copilot-swe-agent[bot]
b62ac7672a
Agent-Logs-Url: https://github.com/bytedance/deer-flow/sessions/a5f192e7-8034-4e46-af22-60b90ee27d40 Co-authored-by: foreleven <4785594+foreleven@users.noreply.github.com>
84 lines
1.5 KiB
Plaintext
84 lines
1.5 KiB
Plaintext
# 创建你的第一个 Harness
|
||
|
||
本教程介绍如何以编程方式使用 DeerFlow Harness Python SDK——直接在你的 Python 代码中导入和使用 DeerFlow，而不是通过 Web 界面。
|
||
|
||
## 前置条件
|
||
|
||
- Python 3.12+
|
||
- 已安装 `uv`
|
||
- 已克隆 DeerFlow 仓库
|
||
|
||
## 安装
|
||
|
||
```bash
|
||
cd deer-flow/backend
|
||
uv sync
|
||
```
|
||
|
||
## 创建配置
|
||
|
||
创建一个最小的 `config.yaml`：
|
||
|
||
```yaml
|
||
config_version: 6
|
||
|
||
models:
|
||
- name: gpt-4o
|
||
use: langchain_openai:ChatOpenAI
|
||
model: gpt-4o
|
||
api_key: $OPENAI_API_KEY
|
||
|
||
sandbox:
|
||
use: deerflow.sandbox.local:LocalSandboxProvider
|
||
|
||
tools:
|
||
- use: deerflow.community.ddg_search.tools:web_search_tool
|
||
- use: deerflow.sandbox.tools:read_file_tool
|
||
- use: deerflow.sandbox.tools:write_file_tool
|
||
```
|
||
|
||
## 编写代码
|
||
|
||
创建 `my_agent.py`：
|
||
|
||
```python
|
||
import asyncio
|
||
import os
|
||
from deerflow.client import DeerFlowClient
|
||
from deerflow.config import load_config
|
||
|
||
# 设置 API Key
|
||
os.environ["OPENAI_API_KEY"] = "sk-..."
|
||
|
||
# 加载配置
|
||
load_config()
|
||
|
||
client = DeerFlowClient()
|
||
|
||
async def main():
|
||
async for event in client.astream(
|
||
thread_id="my-first-thread",
|
||
message="用 Python 写一个斐波那契数列函数，包含文档字符串",
|
||
config={
|
||
"configurable": {
|
||
"model_name": "gpt-4o",
|
||
}
|
||
},
|
||
):
|
||
print(event)
|
||
|
||
asyncio.run(main())
|
||
```
|
||
|
||
## 运行
|
||
|
||
```bash
|
||
cd backend
|
||
uv run python my_agent.py
|
||
```
|
||
|
||
## 下一步
|
||
|
||
- [使用工具和技能](/docs/tutorials/use-tools-and-skills)
|
||
- [快速上手](/docs/harness/quick-start)
|