boykopovar/aiodeepseek
GitHub: boykopovar/aiodeepseek
为 DeepSeek 私有 API 提供高性能异步调用的 Python 客户端，内置 PoW 求解和多轮对话支持。
Stars: 0 | Forks: 0
# aiodeepseek
一个高性能的私有 DeepSeek API 异步 Python 客户端。支持流式输出、图片上传、多轮对话以及新账号注册。
➡️ 俄文文档：[docs/ru/README.md](docs/ru/README.md)
## 安装
```
pip install aiodeepseek
```
C++ 扩展的构建需要支持 AVX2 的编译器以及 `pybind11`。更多详情请参阅 [docs/en/pow.md](docs/en/pow.md)。您也可以下载预编译的 [release](https://github.com/boykopovar/aiodeepseek/releases)。
## 快速开始
### 邮箱/密码认证
```
import asyncio
from aiodeepseek import DeepSeekClient
async def main():
async with DeepSeekClient(email="myname@example.com", password="password123") as client:
result = await client.ask("Hello!")
print(result.text)
asyncio.run(main())
```
### Token 认证
```
import asyncio
from aiodeepseek import DeepSeekClient
async def main():
async with DeepSeekClient(token="YOUR_TOKEN") as client:
result = await client.ask("Hello!")
print(result.text)
asyncio.run(main())
```
### 流式输出响应
```
import asyncio
from aiodeepseek import DeepSeekClient
async def main():
async with DeepSeekClient(token="YOUR_TOKEN") as client:
async for chunk in client.ask_stream("Tell me about Python"):
print(chunk, end="", flush=True)
asyncio.run(main())
```
### 多轮对话
```
import asyncio
from aiodeepseek import DeepSeekClient
async def main():
async with DeepSeekClient(token="YOUR_TOKEN") as client:
chat = client.new_conversation()
print((await chat.ask("What is your name?")).text)
print((await chat.ask("What can you do?")).text)
asyncio.run(main())
```
### 图片上传
```
import asyncio
from pathlib import Path
from aiodeepseek import DeepSeekClient
async def main():
async with DeepSeekClient(token="YOUR_TOKEN") as client:
img = await client.upload_image(Path("photo.jpg"))
result = await client.ask("What is in the photo?", image=img)
print(result.text)
asyncio.run(main())
```
或者通过将 `Path | bytes` 直接传递给 `ask`：
```
import asyncio
from pathlib import Path
from aiodeepseek import DeepSeekClient
async def main():
async with DeepSeekClient(token="YOUR_TOKEN") as client:
result = await client.ask(
prompt="What is in the photo?",
image=Path("photo.jpg")
)
print(result.text)
asyncio.run(main())
```
### 注册新账号
```
import asyncio
from aiodeepseek import DeepSeekClient
async def main():
await DeepSeekClient.send_reg_code("myname@example.com")
code = input("Code from the email: ")
token = await DeepSeekClient.confirm_reg_code("myname@example.com", "password123", code)
print("Token:", token)
asyncio.run(main())
```
## 模型类型
```
from aiodeepseek import DeepSeekClient
from aiodeepseek.types.enums import ModelType
async with DeepSeekClient(token="...", model=ModelType.VISION) as client:
...
```
| 值 | 描述 |
|---------------------|-----------------------------------|
| `ModelType.DEFAULT` | 标准语言模型 |
| `ModelType.EXPERT` | 深度推理模型 |
| `ModelType.VISION` | 支持机器视觉的模型 |
## 错误处理
```
import asyncio
from aiodeepseek import DeepSeekClient
from aiodeepseek.types.exceptions import AuthorizationError, DeepSeekError
async def main():
try:
async with DeepSeekClient(token="invalid") as client:
await client.ask("Hello")
except AuthorizationError:
print("Token is invalid")
except DeepSeekError as e:
print(f"API error: {e}")
asyncio.run(main())
```
## 工作量证明
在每次请求之前，客户端会自动解算 DeepSeek 服务器发放的 PoW 挑战。典型的难度为 **144,000 次迭代**。该计算使用 AVX2 在 C++ 中实现，因此在实际使用中几乎难以察觉。更多详情请参阅 [docs/en/pow.md](docs/en/pow.md)。
## 文档
- [DeepSeekClient - 客户端方法](docs/en/client.md)
- [Conversation - 多轮对话](docs/en/conversation.md)
- [Types 和数据模型](docs/en/types.md)
- [Exceptions 异常](docs/en/exceptions.md)
- [工作量证明](docs/en/pow.md)
## 环境要求
- Python 3.9+
- `aiohttp >= 3.9`
- 支持 AVX2 的 C++17 编译器（用于构建扩展）或手动下载的 wheel 包。
标签：AI对话, API客户端, asyncio, ATT&CK 框架, AVX2, Chatbot, C++扩展, DeepSeek, NLP, PoW验证, pybind11, Python, Spyse API, 人工智能, 图像上传, 多轮对话, 大模型, 开源库, 异步编程, 搜索引擎爬虫, 无后门, 流式响应, 熵值分析, 用户模式Hook绕过, 计算机取证, 逆向工具