Metadata-Version: 2.4
Name: llmskit
Version: 0.0.6
Summary: Client and Tools for LLMs
Author-email: hongbo liu <bananabo@foxmail.com>
License: Apache-2.0
Project-URL: Homepage, https://gitee.com/maxbanana
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: httpx>=0.27.0
Requires-Dist: openai>=2.14.0
Requires-Dist: tenacity>=8.2.3
Requires-Dist: anthropic>=0.75.0
Dynamic: license-file

# llmskit
统一的LLM客户端与工具

## Documentation

完整的 API 文档待补充

## Installation

```bash
pip install llmskit
```

## Api
```python
# 调用embedding
from llmskit import OpenAIEmbeddings, AsyncOpenAIEmbeddings
# 调用LLM
from llmskit import ChatLLM, AsyncChatLLM
```

## Usage
```python
from llmskit.chat import ChatLLM


chat = ChatLLM.from_openai(model="", base_url="")
messages = [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "who are you?"}
        ]

response = chat.complete(messages=messages)

print(response)
# 输出
# LLMChatComplete(content='I am Qwen, a large-scale language model independently developed by the Tongyi Lab under Alibaba Group. I can answer questions, create text such as stories, official documents, emails, scripts, perform logical reasoning, coding, and more. I can also express opinions and play games. I am trained on a vast amount of internet text and have extensive knowledge and strong language understanding capabilities. How can I assist you today?', reasoning_content='', tool_calls=[])

print(response.content)
```


## Todo
使用新版的返回格式
```python
import openai
openai.responses.create()
```
