Metadata-Version: 2.1
Name: cellium
Version: 0.1.0
Summary: Inference client for the Cellium Network. Created by Agent Artificial. Based on OpenAI's API Client.
Author: Richard Porteous
Author-email: richard@agentartificial.com
Requires-Python: >=3.10,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Dist: httpx (>=0.27.0,<0.28.0)
Requires-Dist: loguru (>=0.7.2,<0.8.0)
Requires-Dist: openai (>=1.14.2,<2.0.0)
Requires-Dist: python-dotenv (>=1.0.1,<2.0.0)
Requires-Dist: websocket (>=0.2.1,<0.3.0)
Description-Content-Type: text/markdown

# Agent Artificial OpenAI Client

This library enables OpenAI standard client to interface with the Agent Artificial API endpoints for inference. 

## Instillation 

`pip install agentartificial`

## Usage

Import `AgentArtificial` and instantiate a new instance and pass the `OpenAI` class into the agent client. It will automatically configure the client to hit Agent Artificial endpoints. 

Example
```
import os
from dotenv import load_dotenv
from agentartificial import AgentArtificial

load_dotenv()

client = AgentArtificial()



response = client.chat.completions.create(
    model=client.agent_model,
    messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "Who won the world series in 2020?"},
            {
                "role": "assistant",
                "content": "The Los Angeles Dodgers won the World Series in 2020.",
            },
            {"role": "user", "content": "Where was it played?"},
        ]
)
message = response['data']['choices'][0]['message']['content']


```

