Create

Create Chat

Create a new chat instance to interact with AI models using Python.

Constructor

Chat(broker: ZGComputeBroker, provider_address: str, temperature: float = 0.7, max_tokens: int = 1000)

Parameters

broker · ZGComputeBroker · required

The compute broker instance for connecting to the 0G network

provider_address · str · required

The provider address on the 0G network for the AI model

temperature · float · default: "0.7"

Controls randomness in responses (0.0-2.0)

max_tokens · int · default: "1000"

Maximum number of tokens in the response

Response

Returns a Chat instance that can be used to send messages and stream responses.

Example

Basic Usage

import asyncio
from zg_ai_sdk import create_agent

async def main():
    agent = await create_agent({
        'name': 'My Assistant',
        'provider_address': '0xf07240Efa67755B5311bc75784a061eDB47165Dd',  # llama-3.3-70b-instruct
        'memory_bucket': 'my-agent-memory',
        'private_key': 'your-private-key',
        'max_tokens': 2000,
        'temperature': 0.8
    })
    
    response = await agent.ask('Hello, how are you?')
    print(response)

asyncio.run(main())

Available Models

The 0G AI SDK connects to models running on the 0G decentralized compute network:

Model	Provider Address	Description	Verification
llama-3.3-70b-instruct	0xf07240Efa67755B5311bc75784a061eDB47165Dd	State-of-the-art 70B parameter model for general AI tasks	TEE (TeeML)
deepseek-r1-70b	0x3feE5a4dd5FDb8a32dDA97Bed899830605dBD9D3	Advanced reasoning model optimized for complex problem solving	TEE (TeeML)

Methods

ask()

Send a simple question to the AI model.

async def ask(self, question: str, system_prompt: Optional[str] = None) -> str

Parameters:

• question (str): The question to ask the AI
• system_prompt (Optional[str]): Optional system prompt to set context

Returns: str - The AI’s response

Example:

response = await chat.ask('What is machine learning?')
print(response)

chat_completion()

Send a structured chat completion request.

async def chat_completion(self, messages: List[ChatMessage]) -> ChatCompletionResponse

Parameters:

• messages (List[ChatMessage]): List of chat messages

Returns: ChatCompletionResponse - Structured response with usage info

Example:

from zg_ai_sdk import ChatMessage

messages = [
    ChatMessage(role='system', content='You are a helpful assistant'),
    ChatMessage(role='user', content='Explain quantum computing')
]

response = await chat.chat_completion(messages)
print(response.choices[0].message.content)

stream_chat_completion()

Stream responses for real-time chat.

async def stream_chat_completion(
    self, 
    messages: List[ChatMessage], 
    on_chunk: callable
) -> str

Parameters:

• messages (List[ChatMessage]): List of chat messages
• on_chunk (callable): Callback function for each chunk

Returns: str - Complete response text

Example:

def handle_chunk(chunk: str):
    print(chunk, end='', flush=True)

messages = [ChatMessage(role='user', content='Tell me a story')]
full_response = await chat.stream_chat_completion(messages, handle_chunk)

get_service_info()

Get information about the AI service.

async def get_service_info(self) -> ServiceMetadata

Returns: ServiceMetadata - Service information including endpoint and model

Example:

info = await chat.get_service_info()
print(f"Model: {info.model}, Endpoint: {info.endpoint}")

Configuration Methods

set_temperature()

Update the temperature setting.

def set_temperature(self, temperature: float) -> None

Parameters:

• temperature (float): New temperature value (0.0-2.0)

Example:

chat.set_temperature(0.9)  # More creative responses

set_max_tokens()

Update the maximum tokens setting.

def set_max_tokens(self, max_tokens: int) -> None

Parameters:

• max_tokens (int): New maximum tokens value

Example:

chat.set_max_tokens(2000)  # Allow longer responses

get_config()

Get current configuration.

def get_config(self) -> Dict[str, Any]

Returns: Dict[str, Any] - Current configuration settings

Example:

config = chat.get_config()
print(f"Temperature: {config['temperature']}, Max Tokens: {config['max_tokens']}")

Error Handling

The constructor and methods will raise exceptions if:

• Invalid provider address is provided
• Network connection fails
• Invalid configuration parameters are passed

from zg_ai_sdk import SDKError

try:
    chat = Chat(
        broker=broker,
        provider_address='invalid-address',
        temperature=0.7
    )
    response = await chat.ask('Hello')
except SDKError as error:
    print(f'Failed to create chat: {error.message} (Code: {error.code})')
except Exception as error:
    print(f'Unexpected error: {error}')

Next Steps

• Stream Responses
• View Chat History
• Memory Integration