mirror of
https://github.com/camel-ai/owl.git
synced 2026-03-22 14:07:17 +08:00
Merge pull request #64 from camel-ai/branch_yh
update README.md, add core feature introduction
This commit is contained in:
@@ -64,6 +64,7 @@ Our vision is to revolutionize how AI agents collaborate to solve real-world tas
|
||||
- [📋 Table of Contents](#-table-of-contents)
|
||||
- [🔥 News](#-news)
|
||||
- [🎬 Demo Video](#-demo-video)
|
||||
- [✨️ Core Features](#-code-features)
|
||||
- [🛠️ Installation](#️-installation)
|
||||
- [**Clone the Github repository**](#clone-the-github-repository)
|
||||
- [**Set up Environment**](#set-up-environment)
|
||||
@@ -89,6 +90,13 @@ https://private-user-images.githubusercontent.com/55657767/420211368-f29f477d-7e
|
||||
|
||||
https://private-user-images.githubusercontent.com/55657767/420212194-e813fc05-136a-485f-8df3-f10d9b4e63ec.mp4
|
||||
|
||||
# ✨️ Core Features
|
||||
|
||||
- **Real-time Information Retrieval**: Leverage Wikipedia, Google Search, and other online sources for up-to-date information.
|
||||
- **Multimodal Processing**: Support for handling internet or local videos, images, and audio data.
|
||||
- **Browser Automation**: Utilize the Playwright framework for simulating browser interactions, including scrolling, clicking, input handling, downloading, navigation, and more.
|
||||
- **Document Parsing**: Extract content from Word, Excel, PDF, and PowerPoint files, converting them into text or Markdown format.
|
||||
- **Code Execution**: Write and execute Python code using interpreter.
|
||||
|
||||
# 🛠️ Installation
|
||||
|
||||
|
||||
@@ -65,6 +65,7 @@
|
||||
- [📋 目录](#-目录)
|
||||
- [🔥 新闻](#-新闻)
|
||||
- [🎬 演示视频](#-演示视频)
|
||||
- [✨️ 核心功能](#-核心功能)
|
||||
- [🛠️ 安装](#️-安装)
|
||||
- [**克隆 Github 仓库**](#克隆-github-仓库)
|
||||
- [**设置环境**](#设置环境)
|
||||
@@ -89,6 +90,14 @@ https://private-user-images.githubusercontent.com/55657767/420211368-f29f477d-7e
|
||||
|
||||
https://private-user-images.githubusercontent.com/55657767/420212194-e813fc05-136a-485f-8df3-f10d9b4e63ec.mp4
|
||||
|
||||
# ✨️ 核心功能
|
||||
|
||||
- **在线搜索**:使用维基百科、谷歌搜索等,进行实时信息检索
|
||||
- **多模态处理**:支持互联网或本地视频、图片、语音处理
|
||||
- **浏览器操作**:借助Playwright框架开发浏览器模拟交互,支持页面滚动、点击、输入、下载、历史回退等功能
|
||||
- **文件解析**:word、excel、PDF、PowerPoint信息提取,内容转文本/Markdown
|
||||
- **代码执行**:编写python代码,并使用解释器运行
|
||||
|
||||
# 🛠️ 安装
|
||||
|
||||
## **克隆 Github 仓库**
|
||||
|
||||
Reference in New Issue
Block a user