mirror of
https://github.com/sligter/LandPPT.git
synced 2026-08-30 17:34:51 +08:00
feat: Update version number to 0.1.2, enhance documentation and function description
This commit is contained in:
sligter
@@ -6,6 +6,7 @@
|
||||
[](LICENSE)
|
||||
[](https://www.python.org)
|
||||
[](https://fastapi.tiangolo.com)
|
||||
[](https://hub.docker.com/r/bradleylzh/landppt)
|
||||
|
||||
[English](README_EN.md) | **中文**
|
||||
|
||||
@@ -14,6 +15,7 @@
|
||||
## 📋 目录
|
||||
|
||||
- [项目简介](#-项目简介)
|
||||
- [功能亮点](#-功能亮点)
|
||||
- [核心功能](#-核心功能)
|
||||
- [快速开始](#-快速开始)
|
||||
- [使用指南](#-使用指南)
|
||||
@@ -21,53 +23,77 @@
|
||||
- [API文档](#-api文档)
|
||||
- [技术栈](#️-技术栈)
|
||||
- [贡献指南](#-贡献指南)
|
||||
- [常见问题](#-常见问题)
|
||||
- [许可证](#-许可证)
|
||||
|
||||
## 🎯 项目简介
|
||||
|
||||
LandPPT 是一个基于LLM的演示文稿生成平台，能够自动将文档内容转换为专业的PPT演示文稿。平台支持多种AI模型，提供丰富的模板和样式选择，让用户能够创建高质量的演示文稿。
|
||||
LandPPT 是一个基于大语言模型（LLM）的智能演示文稿生成平台，能够自动将文档内容转换为专业的PPT演示文稿。平台集成了多种AI模型、智能图像处理、深度研究功能和丰富的模板系统，让用户能够轻松创建高质量的演示文稿。
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## 🌟 功能亮点
|
||||
|
||||
- **🚀 一键生成**：从主题到完整PPT，全程AI自动化处理
|
||||
- **🎨 智能配图**：AI自动匹配最适合的图像，支持多源获取
|
||||
- **🔍 深度研究**：集成多个搜索引擎，获取最新最全面的信息
|
||||
- **📱 响应式设计**：完美适配各种设备和屏幕尺寸
|
||||
- **🔒 企业级安全**：支持本地部署，数据安全可控
|
||||
|
||||
## ✨ 核心功能
|
||||
|
||||
### 🤖 多AI提供商支持
|
||||
- **OpenAI GPT系列**：GPT-4.5/GPT-5 等主流模型
|
||||
- **Anthropic Claude**：Claude-3 系列模型
|
||||
- **Google Gemini**：Gemini-2.5 系列模型
|
||||
- **Azure OpenAI**：企业级AI服务
|
||||
- **Ollama**：本地部署的开源模型
|
||||
- **OpenAI GPT系列**：GPT-4o、GPT-4o-mini 等最新模型
|
||||
- **Anthropic Claude**：Claude-3.5 Sonnet、Claude-3 Haiku 系列模型
|
||||
- **Google Gemini**：Gemini-1.5 Flash、Gemini-1.5 Pro 系列模型
|
||||
- **Azure OpenAI**：企业级AI服务，支持自定义部署
|
||||
- **Ollama**：本地部署的开源模型，支持 Llama、Mistral 等
|
||||
|
||||
### 📄 强大的文件处理能力
|
||||
- **多格式支持**：PDF、Word、Markdown、TXT等
|
||||
- **智能解析**：使用minueru和markitdown进行内容提取
|
||||
- **深度研究**：集成Tavily API的DEEP研究功能
|
||||
- **多格式支持**：PDF、Word、Markdown、TXT、Excel 等多种格式
|
||||
- **智能解析**：使用 MinerU 和 MarkItDown 进行高质量内容提取
|
||||
- **深度研究**：集成 Tavily API 和 SearXNG 的多源研究功能
|
||||
- **内容增强**：自动网页内容提取和智能摘要生成
|
||||
|
||||
### 🎨 智能图像处理系统
|
||||
- **多源图像获取**：本地图库、网络搜索、AI生成三合一
|
||||
- **网络图像搜索**：支持 Pixabay、Unsplash 等优质图库
|
||||
- **AI图像生成**：集成 DALL-E、SiliconFlow、Pollinations 等服务
|
||||
- **智能图像选择**：AI自动匹配最适合的图像内容
|
||||
- **图像处理优化**：自动尺寸调整、格式转换、质量优化
|
||||
|
||||
### 🔍 增强研究功能
|
||||
- **多引擎搜索**：Tavily 和 SearXNG 双引擎支持
|
||||
- **深度内容提取**：智能网页内容解析和结构化处理
|
||||
- **多语言支持**：支持中英文等多语言研究内容
|
||||
- **实时信息获取**：获取最新的网络信息和数据
|
||||
|
||||
### 🎨 丰富的模板系统
|
||||
- **全局主模板**：统一的HTML模板系统
|
||||
- **多样化布局**：AI生成多种创意页面布局
|
||||
- **全局主模板**：统一的HTML模板系统，支持响应式设计
|
||||
- **多样化布局**：AI生成多种创意页面布局和设计风格
|
||||
- **场景化模板**：通用、旅游、教育等多种专业场景模板
|
||||
- **自定义模板**：支持导入和创建个性化模板
|
||||
|
||||
### 📊 完整的项目管理
|
||||
- **三阶段工作流**：需求确认 → 大纲生成 → PPT生成
|
||||
- **可视化编辑**：大纲编辑器
|
||||
- **实时预览**：16:9响应式页面预览
|
||||
- **可视化编辑**：直观的大纲编辑器和实时预览
|
||||
- **版本管理**：项目历史记录和版本回溯功能
|
||||
- **批量操作**：支持批量生成和处理多个项目
|
||||
|
||||
### 🌐 现代化Web界面
|
||||
- **直观操作**：用户友好的Web界面
|
||||
- **AI聊天编辑**：侧边栏AI编辑功能
|
||||
- **多格式导出**：PDF/HTML/PPTX导出支持
|
||||
- **直观操作**：用户友好的响应式Web界面
|
||||
- **AI聊天编辑**：侧边栏AI编辑功能，支持实时对话
|
||||
- **多格式导出**：PDF/HTML/PPTX 多种格式导出支持
|
||||
- **实时预览**：16:9 标准比例的实时页面预览
|
||||
|
||||
## 🚀 快速开始
|
||||
|
||||
@@ -78,7 +104,7 @@ LandPPT 是一个基于LLM的演示文稿生成平台，能够自动将文档内
|
||||
|
||||
### 本地安装
|
||||
|
||||
#### 方一：uv（推荐）
|
||||
#### 方法一：uv（推荐）
|
||||
|
||||
```bash
|
||||
# 克隆项目
|
||||
@@ -94,7 +120,9 @@ curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
# 使用uv同步环境
|
||||
uv sync
|
||||
|
||||
# 安装额外依赖（可选，用于PPTX导出）
|
||||
uv pip install apryse-sdk --extra-index-url=https://pypi.apryse.com
|
||||
|
||||
# 配置环境变量
|
||||
cp .env.example .env
|
||||
# 编辑 .env 文件，配置你的AI API密钥
|
||||
@@ -103,6 +131,32 @@ cp .env.example .env
|
||||
uv run python run.py
|
||||
```
|
||||
|
||||
#### 方法二：传统pip安装
|
||||
|
||||
```bash
|
||||
# 克隆项目
|
||||
git clone https://github.com/sligter/LandPPT.git
|
||||
cd LandPPT
|
||||
|
||||
# 创建虚拟环境
|
||||
python -m venv venv
|
||||
# 激活虚拟环境
|
||||
# Windows
|
||||
venv\Scripts\activate
|
||||
# macOS/Linux
|
||||
source venv/bin/activate
|
||||
|
||||
# 安装依赖
|
||||
pip install -e .
|
||||
|
||||
# 配置环境变量
|
||||
cp .env.example .env
|
||||
# 编辑 .env 文件，配置你的AI API密钥
|
||||
|
||||
# 启动服务
|
||||
python run.py
|
||||
```
|
||||
|
||||
### Docker部署
|
||||
|
||||
#### 使用预构建镜像（推荐）
|
||||
@@ -146,14 +200,18 @@ docker logs -f landppt
|
||||
- 或配置本地Ollama服务
|
||||
|
||||
### 3. 创建PPT项目
|
||||
1. **需求确认**：输入主题、选择受众、设置页数范围
|
||||
2. **大纲生成**：AI生成大纲
|
||||
3. **PPT生成**：基于大纲生成完整的HTML演示文稿
|
||||
1. **需求确认**：输入主题、选择受众、设置页数范围、选择场景模板
|
||||
2. **大纲生成**：AI智能生成结构化大纲，支持可视化编辑
|
||||
3. **内容研究**：可选择启用深度研究功能，获取最新相关信息
|
||||
4. **图像配置**：配置图像获取方式（本地/网络/AI生成）
|
||||
5. **PPT生成**：基于大纲生成完整的HTML演示文稿
|
||||
|
||||
### 4. 编辑和导出
|
||||
- 使用AI聊天功能编辑HTML内容
|
||||
- 使用AI聊天功能实时编辑内容和样式
|
||||
- 支持图像替换和优化
|
||||
- 导出为PDF、HTML或PPTX格式
|
||||
- 保存项目版本和历史记录
|
||||
- 支持批量处理和模板复用
|
||||
|
||||
## 🔧 配置说明
|
||||
|
||||
@@ -173,9 +231,20 @@ HOST=0.0.0.0
|
||||
PORT=8000
|
||||
SECRET_KEY=your-secure-secret-key
|
||||
|
||||
# 功能配置
|
||||
TAVILY_API_KEY=your_tavily_api_key_here # 联网功能
|
||||
APRYSE_LICENSE_KEY=your_apryse_key_here # PPTX导出
|
||||
# 研究功能配置
|
||||
TAVILY_API_KEY=your_tavily_api_key_here # Tavily 搜索引擎
|
||||
SEARXNG_HOST=http://localhost:8888 # SearXNG 实例地址
|
||||
RESEARCH_PROVIDER=tavily # 研究提供商：tavily, searxng, both
|
||||
|
||||
# 图像服务配置
|
||||
ENABLE_IMAGE_SERVICE=true # 启用图像服务
|
||||
PIXABAY_API_KEY=your_pixabay_api_key_here # Pixabay 图库
|
||||
UNSPLASH_ACCESS_KEY=your_unsplash_key_here # Unsplash 图库
|
||||
SILICONFLOW_API_KEY=your_siliconflow_key_here # AI图像生成
|
||||
POLLINATIONS_API_TOKEN=your_pollinations_token # Pollinations AI
|
||||
|
||||
# 导出功能配置
|
||||
APRYSE_LICENSE_KEY=your_apryse_key_here # PPTX导出
|
||||
|
||||
# 生成参数
|
||||
MAX_TOKENS=8192
|
||||
@@ -191,24 +260,38 @@ TEMPERATURE=0.7
|
||||
## 🛠️ 技术栈
|
||||
|
||||
### 后端技术
|
||||
- **FastAPI**: 现代化的Python Web框架
|
||||
- **SQLAlchemy**: ORM数据库操作
|
||||
- **Pydantic**: 数据验证和序列化
|
||||
- **Uvicorn**: ASGI服务器
|
||||
- **FastAPI**: 现代化的Python Web框架，支持异步处理
|
||||
- **SQLAlchemy**: ORM数据库操作，支持多种数据库
|
||||
- **Pydantic**: 数据验证和序列化，类型安全
|
||||
- **Uvicorn**: 高性能ASGI服务器
|
||||
|
||||
### AI集成
|
||||
- **OpenAI**: GPT系列模型
|
||||
- **Anthropic**: Claude系列模型
|
||||
- **Google AI**: Gemini系列模型
|
||||
- **LangChain**: AI应用开发框架
|
||||
- **OpenAI**: GPT-4o、GPT-4o-mini 等最新模型
|
||||
- **Anthropic**: Claude-3.5 系列模型
|
||||
- **Google AI**: Gemini-1.5 系列模型
|
||||
- **LangChain**: AI应用开发框架和工具链
|
||||
- **Ollama**: 本地模型部署和管理
|
||||
|
||||
### 文件处理
|
||||
- **mineru**: PDF智能解析
|
||||
- **markitdown**: 多格式文档转换
|
||||
- **MinerU**: 高质量PDF智能解析和结构化提取
|
||||
- **MarkItDown**: 多格式文档转换（Word、Excel、PowerPoint等）
|
||||
- **BeautifulSoup4**: HTML/XML解析和处理
|
||||
|
||||
### 图像处理
|
||||
- **Pillow**: 图像处理和格式转换
|
||||
- **OpenAI DALL-E**: AI图像生成
|
||||
- **SiliconFlow**: 国产AI图像生成服务
|
||||
- **Pollinations**: 开源AI图像生成平台
|
||||
|
||||
### 研究功能
|
||||
- **Tavily**: 专业搜索引擎API
|
||||
- **SearXNG**: 开源元搜索引擎
|
||||
- **HTTPX**: 异步HTTP客户端
|
||||
- **Playwright**: 网页内容提取
|
||||
|
||||
### 导出功能
|
||||
- **Pyppeteer**: HTML转PDF
|
||||
- **Apryse SDK**: PPTX生成
|
||||
- **Playwright**: HTML转PDF高质量导出
|
||||
- **Apryse SDK**: 专业PPTX生成和转换
|
||||
|
||||
## 🤝 贡献指南
|
||||
|
||||
@@ -226,6 +309,26 @@ TEMPERATURE=0.7
|
||||
### 报告问题
|
||||
如果你发现了bug或有功能建议，请在 [Issues](https://github.com/sligter/LandPPT/issues) 页面创建新的issue。
|
||||
|
||||
## ❓ 常见问题
|
||||
|
||||
### Q: 支持哪些AI模型？
|
||||
A: 支持 OpenAI GPT(兼容)、Anthropic Claude、Google Gemini、Azure OpenAI 和 Ollama 本地模型。可以在配置页面切换不同的AI提供商。
|
||||
|
||||
### Q: 如何配置图像功能？
|
||||
A: 在 `.env` 文件中配置相应的API密钥：
|
||||
- Pixabay: `PIXABAY_API_KEY`
|
||||
- Unsplash: `UNSPLASH_ACCESS_KEY`
|
||||
- AI生成: `SILICONFLOW_API_KEY` 或 `POLLINATIONS_API_TOKEN`
|
||||
|
||||
### Q: 研究功能如何使用？
|
||||
A: 配置 `TAVILY_API_KEY` 或部署 SearXNG 实例，然后在创建PPT时启用研究功能即可自动获取相关信息。
|
||||
|
||||
### Q: 支持本地部署吗？
|
||||
A: 完全支持本地部署，可以使用 Docker 或直接安装。支持 Ollama 本地模型，无需依赖外部API。
|
||||
|
||||
### Q: 如何导出PPTX格式？
|
||||
A: 需要配置 `APRYSE_LICENSE_KEY`，然后在导出选项中选择PPTX格式。
|
||||
|
||||
## 📄 许可证
|
||||
|
||||
本项目采用 Apache License 2.0 许可证。详情请见 [LICENSE](LICENSE) 文件。
|
||||
|
||||
+144
-39
@@ -6,6 +6,7 @@
|
||||
[](LICENSE)
|
||||
[](https://www.python.org)
|
||||
[](https://fastapi.tiangolo.com)
|
||||
[](https://hub.docker.com/r/bradleylzh/landppt)
|
||||
|
||||
**English** | [中文](README.md)
|
||||
|
||||
@@ -14,6 +15,7 @@
|
||||
## 📋 Table of Contents
|
||||
|
||||
- [Project Overview](#-project-overview)
|
||||
- [Feature Highlights](#-feature-highlights)
|
||||
- [Key Features](#-key-features)
|
||||
- [Quick Start](#-quick-start)
|
||||
- [Usage Guide](#-usage-guide)
|
||||
@@ -21,52 +23,78 @@
|
||||
- [API Documentation](#-api-documentation)
|
||||
- [Tech Stack](#️-tech-stack)
|
||||
- [Contributing](#-contributing)
|
||||
- [FAQ](#-faq)
|
||||
- [License](#-license)
|
||||
|
||||
## 🎯 Project Overview
|
||||
|
||||
LandPPT is an AI-powered presentation generation platform that automatically converts document content into professional PPT presentations. The platform supports multiple AI models and provides rich templates and style options, enabling users to create high-quality presentations.
|
||||
LandPPT is an intelligent presentation generation platform powered by Large Language Models (LLMs) that automatically converts document content into professional PPT presentations. The platform integrates multiple AI models, intelligent image processing, deep research capabilities, and rich template systems, enabling users to effortlessly create high-quality presentations.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## 🌟 Feature Highlights
|
||||
|
||||
- **🚀 One-Click Generation**: From topic to complete PPT, fully automated AI processing
|
||||
- **🎨 Smart Image Matching**: AI automatically matches the most suitable images with multi-source support
|
||||
- **🔍 Deep Research**: Integrated multiple search engines for latest and comprehensive information
|
||||
- **📱 Responsive Design**: Perfect adaptation to various devices and screen sizes
|
||||
processing
|
||||
- **🔒 Enterprise Security**: Support for local deployment with controllable data security
|
||||
|
||||
## ✨ Key Features
|
||||
|
||||
### 🤖 Multi-AI Provider Support
|
||||
- **OpenAI GPT Series**: GPT-4.5/GPT-5 and other mainstream models
|
||||
- **Anthropic Claude**: Claude-3 series models
|
||||
- **Google Gemini**: Gemini-2.5 series models
|
||||
- **Azure OpenAI**: Enterprise-grade AI services
|
||||
- **Ollama**: Locally deployed open-source models
|
||||
- **OpenAI GPT Series**: GPT-4o, GPT-4o-mini and other latest models
|
||||
- **Anthropic Claude**: Claude-3.5 Sonnet, Claude-3 Haiku series models
|
||||
- **Google Gemini**: Gemini-1.5 Flash, Gemini-1.5 Pro series models
|
||||
- **Azure OpenAI**: Enterprise-grade AI services with custom deployments
|
||||
- **Ollama**: Locally deployed open-source models supporting Llama, Mistral, etc.
|
||||
|
||||
### 📄 Powerful File Processing
|
||||
- **Multi-format Support**: PDF, Word, Markdown, TXT, etc.
|
||||
- **Intelligent Parsing**: Content extraction using minueru and markitdown
|
||||
- **Deep Research**: DEEP research functionality with Tavily API integration
|
||||
- **Multi-format Support**: PDF, Word, Markdown, TXT, Excel and more formats
|
||||
- **Intelligent Parsing**: High-quality content extraction using MinerU and MarkItDown
|
||||
- **Deep Research**: Multi-source research with Tavily API and SearXNG integration
|
||||
- **Content Enhancement**: Automatic web content extraction and intelligent summarization
|
||||
|
||||
### 🎨 Intelligent Image Processing System
|
||||
- **Multi-source Image Acquisition**: Local gallery, network search, and AI generation in one
|
||||
- **Network Image Search**: Support for premium galleries like Pixabay, Unsplash
|
||||
- **AI Image Generation**: Integration with DALL-E, SiliconFlow, Pollinations services
|
||||
- **Smart Image Selection**: AI automatically matches the most suitable image content
|
||||
- **Image Processing Optimization**: Automatic resizing, format conversion, quality optimization
|
||||
|
||||
### 🔍 Enhanced Research Capabilities
|
||||
- **Multi-engine Search**: Dual engine support with Tavily and SearXNG
|
||||
- **Deep Content Extraction**: Intelligent web content parsing and structured processing
|
||||
- **Multi-language Support**: Support for Chinese, English and other languages
|
||||
- **Real-time Information**: Access to latest web information and data
|
||||
|
||||
### 🎨 Rich Template System
|
||||
- **Global Master Templates**: Unified HTML template system
|
||||
- **Diverse Layouts**: AI-generated creative page layouts
|
||||
- **Global Master Templates**: Unified HTML template system with responsive design
|
||||
- **Diverse Layouts**: AI-generated creative page layouts and design styles
|
||||
- **Scenario-based Templates**: Professional templates for general, tourism, education scenarios
|
||||
- **Custom Templates**: Support for importing and creating personalized templates
|
||||
|
||||
### 📊 Complete Project Management
|
||||
- **Three-stage Workflow**: Requirements confirmation → Outline generation → PPT generation
|
||||
- **Visual Editing**: Outline editor
|
||||
- **Real-time Preview**: 16:9 responsive page preview
|
||||
- **Visual Editing**: Intuitive outline editor with real-time preview
|
||||
- **Version Management**: Project history and version rollback functionality
|
||||
- **Batch Operations**: Support for batch generation and processing multiple projects
|
||||
|
||||
### 🌐 Modern Web Interface
|
||||
- **Intuitive Operation**: User-friendly web interface
|
||||
- **AI Chat Editing**: Sidebar AI editing functionality
|
||||
- **Intuitive Operation**: User-friendly responsive web interface
|
||||
- **AI Chat Editing**: Sidebar AI editing with real-time conversation support
|
||||
- **Multi-format Export**: PDF/HTML/PPTX export support
|
||||
- **Real-time Preview**: 16:9 standard ratio real-time page preview
|
||||
|
||||
## 🚀 Quick Start
|
||||
|
||||
@@ -77,7 +105,7 @@ LandPPT is an AI-powered presentation generation platform that automatically con
|
||||
|
||||
### Local Installation
|
||||
|
||||
#### Method 1: Manual Setup with uv (Recommended)
|
||||
#### Method 1: uv Setup (Recommended)
|
||||
|
||||
```bash
|
||||
# Clone the repository
|
||||
@@ -93,7 +121,9 @@ curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
# Sync environment with uv
|
||||
uv sync
|
||||
|
||||
# Install additional dependencies (optional, for PPTX export)
|
||||
uv pip install apryse-sdk --extra-index-url=https://pypi.apryse.com
|
||||
|
||||
# Configure environment variables
|
||||
cp .env.example .env
|
||||
# Edit .env file and configure your AI API keys
|
||||
@@ -102,6 +132,32 @@ cp .env.example .env
|
||||
uv run python run.py
|
||||
```
|
||||
|
||||
#### Method 2: Traditional pip Installation
|
||||
|
||||
```bash
|
||||
# Clone the repository
|
||||
git clone https://github.com/sligter/LandPPT.git
|
||||
cd LandPPT
|
||||
|
||||
# Create virtual environment
|
||||
python -m venv venv
|
||||
# Activate virtual environment
|
||||
# Windows
|
||||
venv\Scripts\activate
|
||||
# macOS/Linux
|
||||
source venv/bin/activate
|
||||
|
||||
# Install dependencies
|
||||
pip install -e .
|
||||
|
||||
# Configure environment variables
|
||||
cp .env.example .env
|
||||
# Edit .env file and configure your AI API keys
|
||||
|
||||
# Start the service
|
||||
python run.py
|
||||
```
|
||||
|
||||
### Docker Deployment
|
||||
|
||||
#### Using Pre-built Image (Recommended)
|
||||
@@ -149,14 +205,18 @@ Configure your AI API keys in the settings page:
|
||||
- Or configure local Ollama service
|
||||
|
||||
### 3. Create PPT Projects
|
||||
1. **Requirements Confirmation**: Input topic, select audience, set page range
|
||||
2. **Outline Generation**: AI generates editable mind map outline
|
||||
3. **PPT Generation**: Generate complete HTML presentation based on outline
|
||||
1. **Requirements Confirmation**: Input topic, select audience, set page range, choose scenario template
|
||||
2. **Outline Generation**: AI intelligently generates structured outline with visual editing support
|
||||
3. **Content Research**: Optionally enable deep research functionality to get latest relevant information
|
||||
4. **Image Configuration**: Configure image acquisition methods (local/network/AI generation)
|
||||
5. **PPT Generation**: Generate complete HTML presentation based on outline
|
||||
|
||||
### 4. Edit and Export
|
||||
- Use AI chat functionality to edit content
|
||||
- Use AI chat functionality for real-time content and style editing
|
||||
- Support image replacement and optimization
|
||||
- Export as PDF, HTML, or PPTX format
|
||||
- Save project versions and history
|
||||
- Support batch processing and template reuse
|
||||
|
||||
## 🔧 Configuration
|
||||
|
||||
@@ -176,9 +236,20 @@ HOST=0.0.0.0
|
||||
PORT=8000
|
||||
SECRET_KEY=your-secure-secret-key
|
||||
|
||||
# Feature Configuration
|
||||
TAVILY_API_KEY=your_tavily_api_key_here # Research functionality
|
||||
APRYSE_LICENSE_KEY=your_apryse_key_here # PPTX export
|
||||
# Research Functionality Configuration
|
||||
TAVILY_API_KEY=your_tavily_api_key_here # Tavily search engine
|
||||
SEARXNG_HOST=http://localhost:8888 # SearXNG instance URL
|
||||
RESEARCH_PROVIDER=tavily # Research provider: tavily, searxng, both
|
||||
|
||||
# Image Service Configuration
|
||||
ENABLE_IMAGE_SERVICE=true # Enable image service
|
||||
PIXABAY_API_KEY=your_pixabay_api_key_here # Pixabay gallery
|
||||
UNSPLASH_ACCESS_KEY=your_unsplash_key_here # Unsplash gallery
|
||||
SILICONFLOW_API_KEY=your_siliconflow_key_here # AI image generation
|
||||
POLLINATIONS_API_TOKEN=your_pollinations_token # Pollinations AI
|
||||
|
||||
# Export Functionality Configuration
|
||||
APRYSE_LICENSE_KEY=your_apryse_key_here # PPTX export
|
||||
|
||||
# Generation Parameters
|
||||
MAX_TOKENS=8192
|
||||
@@ -194,24 +265,38 @@ After starting the service, visit:
|
||||
## 🛠️ Tech Stack
|
||||
|
||||
### Backend Technologies
|
||||
- **FastAPI**: Modern Python web framework
|
||||
- **SQLAlchemy**: ORM database operations
|
||||
- **Pydantic**: Data validation and serialization
|
||||
- **Uvicorn**: ASGI server
|
||||
- **FastAPI**: Modern Python web framework with async support
|
||||
- **SQLAlchemy**: ORM database operations supporting multiple databases
|
||||
- **Pydantic**: Data validation and serialization with type safety
|
||||
- **Uvicorn**: High-performance ASGI server
|
||||
|
||||
### AI Integration
|
||||
- **OpenAI**: GPT series models
|
||||
- **Anthropic**: Claude series models
|
||||
- **Google AI**: Gemini series models
|
||||
- **LangChain**: AI application development framework
|
||||
- **OpenAI**: GPT-4o, GPT-4o-mini and other latest models
|
||||
- **Anthropic**: Claude-3.5 series models
|
||||
- **Google AI**: Gemini-1.5 series models
|
||||
- **LangChain**: AI application development framework and toolchain
|
||||
- **Ollama**: Local model deployment and management
|
||||
|
||||
### File Processing
|
||||
- **mineru**: Intelligent PDF parsing
|
||||
- **markitdown**: Multi-format document conversion
|
||||
- **MinerU**: High-quality PDF intelligent parsing and structured extraction
|
||||
- **MarkItDown**: Multi-format document conversion (Word, Excel, PowerPoint, etc.)
|
||||
- **BeautifulSoup4**: HTML/XML parsing and processing
|
||||
|
||||
### Image Processing
|
||||
- **Pillow**: Image processing and format conversion
|
||||
- **OpenAI DALL-E**: AI image generation
|
||||
- **SiliconFlow**: Domestic AI image generation service
|
||||
- **Pollinations**: Open-source AI image generation platform
|
||||
|
||||
### Research Capabilities
|
||||
- **Tavily**: Professional search engine API
|
||||
- **SearXNG**: Open-source meta search engine
|
||||
- **HTTPX**: Asynchronous HTTP client
|
||||
- **Playwright**: Web content extraction
|
||||
|
||||
### Export Functionality
|
||||
- **Pyppeteer**: HTML to PDF conversion
|
||||
- **Apryse SDK**: PPTX generation
|
||||
- **Playwright**: High-quality HTML to PDF export
|
||||
- **Apryse SDK**: Professional PPTX generation and conversion
|
||||
|
||||
## 🤝 Contributing
|
||||
|
||||
@@ -229,6 +314,26 @@ For details, please see [Contributing Guide](CONTRIBUTING.md).
|
||||
### Reporting Issues
|
||||
If you find bugs or have feature suggestions, please create a new issue on the [Issues](https://github.com/sligter/LandPPT/issues) page.
|
||||
|
||||
## ❓ FAQ
|
||||
|
||||
### Q: Which AI models are supported?
|
||||
A: Supports OpenAI GPT, Anthropic Claude, Google Gemini, Azure OpenAI, and Ollama local models. You can switch between different AI providers in the configuration page.
|
||||
|
||||
### Q: How to configure image functionality?
|
||||
A: Configure the corresponding API keys in the `.env` file:
|
||||
- Pixabay: `PIXABAY_API_KEY`
|
||||
- Unsplash: `UNSPLASH_ACCESS_KEY`
|
||||
- AI Generation: `SILICONFLOW_API_KEY` or `POLLINATIONS_API_TOKEN`
|
||||
|
||||
### Q: How to use the research functionality?
|
||||
A: Configure `TAVILY_API_KEY` or deploy a SearXNG instance, then enable research functionality when creating PPTs to automatically get relevant information.
|
||||
|
||||
### Q: Does it support local deployment?
|
||||
A: Fully supports local deployment, can use Docker or direct installation. Supports Ollama local models without relying on external APIs.
|
||||
|
||||
### Q: How to export PPTX format?
|
||||
A: Need to configure `APRYSE_LICENSE_KEY`, then select PPTX format in export options.
|
||||
|
||||
## 📄 License
|
||||
|
||||
This project is licensed under the Apache License 2.0. See the [LICENSE](LICENSE) file for details.
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
[project]
|
||||
name = "landppt"
|
||||
version = "0.1.1"
|
||||
version = "0.1.2"
|
||||
description = "AI-powered PPT generation platform with OpenAI-compatible API"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.11"
|
||||
|
||||
Reference in New Issue
Block a user