easydel.inference.vinference.api_client

easydel.inference.vinference.api_client#

exception easydel.inference.vinference.api_client.vInferenceAPIError(status_code: int, message: str, response_content: Optional[str] = None)[source]#

Bases: Exception

class easydel.inference.vinference.api_client.vInferenceChatCompletionClient(base_url: str, max_retries: int = 5, timeout: float = 30.0)[source]#

Bases: object

create_chat_completion(request: ChatCompletionRequest, extra_headers: Optional[dict] = None) → Generator[Union[ChatCompletionStreamResponse, ChatCompletionResponse], None, None][source]#

Create a chat completion with streaming response.

Parameters

request – ChatCompletionRequest object containing the request parameters

Yields

dict – Parsed response chunks from the API

Raises

  • vInferenceAPIError – If the API returns an error response

  • requests.RequestException – For network-related errors

Contents