sensenova

Module Contents

Classes

SensenovaAPI

Model wrapper around SenseTime's models.

Attributes

SENSENOVA_API_BASE
sensechat_models

lagent.llms.sensenova.SENSENOVA_API_BASE = 'https://api.sensenova.cn/v1/llm/chat-completions'

lagent.llms.sensenova.sensechat_models

class lagent.llms.sensenova.SensenovaAPI(model_type='SenseChat-5-Cantonese', retry=2, json_mode=False, key='ENV', meta_template=[dict(role='system', api_role='system'), dict(role='user', api_role='user'), dict(role='assistant', api_role='assistant'), dict(role='environment', api_role='system')], sensenova_api_base=SENSENOVA_API_BASE, proxies=None, **gen_params)

Bases: lagent.llms.base_api.BaseAPILLM

Model wrapper around SenseTime’s models.

参数:

• model_type (str) – The name of SenseTime’s model.

• retry (int) – Number of retires if the API call fails. Defaults to 2.

• key (str or List[str]) – SenseTime key(s). In particular, when it is set to “ENV”, the key will be fetched from the environment variable $SENSENOVA_API_KEY. If it’s a list, the keys will be used in round-robin manner. Defaults to ‘ENV’.

• meta_template (Dict, optional) – The model’s meta prompt template if needed, in case the requirement of injecting or wrapping of any meta instructions.

• sensenova_api_base (str) – The base url of SenseTime’s API. Defaults to ‘https://api.sensenova.cn/v1/llm/chat-completions’.

• gen_params – Default generation configuration which could be overridden on the fly of generation.

• json_mode (bool) –

• proxies (Optional[Dict]) –

is_api: bool = True

logger

invalid_keys

key_ctr = 0

url = 'https://api.sensenova.cn/v1/llm/chat-completions'

model_type = 'SenseChat-5-Cantonese'

proxies = None

json_mode = False

chat(inputs, **gen_params)

Generate responses given the contexts.

参数:

• inputs (Union[List[dict], List[List[dict]]]) – a list of messages or list of lists of messages

• gen_params – additional generation configuration

返回:

generated string(s)

返回类型:

Union[str, List[str]]

stream_chat(inputs, **gen_params)

Generate responses given the contexts.

参数:

• inputs (List[dict]) – a list of messages

• gen_params – additional generation configuration

生成器:

Tuple[ModelStatusCode, str, Optional[str]] – Status code, generated string, and optional metadata

返回类型:

Generator[Tuple[lagent.schema.ModelStatusCode, str, Optional[str]], None, None]

generate_request_data(model_type, messages, gen_params, json_mode=False)

Generates the request data for different model types.

参数:

• model_type (str) – The type of the model (e.g., ‘sense’).

• messages (list) – The list of messages to be sent to the model.

• gen_params (dict) – The generation parameters.

• json_mode (bool) – Flag to determine if the response format should be JSON.

返回:

A tuple containing the header and the request data.

返回类型:

tuple

tokenize(prompt)

Tokenize the input prompt.

参数:

prompt (str) – Input string.

返回:

token ids

返回类型:

list