qianfan.resources.requestor package

Submodules

qianfan.resources.requestor.base module

API Requestor for SDK

class qianfan.resources.requestor.base.BaseAPIRequestor(**kwargs: Any)

Bases: object

Base class of API Requestor

qianfan.resources.requestor.console_requestor module

Console API Requestor

class qianfan.resources.requestor.console_requestor.ConsoleAPIRequestor(**kwargs: Any)

Bases: BaseAPIRequestor

object to manage console API requests

qianfan.resources.requestor.openapi_requestor module

Qianfan API Requestor

class qianfan.resources.requestor.openapi_requestor.PrivateAPIRequestor(**kwargs: Any)

Bases: QfAPIRequestor

qianfan private api requestor

llm(endpoint: str, header: ~typing.Dict[str, ~typing.Any] = {}, query: ~typing.Dict[str, ~typing.Any] = {}, body: ~typing.Dict[str, ~typing.Any] = {}, stream: bool = False, data_postprocess: ~typing.Callable[[~qianfan.resources.typing.QfResponse], ~qianfan.resources.typing.QfResponse] = <function PrivateAPIRequestor.<lambda>>, retry_config: ~qianfan.resources.typing.RetryConfig = RetryConfig(retry_count=1, timeout=10, max_wait_interval=120, backoff_factor=1, jitter=1, retry_err_codes={})) → Union[QfResponse, Iterator[QfResponse]]

llm related api request

class qianfan.resources.requestor.openapi_requestor.QfAPIRequestor(**kwargs: Any)

Bases: BaseAPIRequestor

object to manage Qianfan API requests

async async_llm(endpoint: str, header: ~typing.Dict[str, ~typing.Any] = {}, query: ~typing.Dict[str, ~typing.Any] = {}, body: ~typing.Dict[str, ~typing.Any] = {}, stream: bool = False, data_postprocess: ~typing.Callable[[~qianfan.resources.typing.QfResponse], ~qianfan.resources.typing.QfResponse] = <function QfAPIRequestor.<lambda>>, retry_config: ~qianfan.resources.typing.RetryConfig = RetryConfig(retry_count=1, timeout=10, max_wait_interval=120, backoff_factor=1, jitter=1, retry_err_codes={})) → Union[QfResponse, AsyncIterator[QfResponse]]

llm related api request

llm(endpoint: str, header: ~typing.Dict[str, ~typing.Any] = {}, query: ~typing.Dict[str, ~typing.Any] = {}, body: ~typing.Dict[str, ~typing.Any] = {}, stream: bool = False, data_postprocess: ~typing.Callable[[~qianfan.resources.typing.QfResponse], ~qianfan.resources.typing.QfResponse] = <function QfAPIRequestor.<lambda>>, retry_config: ~qianfan.resources.typing.RetryConfig = RetryConfig(retry_count=1, timeout=10, max_wait_interval=120, backoff_factor=1, jitter=1, retry_err_codes={})) → Union[QfResponse, Iterator[QfResponse]]

llm related api request

qianfan.resources.requestor.openapi_requestor.create_api_requestor(*args: Any, **kwargs: Any) → QfAPIRequestor