agents.clients.generic#
Module Contents#
Classes#
A generic client for interacting with OpenAI-compatible APIs, including vLLM, ms-swift, lmdeploy, Google Gemini etc. This client works with LLM multimodal LLM models and supports both standard and streaming responses. It is designed to be compatible with any API that follows the OpenAI standard. |
API#
- class agents.clients.generic.GenericHTTPClient(model: Union[agents.models.Model, Dict], host: str = '127.0.0.1', port: Optional[int] = 8000, inference_timeout: int = 30, api_key: Optional[str] = None, logging_level: str = 'info', **kwargs)#
Bases:
agents.clients.model_base.ModelClientA generic client for interacting with OpenAI-compatible APIs, including vLLM, ms-swift, lmdeploy, Google Gemini etc. This client works with LLM multimodal LLM models and supports both standard and streaming responses. It is designed to be compatible with any API that follows the OpenAI standard.
- property supports_tool_calls: bool#
Generic HTTP client (OpenAI compatible) supports tool calling.
- Return type:
bool
- serialize() Dict#
Get client json
- Return type:
Dict
- check_connection() None#
initialize.
- Return type:
None
- initialize() None#
initialize.
- Return type:
None
- inference(inference_input: Dict[str, Any]) Optional[MutableMapping]#
inference.
- Parameters:
inference_input (dict[str, Any])
- Return type:
dict | None
- deinitialize()#
deinitialize.