anthropic_llm

Module Contents

Classes

ClaudeAPI	Base class for API model wrapper.
AsyncClaudeAPI	Base class for API model wrapper.

class lagent.llms.anthropic_llm.ClaudeAPI(model_type='claude-3-5-sonnet-20241022', retry=5, key='ENV', proxies=None, 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='user')], temperature=NOT_GIVEN, max_new_tokens=512, top_p=NOT_GIVEN, top_k=NOT_GIVEN, repetition_penalty=0.0, stop_words=None)

Bases: lagent.llms.base_api.BaseAPILLM

Base class for API model wrapper.

参数:

• model_type (str) – The type of model.

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

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

• key (Union[str, List[str]]) –

• proxies (Optional[Dict]) –

• temperature (float) –

• max_new_tokens (int) –

• top_p (float) –

• top_k (int) –

• repetition_penalty (float) –

• stop_words (Union[List[str], str]) –

is_api: bool = True

clients

invalid_keys

key_ctr = 0

model_type = 'claude-3-5-sonnet-20241022'

proxies = None

chat(inputs, session_ids=None, **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

• session_ids (Union[int, List[int]]) –

返回:

generated string(s)

返回类型:

Union[str, List[str]]

generate_request_data(model_type, messages, gen_params)

Generates the request data for different model types.

参数:

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

• 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

class lagent.llms.anthropic_llm.AsyncClaudeAPI(model_type='claude-3-5-sonnet-20241022', retry=5, key='ENV', proxies=None, 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='user')], temperature=NOT_GIVEN, max_new_tokens=512, top_p=NOT_GIVEN, top_k=NOT_GIVEN, repetition_penalty=0.0, stop_words=None)

Bases: lagent.llms.base_api.AsyncBaseAPILLM

Base class for API model wrapper.

参数:

• model_type (str) – The type of model.

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

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

• key (Union[str, List[str]]) –

• proxies (Optional[Dict]) –

• temperature (float) –

• max_new_tokens (int) –

• top_p (float) –

• top_k (int) –

• repetition_penalty (float) –

• stop_words (Union[List[str], str]) –

is_api: bool = True

clients

invalid_keys

key_ctr = 0

model_type = 'claude-3-5-sonnet-20241022'

proxies = None

async chat(inputs, session_ids=None, **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

• session_ids (Union[int, List[int]]) –

返回:

generated string(s)

返回类型:

Union[str, List[str]]

generate_request_data(model_type, messages, gen_params)

Generates the request data for different model types.

参数:

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

• 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