Metadata-Version: 2.1
Name: pure_agent
Version: 0.1.1
Summary: A brief description of the package.
Home-page: https://github.com/yourusername/pbot
Author: Your Name
Author-email: your.email@example.com
License: MIT
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Requires-Python: >=3.6
Description-Content-Type: text/markdown

## Quickstart

First install the packages:

```bash

pip install pure_agent 
```

setup your config.yaml
```yaml
env:
  api_key: xxx
infer_params:
  model: gpt-4o-mini
  temperature: 0.8
  top_p: 0.8
  max_tokens: 512
```

write your first agent based on pure\_agent!
```python
from pure_agent import *

class MyAgent(BaseAgent):
    @append_msg('msgs')
    def greeting(self, sys_name, prompt):
        with RoleCtx('system'):
            yield f"You are a helpful assistant, your name is {sys_name}."
        with RoleCtx('user'):
            yield prompt

sys_names = ['pbot0', 'pbot1']
prompts = ['who are u?', 'who are u?']
with MultiThreadExecutor(10, '.cache') as pool:
    for i in range(len(sys_names)):
        agent = MyAgent(client_config='config.yaml')
        task = agent.greeting(sys_names[i], prompts[i])
        # print(pretty_print_nested(msgs))
        pool.submit(task)
```
