mirror of
https://github.com/camel-ai/owl.git
synced 2026-03-22 05:57:17 +08:00
Merge pull request #62 from camel-ai/branch_mk
update the instructions for customize task
This commit is contained in:
6
.gitignore
vendored
6
.gitignore
vendored
@@ -53,4 +53,8 @@ htmlcov/
|
||||
.coverage.*
|
||||
.cache
|
||||
coverage.xml
|
||||
*.cover
|
||||
*.cover
|
||||
|
||||
owl/camel/types/__pycache__/
|
||||
owl/camel/__pycache__/
|
||||
owl/camel/utils/__pycache_/
|
||||
|
||||
24
README.md
24
README.md
@@ -75,6 +75,7 @@ Our vision is to revolutionize how AI agents collaborate to solve real-world tas
|
||||
- [📄 License](#-license)
|
||||
- [🖊️ Cite](#️-cite)
|
||||
- [🔥 Community](#-community)
|
||||
- [❓ FAQ](#-faq)
|
||||
- [⭐ Star History](#-star-history)
|
||||
|
||||
|
||||
@@ -141,6 +142,23 @@ Run the following minimal example:
|
||||
```bash
|
||||
python owl/run.py
|
||||
```
|
||||
You can run OWL agent with your own task by modifying the `run.py` script:
|
||||
|
||||
```python
|
||||
# Define your own task
|
||||
question = "Task description here."
|
||||
|
||||
society = construct_society(question)
|
||||
answer, chat_history, token_count = run_society(society)
|
||||
|
||||
logger.success(f"Answer: {answer}")
|
||||
```
|
||||
|
||||
Example tasks you can try:
|
||||
- "Find the latest stock price for Apple Inc."
|
||||
- "Analyze the sentiment of recent tweets about climate change"
|
||||
- "Help me debug this Python code: [your code here]"
|
||||
- "Summarize the main points from this research paper: [paper URL]"
|
||||
|
||||
# 🧪 Experiments
|
||||
|
||||
@@ -183,12 +201,18 @@ Join us for further discussions!
|
||||

|
||||

|
||||
|
||||
# ❓ FAQ
|
||||
|
||||
**Q: Why is my Chrome browser showing a blank screen even though there's output in the console?**
|
||||
|
||||
A: This is expected behavior. When OWL determines that a task can be completed using non-browser tools (like search, code analysis, etc.), the browser window may remain blank. The browser is only activated when web interaction is necessary. We plan to implement lazy loading in future updates to improve this user experience.
|
||||
|
||||
# ⭐ Star History
|
||||
|
||||
[](https://star-history.com/#camel-ai/owl&Date)
|
||||
|
||||
|
||||
|
||||
[docs-image]: https://img.shields.io/badge/Documentation-EB3ECC
|
||||
[docs-url]: https://camel-ai.github.io/camel/index.html
|
||||
[star-image]: https://img.shields.io/github/stars/camel-ai/owl?label=stars&logo=github&color=brightgreen
|
||||
|
||||
23
README_zh.md
23
README_zh.md
@@ -76,6 +76,7 @@
|
||||
- [📄 许可证](#-许可证)
|
||||
- [🖊️ 引用](#️-引用)
|
||||
- [🔥 社区](#-社区)
|
||||
- [❓ 常见问题](#-常见问题)
|
||||
|
||||
|
||||
# 🔥 新闻
|
||||
@@ -138,6 +139,23 @@ python -m pip install -r requirements.txt
|
||||
python owl/run.py
|
||||
```
|
||||
|
||||
你可以通过修改 `run.py` 来运行自定义任务的 OWL 智能体:
|
||||
|
||||
```python
|
||||
# Define your own task
|
||||
question = "Task description here."
|
||||
|
||||
society = construct_society(question)
|
||||
answer, chat_history, token_count = run_society(society)
|
||||
|
||||
logger.success(f"Answer: {answer}")
|
||||
```
|
||||
|
||||
你可以尝试以下示例任务:
|
||||
- "查询苹果公司的最新股票价格"
|
||||
- "分析关于气候变化的最新推文情绪"
|
||||
- "帮我调试这段 Python 代码:[在此粘贴你的代码]"
|
||||
- "总结这篇研究论文的主要观点:[论文URL]"
|
||||
# 🧪 实验
|
||||
|
||||
我们提供了一个脚本用于复现 GAIA 上的实验结果。
|
||||
@@ -179,6 +197,11 @@ python run_gaia_roleplaying.py
|
||||

|
||||

|
||||
|
||||
# ❓ 常见问题
|
||||
|
||||
**Q: 为什么我的Chrome浏览器显示空白页面,但控制台有输出结果?**
|
||||
|
||||
A: 这是预期的行为。当OWL判断某个任务可以使用非浏览器工具(如搜索、代码分析等)完成时,浏览器窗口可能保持空白。浏览器仅在需要网页交互时才会被激活。我们计划在未来的更新中实现延迟加载以改善这一用户体验。
|
||||
|
||||
|
||||
[docs-image]: https://img.shields.io/badge/Documentation-EB3ECC
|
||||
|
||||
Reference in New Issue
Block a user