI Backend (handles requests) + │ API │ + └───────┬───────┘ + │ + ▼ + ┌───────────────┐ + │ SurrealDB │ ← Database (internal, auto-configured) + │ (Port 8000) │ + └───────────────┘ +``` + +**Key Points:** +- **v1.1+**: Next.js automatically proxies `/api/*` requests to the backend, simplifying reverse proxy setup +- Your browser loads the frontend from port 8502 +- The frontend needs to know where to find the API - when accessing remotely, set: `API_URL=http://your-server-ip:5055` +- **Behind reverse proxy?** You only need to proxy to port 8502 now! See [Reverse Proxy Guide](docs/deployment/reverse-proxy.md) + +## Provider Support Matrix + +Thanks to the [Esperanto](https://github.com/lfnovo/esperanto) library, we support this providers out of the box! + +| Provider | LLM Support | Embedding Support | Speech-to-Text | Text-to-Speech | +|--------------|-------------|------------------|----------------|----------------| +| OpenAI | ✅ | ✅ | ✅ | ✅ | +| Anthropic | ✅ | ❌ | ❌ | ❌ | +| Groq | ✅ | ❌ | ✅ | ❌ | +| Google (GenAI) | ✅ | ✅ | ❌ | ✅ | +| Vertex AI | ✅ | ✅ | ❌ | ✅ | +| Ollama | ✅ | ✅ | ❌ | ❌ | +| Perplexity | ✅ | ❌ | ❌ | ❌ | +| ElevenLabs | ❌ | ❌ | ✅ | ✅ | +| Azure OpenAI | ✅ | ✅ | ❌ | ❌ | +| Mistral | ✅ | ✅ | ❌ | ❌ | +| DeepSeek | ✅ | ❌ | ❌ | ❌ | +| Voyage | ❌ | ✅ | ❌ | ❌ | +| xAI | ✅ | ❌ | ❌ | ❌ | +| OpenRouter | ✅ | ❌ | ❌ | ❌ | +| OpenAI Compatible* | ✅ | ❌ | ❌ | ❌ | + +*Supports LM Studio and any OpenAI-compatible endpoint + +## ✨ Key Features + +### Core Capabilities +- **🔒 Privacy-First**: Your data stays under your control - no cloud dependencies +- **🎯 Multi-Notebook Organization**: Manage multiple research projects seamlessly +- **📚 Universal Content Support**: PDFs, videos, audio, web pages, Office docs, and more +- **🤖 Multi-Model AI Support**: 16+ providers including OpenAI, Anthropic, Ollama, Google, LM Studio, and more +- **🎙️ Professional Podcast Generation**: Advanced multi-speaker podcasts with Episode Profiles +- **🔍 Intelligent Search**: Full-text and vector search across all your content +- **💬 Context-Aware Chat**: AI conversations powered by your research materials +- **📝 AI-Assisted Notes**: Generate insights or write notes manually + +### Advanced Features +- **⚡ Reasoning Model Support**: Full support for thinking models like DeepSeek-R1 and Qwen3 +- **🔧 Content Transformations**: Powerful customizable actions to summarize and extract insights +- **🌐 Comprehensive REST API**: Full programmatic access for custom integrations [![API Docs](https://img.shields.io/badge/API-Documentation-blue?style=flat-square)](http://localhost:5055/docs) +- **🔐 Optional Password Protection**: Secure public deployments with authentication +- **📊 Fine-Grained Context Control**: Choose exactly what to share with AI models +- **📎 Citations**: Get answers with proper source citations + +### Three-Column Interface +1. **Sources**: Manage all your research materials +2. **Notes**: Create manual or AI-generated notes +3. **Chat**: Converse with AI using your content as context + + + + + diff --git a/apps/open-notebook/data.yml b/apps/open-notebook/data.yml new file mode 100644 index 0000000..50526e9 --- /dev/null +++ b/apps/open-notebook/data.yml @@ -0,0 +1,26 @@ +name: Open Notebook +tags: + - 实用工具 + - Web 服务器 +title: 一个开源的、注重隐私的 Google Notebook LM 替代方案！ +description: + en: An open source, privacy-focused alternative to Google's Notebook LM! + zh: 一个开源的、注重隐私的 Google Notebook LM 替代方案！ +additionalProperties: + key: open-notebook + name: Open Notebook + tags: + - Tool + - Server + shortDescZh: 一个开源的、注重隐私的 Google Notebook LM 替代方案！ + shortDescEn: An open source, privacy-focused alternative to Google's Notebook LM! + type: website + crossVersionUpdate: true + limit: 0 + website: https://www.open-notebook.ai + github: https://github.com/lfnovo/open-notebook + document: https://www.open-notebook.ai/get-started.html + memoryRequired: 2048 + architectures: + - amd64 + - arm64 diff --git a/apps/open-notebook/latest/data.yml b/apps/open-notebook/latest/data.yml new file mode 100644 index 0000000..fed6d06 --- /dev/null +++ b/apps/open-notebook/latest/data.yml @@ -0,0 +1,26 @@ +additionalProperties: + formFields: + - default: "8502" + envKey: PANEL_APP_PORT_HTTP + required: true + type: number + labelEn: Port + labelZh: 端口 + edit: true + rule: paramPort + - default: "5055" + envKey: PANEL_APP_PORT_API + required: true + type: number + labelEn: API Port + labelZh: API端口 + edit: true + rule: paramPort + - default: "8000" + envKey: PANEL_APP_PORT_DB + required: true + type: number + labelEn: Database Port + labelZh: 数据库端口 + edit: true + rule: paramPort diff --git a/apps/open-notebook/latest/docker-compose.yml b/apps/open-notebook/latest/docker-compose.yml new file mode 100644 index 0000000..62c75ef --- /dev/null +++ b/apps/open-notebook/latest/docker-compose.yml @@ -0,0 +1,38 @@ +services: + open_notebook: + image: lfnovo/open_notebook:v1-latest + ports: + - ${PANEL_APP_PORT_HTTP}:8502 + - ${PANEL_APP_PORT_API}:5055 + env_file: + - ./docker.env + depends_on: + - surrealdb + volumes: + - ./notebook_data:/app/data + restart: always + container_name: ${CONTAINER_NAME} + networks: + - 1panel-network + labels: + createdBy: Apps + surrealdb: + image: surrealdb/surrealdb:v2 + volumes: + - ./surreal_data:/mydata + environment: + - SURREAL_EXPERIMENTAL_GRAPHQL=true + ports: + - ${PANEL_APP_PORT_DB}:8000 + command: start --log info --user root --pass root rocksdb:/mydata/mydatabase.db + pull_policy: always + user: root + restart: always + container_name: ${CONTAINER_NAME}-surrealdb + networks: + - 1panel-network + labels: + createdBy: Apps +networks: + 1panel-network: + external: true diff --git a/apps/open-notebook/latest/docker.env b/apps/open-notebook/latest/docker.env new file mode 100644 index 0000000..6f1d1da --- /dev/null +++ b/apps/open-notebook/latest/docker.env @@ -0,0 +1,259 @@ + +# API CONFIGURATION +# URL where the API can be accessed by the browser +# This setting allows the frontend to connect to the API at runtime (no rebuild needed!) +# +# IMPORTANT: Do NOT include /api at the end - it will be added automatically! +# +# Common scenarios: +# - Docker on localhost: http://localhost:5055 (default, works for most cases) +# - Docker on LAN/remote server: http://192.168.1.100:5055 or http://your-server-ip:5055 +# - Behind reverse proxy with custom domain: https://your-domain.com +# - Behind reverse proxy with subdomain: https://api.your-domain.com +# +# Examples for reverse proxy users: +# - API_URL=https://notebook.example.com (frontend will call https://notebook.example.com/api/*) +# - API_URL=https://api.example.com (frontend will call https://api.example.com/api/*) +# +# Note: If not set, the system will auto-detect based on the incoming request. +# Only set this if you need to override the auto-detection (e.g., reverse proxy scenarios). +API_URL=http://localhost:5055 + +# INTERNAL API URL (Server-Side) +# URL where Next.js server-side should proxy API requests (via rewrites) +# This is DIFFERENT from API_URL which is used by the browser client +# +# INTERNAL_API_URL is used by Next.js rewrites to forward /api/* requests to the FastAPI backend +# API_URL is used by the browser to know where to make API calls +# +# Default: http://localhost:5055 (single-container deployment - both services on same host) +# Override for multi-container: INTERNAL_API_URL=http://api-service:5055 +# +# Common scenarios: +# - Single container (default): Don't set - defaults to http://localhost:5055 +# - Multi-container Docker Compose: INTERNAL_API_URL=http://api:5055 (use service name) +# - Kubernetes/advanced networking: INTERNAL_API_URL=http://api-service.namespace.svc.cluster.local:5055 +# +# Why two variables? +# - API_URL: External/public URL that browsers use (can be https://your-domain.com) +# - INTERNAL_API_URL: Internal container networking URL (usually http://localhost:5055 or service name) +# +# INTERNAL_API_URL=http://localhost:5055 + +# API CLIENT TIMEOUT (in seconds) +# Controls how long the frontend/Streamlit UI waits for API responses +# Increase this if you're using slow AI providers or hardware (Ollama on CPU, remote LM Studio, etc.) +# Default: 300 seconds (5 minutes) - sufficient for most transformation/insight operations +# +# Common scenarios: +# - Fast cloud APIs (OpenAI, Anthropic): 300 seconds is more than enough +# - Local Ollama on GPU: 300 seconds should work fine +# - Local Ollama on CPU: Consider 600 seconds (10 minutes) or more +# - Remote LM Studio over slow network: Consider 900 seconds (15 minutes) +# - Very large documents: May need 900+ seconds +# +# API_CLIENT_TIMEOUT=300 + +# ESPERANTO LLM TIMEOUT (in seconds) +# Controls the timeout for AI model API calls at the Esperanto library level +# This is separate from API_CLIENT_TIMEOUT and applies to the actual LLM provider requests +# Only increase this if you're experiencing timeouts during model inference itself +# Default: 60 seconds (built into Esperanto) +# +# Important: This should generally be LOWER than API_CLIENT_TIMEOUT to allow proper error handling +# +# Common scenarios: +# - Fast cloud APIs (OpenAI, Anthropic, Groq): 60 seconds is sufficient +# - Local Ollama with small models: 120-180 seconds may help +# - Local Ollama with large models on CPU: 300+ seconds +# - Remote or self-hosted LLMs: 180-300 seconds depending on hardware +# +# Note: If transformations complete but you see timeout errors, increase API_CLIENT_TIMEOUT first. +# Only increase ESPERANTO_LLM_TIMEOUT if the model itself is timing out during inference. +# +# ESPERANTO_LLM_TIMEOUT=60 + +# SSL VERIFICATION CONFIGURATION +# Configure SSL certificate verification for local AI providers (Ollama, LM Studio, etc.) +# behind reverse proxies with self-signed certificates +# +# Option 1: Custom CA Bundle (recommended for self-signed certs) +# Point to your CA certificate file to verify SSL while using custom certificates +# ESPERANTO_SSL_CA_BUNDLE=/path/to/your/ca-bundle.pem +# +# Option 2: Disable SSL Verification (development only) +# WARNING: Disabling SSL verification exposes you to man-in-the-middle attacks +# Only use in trusted development/testing environments +# ESPERANTO_SSL_VERIFY=false + +# SECURITY +# Set this to protect your Open Notebook instance with a password (for public hosting) +# OPEN_NOTEBOOK_PASSWORD= + +# OPENAI +# OPENAI_API_KEY= + + +# ANTHROPIC +# ANTHROPIC_API_KEY= + +# GEMINI +# this is the best model for long context and podcast generation +# GOOGLE_API_KEY= +# GEMINI_API_BASE_URL= # Optional: Override default endpoint (for Vertex AI, proxies, etc.) + +# VERTEXAI +# VERTEX_PROJECT=my-google-cloud-project-name +# GOOGLE_APPLICATION_CREDENTIALS=./google-credentials.json +# VERTEX_LOCATION=us-east5 + +# MISTRAL +# MISTRAL_API_KEY= + +# DEEPSEEK +# DEEPSEEK_API_KEY= + +# OLLAMA +# OLLAMA_API_BASE="http://10.20.30.20:11434" + +# OPEN ROUTER +# OPENROUTER_BASE_URL="https://openrouter.ai/api/v1" +# OPENROUTER_API_KEY= + +# GROQ +# GROQ_API_KEY= + +# XAI +# XAI_API_KEY= + +# ELEVENLABS +# Used only by the podcast feature +# ELEVENLABS_API_KEY= + +# TTS BATCH SIZE +# Controls concurrent TTS requests for podcast generation (default: 5) +# Lower values reduce provider load but increase generation time +# Recommended: OpenAI=5, ElevenLabs=2, Google=4, Custom=1 +# TTS_BATCH_SIZE=2 + +# VOYAGE AI +# VOYAGE_API_KEY= + +# OPENAI COMPATIBLE ENDPOINTS +# Generic configuration (applies to all modalities: language, embedding, STT, TTS) +# OPENAI_COMPATIBLE_BASE_URL=http://localhost:1234/v1 +# OPENAI_COMPATIBLE_API_KEY= + +# Mode-specific configuration (overrides generic if set) +# Use these when you want different endpoints for different capabilities +# OPENAI_COMPATIBLE_BASE_URL_LLM=http://localhost:1234/v1 +# OPENAI_COMPATIBLE_API_KEY_LLM= +# OPENAI_COMPATIBLE_BASE_URL_EMBEDDING=http://localhost:8080/v1 +# OPENAI_COMPATIBLE_API_KEY_EMBEDDING= +# OPENAI_COMPATIBLE_BASE_URL_STT=http://localhost:9000/v1 +# OPENAI_COMPATIBLE_API_KEY_STT= +# OPENAI_COMPATIBLE_BASE_URL_TTS=http://localhost:9000/v1 +# OPENAI_COMPATIBLE_API_KEY_TTS= + +# AZURE OPENAI +# Generic configuration (applies to all modalities: language, embedding, STT, TTS) +# AZURE_OPENAI_API_KEY= +# AZURE_OPENAI_ENDPOINT= +# AZURE_OPENAI_API_VERSION=2024-12-01-preview + +# Mode-specific configuration (overrides generic if set) +# Use these when you want different deployments for different AI capabilities +# AZURE_OPENAI_API_KEY_LLM= +# AZURE_OPENAI_ENDPOINT_LLM= +# AZURE_OPENAI_API_VERSION_LLM= + +# AZURE_OPENAI_API_KEY_EMBEDDING= +# AZURE_OPENAI_ENDPOINT_EMBEDDING= +# AZURE_OPENAI_API_VERSION_EMBEDDING= + +# AZURE_OPENAI_API_KEY_STT= +# AZURE_OPENAI_ENDPOINT_STT= +# AZURE_OPENAI_API_VERSION_STT= + +# AZURE_OPENAI_API_KEY_TTS= +# AZURE_OPENAI_ENDPOINT_TTS= +# AZURE_OPENAI_API_VERSION_TTS= + +# USE THIS IF YOU WANT TO DEBUG THE APP ON LANGSMITH +# LANGCHAIN_TRACING_V2=true +# LANGCHAIN_ENDPOINT="https://api.smith.langchain.com" +# LANGCHAIN_API_KEY= +# LANGCHAIN_PROJECT="Open Notebook" + +# CONNECTION DETAILS FOR YOUR SURREAL DB +# New format (preferred) - WebSocket URL +SURREAL_URL="ws://surrealdb/rpc:8000" +SURREAL_USER="root" +SURREAL_PASSWORD="root" +SURREAL_NAMESPACE="open_notebook" +SURREAL_DATABASE="staging" + +# RETRY CONFIGURATION (surreal-commands v1.2.0+) +# Global defaults for all background commands unless explicitly overridden at command level +# These settings help commands automatically recover from transient failures like: +# - Database transaction conflicts during concurrent operations +# - Network timeouts when calling external APIs +# - Rate limits from LLM/embedding providers +# - Temporary resource unavailability + +# Enable/disable retry globally (default: true) +# Set to false to disable retries for all commands (useful for debugging) +SURREAL_COMMANDS_RETRY_ENABLED=true + +# Maximum retry attempts before giving up (default: 3) +# Database operations use 5 attempts (defined per-command) +# API calls use 3 attempts (defined per-command) +SURREAL_COMMANDS_RETRY_MAX_ATTEMPTS=3 + +# Wait strategy between retry attempts (default: exponential_jitter) +# Options: exponential_jitter, exponential, fixed, random +# - exponential_jitter: Recommended - prevents thundering herd during DB conflicts +# - exponential: Good for API rate limits (predictable backoff) +# - fixed: Use for quick recovery scenarios +# - random: Use when you want unpredictable retry timing +SURREAL_COMMANDS_RETRY_WAIT_STRATEGY=exponential_jitter + +# Minimum wait time between retries in seconds (default: 1) +# Database conflicts: 1 second (fast retry for transient issues) +# API rate limits: 5 seconds (wait for quota reset) +SURREAL_COMMANDS_RETRY_WAIT_MIN=1 + +# Maximum wait time between retries in seconds (default: 30) +# Database conflicts: 30 seconds maximum +# API rate limits: 120 seconds maximum (defined per-command) +# Total retry time won't exceed max_attempts * wait_max +SURREAL_COMMANDS_RETRY_WAIT_MAX=30 + +# WORKER CONCURRENCY +# Maximum number of concurrent tasks in the worker pool (default: 5) +# This affects the likelihood of database transaction conflicts during batch operations +# +# Tuning guidelines based on deployment size: +# - Resource-constrained (low CPU/memory): 1-2 workers +# Reduces conflicts and resource usage, but slower processing +# +# - Normal deployment (balanced): 5 workers (RECOMMENDED) +# Good balance between throughput and conflict rate +# Retry logic handles occasional conflicts gracefully +# +# - Large instances (high CPU/memory): 10-20 workers +# Higher throughput but more frequent DB conflicts +# Relies heavily on retry logic with jittered backoff +# +# Note: Higher concurrency increases vectorization speed but also increases +# SurrealDB transaction conflicts. The retry logic with exponential-jitter +# backoff ensures operations complete successfully even at high concurrency. +SURREAL_COMMANDS_MAX_TASKS=5 + +# OPEN_NOTEBOOK_PASSWORD= + +# FIRECRAWL - Get a key at https://firecrawl.dev/ +FIRECRAWL_API_KEY= + +# JINA - Get a key at https://jina.ai/ +JINA_API_KEY= \ No newline at end of file diff --git a/apps/open-notebook/logo.png b/apps/open-notebook/logo.png new file mode 100644 index 0000000..0e75264 Binary files /dev/null and b/apps/open-notebook/logo.png differ