sherpa_ai.models package

Submodules

sherpa_ai.models.chat_model_with_logging module

class sherpa_ai.models.chat_model_with_logging.ChatModelWithLogging(*args: Any, name: str | None = None, cache: BaseCache | bool | None = None, verbose: bool = None, callbacks: Callbacks = None, tags: List[str] | None = None, metadata: Dict[str, Any] | None = None, custom_get_token_ids: Callable[[str], List[int]] | None = None, callback_manager: BaseCallbackManager | None = None, rate_limiter: BaseRateLimiter | None = None, disable_streaming: bool | Literal['tool_calling'] = False, llm: BaseChatModel, logger: Logger)

Bases: BaseChatModel

llm: BaseChatModel

logger: Logger

sherpa_ai.models.sherpa_base_chat_model module

class sherpa_ai.models.sherpa_base_chat_model.SherpaBaseChatModel(*args: Any, name: str | None = None, cache: BaseCache | bool | None = None, verbose: bool = None, callbacks: Callbacks = None, tags: List[str] | None = None, metadata: Dict[str, Any] | None = None, custom_get_token_ids: Callable[[str], List[int]] | None = None, callback_manager: BaseCallbackManager | None = None, rate_limiter: BaseRateLimiter | None = None, disable_streaming: bool | Literal['tool_calling'] = False, user_id: str | None = None, verbose_logger: BaseVerboseLogger = None)

Bases: BaseChatModel

user_id: str | None

verbose_logger: BaseVerboseLogger

class sherpa_ai.models.sherpa_base_chat_model.SherpaChatOpenAI(*args: Any, name: str | None = None, cache: BaseCache | bool | None = None, verbose: bool = None, callbacks: Callbacks = None, tags: List[str] | None = None, metadata: Dict[str, Any] | None = None, custom_get_token_ids: Callable[[str], List[int]] | None = None, callback_manager: BaseCallbackManager | None = None, rate_limiter: BaseRateLimiter | None = None, disable_streaming: bool | Literal['tool_calling'] = False, client: Any = None, async_client: Any = None, model: str = 'gpt-3.5-turbo', temperature: float = 0.7, model_kwargs: Dict[str, Any] = None, api_key: SecretStr | None = None, base_url: str | None = None, organization: str | None = None, openai_proxy: str | None = None, timeout: float | Tuple[float, float] | Any | None = None, max_retries: int = 2, streaming: bool = False, n: int = 1, max_tokens: int | None = None, tiktoken_model_name: str | None = None, default_headers: Mapping[str, str] | None = None, default_query: Mapping[str, object] | None = None, http_client: Any | None = None, http_async_client: Any | None = None, stop_sequences: List[str] | str | None = None, extra_body: Mapping[str, Any] | None = None, stream_usage: bool = False, user_id: str | None = None, verbose_logger: BaseVerboseLogger = None)

Bases: ChatOpenAI

user_id: str | None

verbose_logger: BaseVerboseLogger

sherpa_ai.models.sherpa_base_model module

class sherpa_ai.models.sherpa_base_model.SherpaOpenAI(*args: Any, name: str | None = None, cache: BaseCache | bool | None = None, verbose: bool = None, callbacks: Callbacks = None, tags: List[str] | None = None, metadata: Dict[str, Any] | None = None, custom_get_token_ids: Callable[[str], List[int]] | None = None, callback_manager: BaseCallbackManager | None = None, rate_limiter: BaseRateLimiter | None = None, disable_streaming: bool | Literal['tool_calling'] = False, client: Any = None, async_client: Any = None, model: str = 'gpt-3.5-turbo', temperature: float = 0.7, model_kwargs: Dict[str, Any] = None, api_key: SecretStr | None = None, base_url: str | None = None, organization: str | None = None, openai_proxy: str | None = None, timeout: float | Tuple[float, float] | Any | None = None, max_retries: int = 2, streaming: bool = False, n: int = 1, max_tokens: int | None = None, tiktoken_model_name: str | None = None, default_headers: Mapping[str, str] | None = None, default_query: Mapping[str, object] | None = None, http_client: Any | None = None, http_async_client: Any | None = None, stop_sequences: List[str] | str | None = None, extra_body: Mapping[str, Any] | None = None, stream_usage: bool = False, user_id: str | None = None)

Bases: ChatOpenAI

user_id: str | None

Module contents

class sherpa_ai.models.SherpaChatOpenAI(*args: Any, name: str | None = None, cache: BaseCache | bool | None = None, verbose: bool = None, callbacks: Callbacks = None, tags: List[str] | None = None, metadata: Dict[str, Any] | None = None, custom_get_token_ids: Callable[[str], List[int]] | None = None, callback_manager: BaseCallbackManager | None = None, rate_limiter: BaseRateLimiter | None = None, disable_streaming: bool | Literal['tool_calling'] = False, client: Any = None, async_client: Any = None, model: str = 'gpt-3.5-turbo', temperature: float = 0.7, model_kwargs: Dict[str, Any] = None, api_key: SecretStr | None = None, base_url: str | None = None, organization: str | None = None, openai_proxy: str | None = None, timeout: float | Tuple[float, float] | Any | None = None, max_retries: int = 2, streaming: bool = False, n: int = 1, max_tokens: int | None = None, tiktoken_model_name: str | None = None, default_headers: Mapping[str, str] | None = None, default_query: Mapping[str, object] | None = None, http_client: Any | None = None, http_async_client: Any | None = None, stop_sequences: List[str] | str | None = None, extra_body: Mapping[str, Any] | None = None, stream_usage: bool = False, user_id: str | None = None, verbose_logger: BaseVerboseLogger = None)

Bases: ChatOpenAI

cache: BaseCache | bool | None

Whether to cache the response.

• If true, will use the global cache.

• If false, will not use a cache

• If None, will use the global cache if it’s set, otherwise no cache.

• If instance of BaseCache, will use the provided cache.

Caching is not currently supported for streaming methods of models.

callback_manager: BaseCallbackManager | None

callbacks: Callbacks

Callbacks to add to the run trace.

custom_get_token_ids: Callable[[str], List[int]] | None

Optional encoder to use for counting tokens.

default_headers: Mapping[str, str] | None

default_query: Mapping[str, object] | None

disable_streaming: bool | Literal['tool_calling']

Whether to disable streaming for this model.

If streaming is bypassed, then stream()/astream() will defer to invoke()/ainvoke().

• If True, will always bypass streaming case.

• If “tool_calling”, will bypass streaming case only when the model is called with a tools keyword argument.

• If False (default), will always use streaming case if available.

extra_body: Mapping[str, Any] | None

Optional additional JSON properties to include in the request parameters when making requests to OpenAI compatible APIs, such as vLLM.

http_async_client: Any | None

Optional httpx.AsyncClient. Only used for async invocations. Must specify http_client as well if you’d like a custom client for sync invocations.

http_client: Any | None

Optional httpx.Client. Only used for sync invocations. Must specify http_async_client as well if you’d like a custom client for async invocations.

max_retries: int

Maximum number of retries to make when generating.

max_tokens: int | None

Maximum number of tokens to generate.

metadata: Dict[str, Any] | None

Metadata to add to the run trace.

model_kwargs: Dict[str, Any]

Holds any model parameters valid for create call not explicitly specified.

model_name: str

Model name to use.

n: int

Number of chat completions to generate for each prompt.

openai_api_base: str | None

Base URL path for API requests, leave blank if not using a proxy or service emulator.

openai_api_key: SecretStr | None

Automatically inferred from env var OPENAI_API_KEY if not provided.

openai_organization: str | None

Automatically inferred from env var OPENAI_ORG_ID if not provided.

openai_proxy: str | None

rate_limiter: BaseRateLimiter | None

An optional rate limiter to use for limiting the number of requests.

request_timeout: float | Tuple[float, float] | Any | None

Timeout for requests to OpenAI completion API. Can be float, httpx.Timeout or None.

stop: List[str] | str | None

Default stop sequences.

stream_usage: bool

Whether to include usage metadata in streaming output. If True, additional message chunks will be generated during the stream including usage metadata.

streaming: bool

Whether to stream the results or not.

tags: List[str] | None

Tags to add to the run trace.

temperature: float

What sampling temperature to use.

tiktoken_model_name: str | None

The model name to pass to tiktoken when using this class. Tiktoken is used to count the number of tokens in documents to constrain them to be under a certain limit. By default, when set to None, this will be the same as the embedding model name. However, there are some cases where you may want to use this Embedding class with a model name not supported by tiktoken. This can include when using Azure embeddings or when using one of the many model providers that expose an OpenAI-like API but with different models. In those cases, in order to avoid erroring when tiktoken is called, you can specify a model name to use here.

user_id: str | None

verbose: bool

Whether to print out response text.

verbose_logger: BaseVerboseLogger

class sherpa_ai.models.SherpaOpenAI(*args: Any, name: str | None = None, cache: BaseCache | bool | None = None, verbose: bool = None, callbacks: Callbacks = None, tags: List[str] | None = None, metadata: Dict[str, Any] | None = None, custom_get_token_ids: Callable[[str], List[int]] | None = None, callback_manager: BaseCallbackManager | None = None, rate_limiter: BaseRateLimiter | None = None, disable_streaming: bool | Literal['tool_calling'] = False, client: Any = None, async_client: Any = None, model: str = 'gpt-3.5-turbo', temperature: float = 0.7, model_kwargs: Dict[str, Any] = None, api_key: SecretStr | None = None, base_url: str | None = None, organization: str | None = None, openai_proxy: str | None = None, timeout: float | Tuple[float, float] | Any | None = None, max_retries: int = 2, streaming: bool = False, n: int = 1, max_tokens: int | None = None, tiktoken_model_name: str | None = None, default_headers: Mapping[str, str] | None = None, default_query: Mapping[str, object] | None = None, http_client: Any | None = None, http_async_client: Any | None = None, stop_sequences: List[str] | str | None = None, extra_body: Mapping[str, Any] | None = None, stream_usage: bool = False, user_id: str | None = None)

Bases: ChatOpenAI

cache: BaseCache | bool | None

Whether to cache the response.

• If true, will use the global cache.

• If false, will not use a cache

• If None, will use the global cache if it’s set, otherwise no cache.

• If instance of BaseCache, will use the provided cache.

Caching is not currently supported for streaming methods of models.

callback_manager: BaseCallbackManager | None

callbacks: Callbacks

Callbacks to add to the run trace.

custom_get_token_ids: Callable[[str], List[int]] | None

Optional encoder to use for counting tokens.

default_headers: Mapping[str, str] | None

default_query: Mapping[str, object] | None

disable_streaming: bool | Literal['tool_calling']

Whether to disable streaming for this model.

If streaming is bypassed, then stream()/astream() will defer to invoke()/ainvoke().

• If True, will always bypass streaming case.

• If “tool_calling”, will bypass streaming case only when the model is called with a tools keyword argument.

• If False (default), will always use streaming case if available.

extra_body: Mapping[str, Any] | None

Optional additional JSON properties to include in the request parameters when making requests to OpenAI compatible APIs, such as vLLM.

http_async_client: Any | None

Optional httpx.AsyncClient. Only used for async invocations. Must specify http_client as well if you’d like a custom client for sync invocations.

http_client: Any | None

Optional httpx.Client. Only used for sync invocations. Must specify http_async_client as well if you’d like a custom client for async invocations.

max_retries: int

Maximum number of retries to make when generating.

max_tokens: int | None

Maximum number of tokens to generate.

metadata: Dict[str, Any] | None

Metadata to add to the run trace.

model_kwargs: Dict[str, Any]

Holds any model parameters valid for create call not explicitly specified.

model_name: str

Model name to use.

n: int

Number of chat completions to generate for each prompt.

openai_api_base: str | None

Base URL path for API requests, leave blank if not using a proxy or service emulator.

openai_api_key: SecretStr | None

Automatically inferred from env var OPENAI_API_KEY if not provided.

openai_organization: str | None

Automatically inferred from env var OPENAI_ORG_ID if not provided.

openai_proxy: str | None

rate_limiter: BaseRateLimiter | None

An optional rate limiter to use for limiting the number of requests.

request_timeout: float | Tuple[float, float] | Any | None

Timeout for requests to OpenAI completion API. Can be float, httpx.Timeout or None.

stop: List[str] | str | None

Default stop sequences.

stream_usage: bool

Whether to include usage metadata in streaming output. If True, additional message chunks will be generated during the stream including usage metadata.

streaming: bool

Whether to stream the results or not.

tags: List[str] | None

Tags to add to the run trace.

temperature: float

What sampling temperature to use.

tiktoken_model_name: str | None

The model name to pass to tiktoken when using this class. Tiktoken is used to count the number of tokens in documents to constrain them to be under a certain limit. By default, when set to None, this will be the same as the embedding model name. However, there are some cases where you may want to use this Embedding class with a model name not supported by tiktoken. This can include when using Azure embeddings or when using one of the many model providers that expose an OpenAI-like API but with different models. In those cases, in order to avoid erroring when tiktoken is called, you can specify a model name to use here.

user_id: str | None

verbose: bool

Whether to print out response text.