| |
- gen_ai_hub.proxy.langchain.openai.ProxyOpenAI(gen_ai_hub.proxy.langchain.base.BaseAuth)
-
- gen_ai_hub.proxy.langchain.openai.ChatOpenAI(gen_ai_hub.proxy.langchain.openai.ProxyOpenAI, langchain_openai.chat_models.base.ChatOpenAI)
- gen_ai_hub.proxy.langchain.openai.OpenAI(gen_ai_hub.proxy.langchain.openai.ProxyOpenAI, langchain_openai.llms.base.OpenAI)
- gen_ai_hub.proxy.langchain.openai.OpenAIEmbeddings(gen_ai_hub.proxy.langchain.openai.ProxyOpenAI, langchain_openai.embeddings.base.OpenAIEmbeddings)
- langchain_openai.chat_models.base.ChatOpenAI(langchain_core.language_models.chat_models.BaseChatModel)
-
- gen_ai_hub.proxy.langchain.openai.ChatOpenAI(gen_ai_hub.proxy.langchain.openai.ProxyOpenAI, langchain_openai.chat_models.base.ChatOpenAI)
- langchain_openai.embeddings.base.OpenAIEmbeddings(pydantic.v1.main.BaseModel, langchain_core.embeddings.Embeddings)
-
- gen_ai_hub.proxy.langchain.openai.OpenAIEmbeddings(gen_ai_hub.proxy.langchain.openai.ProxyOpenAI, langchain_openai.embeddings.base.OpenAIEmbeddings)
- langchain_openai.llms.base.OpenAI(langchain_openai.llms.base.BaseOpenAI)
-
- gen_ai_hub.proxy.langchain.openai.OpenAI(gen_ai_hub.proxy.langchain.openai.ProxyOpenAI, langchain_openai.llms.base.OpenAI)
class ChatOpenAI(ProxyOpenAI, langchain_openai.chat_models.base.ChatOpenAI) |
|
ChatOpenAI(*args, name: Optional[str] = None, cache: Optional[bool] = None, verbose: bool = None, callbacks: Union[List[langchain_core.callbacks.base.BaseCallbackHandler], langchain_core.callbacks.base.BaseCallbackManager, NoneType] = None, callback_manager: Optional[langchain_core.callbacks.base.BaseCallbackManager] = None, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, client: Any = None, async_client: Any = None, model_name: Optional[str] = None, temperature: float = 0.7, model_kwargs: Dict[str, Any] = None, api_key: Optional[str] = None, base_url: Optional[str] = None, organization: Optional[str] = None, openai_proxy: Optional[str] = None, timeout: Union[float, Tuple[float, float], Any, NoneType] = None, max_retries: int = 2, streaming: bool = False, n: int = 1, max_tokens: Optional[int] = None, tiktoken_model_name: Optional[str] = None, default_headers: Optional[Mapping[str, str]] = None, default_query: Optional[Mapping[str, object]] = None, http_client: Optional[Any] = None, proxy_client: Optional[Any] = None, deployment_id: Optional[str] = None, config_name: Optional[str] = None, config_id: Optional[str] = None, proxy_model_name: Optional[str] = None, api_version: Optional[str] = None) -> None
|
|
- Method resolution order:
- ChatOpenAI
- ProxyOpenAI
- gen_ai_hub.proxy.langchain.base.BaseAuth
- langchain_openai.chat_models.base.ChatOpenAI
- langchain_core.language_models.chat_models.BaseChatModel
- langchain_core.language_models.base.BaseLanguageModel
- langchain_core.runnables.base.RunnableSerializable
- langchain_core.load.serializable.Serializable
- pydantic.v1.main.BaseModel
- pydantic.v1.utils.Representation
- langchain_core.runnables.base.Runnable
- typing.Generic
- abc.ABC
- builtins.object
Methods defined here:
- __init__(self, *args, **kwargs)
- Create a new model by parsing and validating input data from keyword arguments.
Raises ValidationError if the input data cannot be parsed to form a valid model.
Class methods defined here:
- validate_environment(values: Dict) -> Dict from pydantic.v1.main.ModelMetaclass
- Validate that api key and python package exists in environment.
Static methods defined here:
- __json_encoder__ = pydantic_encoder(obj: Any) -> Any
- __new__(cls, **data: Any)
- Initialize the OpenAI object.
:param data: Additional data to initialize the object
:type data: Any
:return: The initialized OpenAI object
:rtype: OpenAIBase
Data and other attributes defined here:
- __abstractmethods__ = frozenset()
- __annotations__ = {'model_name': typing.Optional[str], 'openai_api_version': typing.Optional[str]}
- __class_vars__ = set()
- __config__ = <class 'pydantic.v1.config.Config'>
- __custom_root_type__ = False
- __exclude_fields__ = {'async_client': True, 'callback_manager': True, 'callbacks': True, 'client': True, 'metadata': True, 'tags': True}
- __fields__ = {'async_client': ModelField(name='async_client', type=Optional[Any], required=False, default=None), 'cache': ModelField(name='cache', type=Optional[bool], required=False, default=None), 'callback_manager': ModelField(name='callback_manager', type=Optiona...seCallbackManager], required=False, default=None), 'callbacks': ModelField(name='callbacks', type=Union[List[lan...Manager, NoneType], required=False, default=None), 'client': ModelField(name='client', type=Optional[Any], required=False, default=None), 'config_id': ModelField(name='config_id', type=Optional[str], required=False, default=None), 'config_name': ModelField(name='config_name', type=Optional[str], required=False, default=None), 'default_headers': ModelField(name='default_headers', type=Optional[Mapping[str, str]], required=False, default=None), 'default_query': ModelField(name='default_query', type=Optional[Mapping[str, object]], required=False, default=None), 'deployment_id': ModelField(name='deployment_id', type=Optional[str], required=False, default=None), ...}
- __hash__ = None
- __include_fields__ = None
- __parameters__ = ()
- __post_root_validators__ = [(False, <function BaseChatModel.raise_deprecation>), (False, <function ChatOpenAI.validate_environment>)]
- __pre_root_validators__ = [<function ChatOpenAI.build_extra>]
- __private_attributes__ = {'_lc_kwargs': ModelPrivateAttr(default=PydanticUndefined, default_factory=<class 'dict'>)}
- __schema_cache__ = {}
- __signature__ = <Signature (*args, name: Optional[str] = None, c...None, api_version: Optional[str] = None) -> None>
- __validators__ = {}
Class methods inherited from ProxyOpenAI:
- validate_clients(values: Dict) -> Dict from pydantic.v1.main.ModelMetaclass
Methods inherited from langchain_openai.chat_models.base.ChatOpenAI:
- bind_functions(self, functions: 'Sequence[Union[Dict[str, Any], Type[BaseModel], Callable, BaseTool]]', function_call: "Optional[Union[_FunctionCall, str, Literal['auto', 'none']]]" = None, **kwargs: 'Any') -> 'Runnable[LanguageModelInput, BaseMessage]'
- Bind functions (and other objects) to this chat model.
Assumes model is compatible with OpenAI function-calling API.
NOTE: Using bind_tools is recommended instead, as the `functions` and
`function_call` request parameters are officially marked as deprecated by
OpenAI.
Args:
functions: A list of function definitions to bind to this chat model.
Can be a dictionary, pydantic model, or callable. Pydantic
models and callables will be automatically converted to
their schema dictionary representation.
function_call: Which function to require the model to call.
Must be the name of the single provided function or
"auto" to automatically determine which function to call
(if any).
kwargs: Any additional parameters to pass to the
:class:`~langchain.runnable.Runnable` constructor.
- bind_tools(self, tools: 'Sequence[Union[Dict[str, Any], Type[BaseModel], Callable, BaseTool]]', *, tool_choice: "Optional[Union[dict, str, Literal['auto', 'none']]]" = None, **kwargs: 'Any') -> 'Runnable[LanguageModelInput, BaseMessage]'
- Bind tool-like objects to this chat model.
Assumes model is compatible with OpenAI tool-calling API.
Args:
tools: A list of tool definitions to bind to this chat model.
Can be a dictionary, pydantic model, callable, or BaseTool. Pydantic
models, callables, and BaseTools will be automatically converted to
their schema dictionary representation.
tool_choice: Which tool to require the model to call.
Must be the name of the single provided function or
"auto" to automatically determine which function to call
(if any), or a dict of the form:
{"type": "function", "function": {"name": <<tool_name>>}}.
kwargs: Any additional parameters to pass to the
:class:`~langchain.runnable.Runnable` constructor.
- get_num_tokens_from_messages(self, messages: 'List[BaseMessage]') -> 'int'
- Calculate num tokens for gpt-3.5-turbo and gpt-4 with tiktoken package.
Official documentation: https://github.com/openai/openai-cookbook/blob/
main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb
- get_token_ids(self, text: 'str') -> 'List[int]'
- Get the tokens present in the text with tiktoken package.
Class methods inherited from langchain_openai.chat_models.base.ChatOpenAI:
- build_extra(values: 'Dict[str, Any]') -> 'Dict[str, Any]' from pydantic.v1.main.ModelMetaclass
- Build extra kwargs from additional params that were passed in.
- get_lc_namespace() -> 'List[str]' from pydantic.v1.main.ModelMetaclass
- Get the namespace of the langchain object.
- is_lc_serializable() -> 'bool' from pydantic.v1.main.ModelMetaclass
- Return whether this model can be serialized by Langchain.
Readonly properties inherited from langchain_openai.chat_models.base.ChatOpenAI:
- lc_attributes
- List of attribute names that should be included in the serialized kwargs.
These attributes must be accepted by the constructor.
- lc_secrets
- A map of constructor argument names to secret ids.
For example,
{"openai_api_key": "OPENAI_API_KEY"}
Data and other attributes inherited from langchain_openai.chat_models.base.ChatOpenAI:
- Config = <class 'langchain_openai.chat_models.base.ChatOpenAI.Config'>
- Configuration for this pydantic object.
Methods inherited from langchain_core.language_models.chat_models.BaseChatModel:
- __call__(self, messages: 'List[BaseMessage]', stop: 'Optional[List[str]]' = None, callbacks: 'Callbacks' = None, **kwargs: 'Any') -> 'BaseMessage'
- [*Deprecated*][*Deprecated*]
Notes
-----
.. deprecated:: 0.1.7
Use invoke instead.
- async agenerate(self, messages: 'List[List[BaseMessage]]', stop: 'Optional[List[str]]' = None, callbacks: 'Callbacks' = None, *, tags: 'Optional[List[str]]' = None, metadata: 'Optional[Dict[str, Any]]' = None, run_name: 'Optional[str]' = None, **kwargs: 'Any') -> 'LLMResult'
- Asynchronously pass a sequence of prompts to a model and return generations.
This method should make use of batched calls for models that expose a batched
API.
Use this method when you want to:
1. take advantage of batched calls,
2. need more output from the model than just the top generated value,
3. are building chains that are agnostic to the underlying language model
type (e.g., pure text completion models vs chat models).
Args:
messages: List of list of messages.
stop: Stop words to use when generating. Model output is cut off at the
first occurrence of any of these substrings.
callbacks: Callbacks to pass through. Used for executing additional
functionality, such as logging or streaming, throughout generation.
**kwargs: Arbitrary additional keyword arguments. These are usually passed
to the model provider API call.
Returns:
An LLMResult, which contains a list of candidate Generations for each input
prompt and additional model provider-specific output.
- async agenerate_prompt(self, prompts: 'List[PromptValue]', stop: 'Optional[List[str]]' = None, callbacks: 'Callbacks' = None, **kwargs: 'Any') -> 'LLMResult'
- Asynchronously pass a sequence of prompts and return model generations.
This method should make use of batched calls for models that expose a batched
API.
Use this method when you want to:
1. take advantage of batched calls,
2. need more output from the model than just the top generated value,
3. are building chains that are agnostic to the underlying language model
type (e.g., pure text completion models vs chat models).
Args:
prompts: List of PromptValues. A PromptValue is an object that can be
converted to match the format of any language model (string for pure
text generation models and BaseMessages for chat models).
stop: Stop words to use when generating. Model output is cut off at the
first occurrence of any of these substrings.
callbacks: Callbacks to pass through. Used for executing additional
functionality, such as logging or streaming, throughout generation.
**kwargs: Arbitrary additional keyword arguments. These are usually passed
to the model provider API call.
Returns:
An LLMResult, which contains a list of candidate Generations for each input
prompt and additional model provider-specific output.
- async ainvoke(self, input: 'LanguageModelInput', config: 'Optional[RunnableConfig]' = None, *, stop: 'Optional[List[str]]' = None, **kwargs: 'Any') -> 'BaseMessage'
- Default implementation of ainvoke, calls invoke from a thread.
The default implementation allows usage of async code even if
the runnable did not implement a native async version of invoke.
Subclasses should override this method if they can run asynchronously.
- async apredict(self, text: 'str', *, stop: 'Optional[Sequence[str]]' = None, **kwargs: 'Any') -> 'str'
- [*Deprecated*][*Deprecated*]
Notes
-----
.. deprecated:: 0.1.7
Use ainvoke instead.
- async apredict_messages(self, messages: 'List[BaseMessage]', *, stop: 'Optional[Sequence[str]]' = None, **kwargs: 'Any') -> 'BaseMessage'
- [*Deprecated*][*Deprecated*]
Notes
-----
.. deprecated:: 0.1.7
Use ainvoke instead.
- async astream(self, input: 'LanguageModelInput', config: 'Optional[RunnableConfig]' = None, *, stop: 'Optional[List[str]]' = None, **kwargs: 'Any') -> 'AsyncIterator[BaseMessageChunk]'
- Default implementation of astream, which calls ainvoke.
Subclasses should override this method if they support streaming output.
- call_as_llm(self, message: 'str', stop: 'Optional[List[str]]' = None, **kwargs: 'Any') -> 'str'
- [*Deprecated*][*Deprecated*]
Notes
-----
.. deprecated:: 0.1.7
Use invoke instead.
- dict(self, **kwargs: 'Any') -> 'Dict'
- Return a dictionary of the LLM.
- generate(self, messages: 'List[List[BaseMessage]]', stop: 'Optional[List[str]]' = None, callbacks: 'Callbacks' = None, *, tags: 'Optional[List[str]]' = None, metadata: 'Optional[Dict[str, Any]]' = None, run_name: 'Optional[str]' = None, **kwargs: 'Any') -> 'LLMResult'
- Pass a sequence of prompts to the model and return model generations.
This method should make use of batched calls for models that expose a batched
API.
Use this method when you want to:
1. take advantage of batched calls,
2. need more output from the model than just the top generated value,
3. are building chains that are agnostic to the underlying language model
type (e.g., pure text completion models vs chat models).
Args:
messages: List of list of messages.
stop: Stop words to use when generating. Model output is cut off at the
first occurrence of any of these substrings.
callbacks: Callbacks to pass through. Used for executing additional
functionality, such as logging or streaming, throughout generation.
**kwargs: Arbitrary additional keyword arguments. These are usually passed
to the model provider API call.
Returns:
An LLMResult, which contains a list of candidate Generations for each input
prompt and additional model provider-specific output.
- generate_prompt(self, prompts: 'List[PromptValue]', stop: 'Optional[List[str]]' = None, callbacks: 'Callbacks' = None, **kwargs: 'Any') -> 'LLMResult'
- Pass a sequence of prompts to the model and return model generations.
This method should make use of batched calls for models that expose a batched
API.
Use this method when you want to:
1. take advantage of batched calls,
2. need more output from the model than just the top generated value,
3. are building chains that are agnostic to the underlying language model
type (e.g., pure text completion models vs chat models).
Args:
prompts: List of PromptValues. A PromptValue is an object that can be
converted to match the format of any language model (string for pure
text generation models and BaseMessages for chat models).
stop: Stop words to use when generating. Model output is cut off at the
first occurrence of any of these substrings.
callbacks: Callbacks to pass through. Used for executing additional
functionality, such as logging or streaming, throughout generation.
**kwargs: Arbitrary additional keyword arguments. These are usually passed
to the model provider API call.
Returns:
An LLMResult, which contains a list of candidate Generations for each input
prompt and additional model provider-specific output.
- invoke(self, input: 'LanguageModelInput', config: 'Optional[RunnableConfig]' = None, *, stop: 'Optional[List[str]]' = None, **kwargs: 'Any') -> 'BaseMessage'
- Transform a single input into an output. Override to implement.
Args:
input: The input to the runnable.
config: A config to use when invoking the runnable.
The config supports standard keys like 'tags', 'metadata' for tracing
purposes, 'max_concurrency' for controlling how much work to do
in parallel, and other keys. Please refer to the RunnableConfig
for more details.
Returns:
The output of the runnable.
- predict(self, text: 'str', *, stop: 'Optional[Sequence[str]]' = None, **kwargs: 'Any') -> 'str'
- [*Deprecated*][*Deprecated*]
Notes
-----
.. deprecated:: 0.1.7
Use invoke instead.
- predict_messages(self, messages: 'List[BaseMessage]', *, stop: 'Optional[Sequence[str]]' = None, **kwargs: 'Any') -> 'BaseMessage'
- [*Deprecated*][*Deprecated*]
Notes
-----
.. deprecated:: 0.1.7
Use invoke instead.
- stream(self, input: 'LanguageModelInput', config: 'Optional[RunnableConfig]' = None, *, stop: 'Optional[List[str]]' = None, **kwargs: 'Any') -> 'Iterator[BaseMessageChunk]'
- Default implementation of stream, which calls invoke.
Subclasses should override this method if they support streaming output.
Class methods inherited from langchain_core.language_models.chat_models.BaseChatModel:
- raise_deprecation(values: 'Dict') -> 'Dict' from pydantic.v1.main.ModelMetaclass
- Raise deprecation warning if callback_manager is used.
Readonly properties inherited from langchain_core.language_models.chat_models.BaseChatModel:
- OutputType
- Get the output type for this runnable.
Data and other attributes inherited from langchain_core.language_models.chat_models.BaseChatModel:
- __orig_bases__ = (langchain_core.language_models.base.BaseLanguageModel[langchain_core.messages.base.BaseMessage], <class 'abc.ABC'>)
Methods inherited from langchain_core.language_models.base.BaseLanguageModel:
- get_num_tokens(self, text: 'str') -> 'int'
- Get the number of tokens present in the text.
Useful for checking if an input will fit in a model's context window.
Args:
text: The string input to tokenize.
Returns:
The integer number of tokens in the text.
Readonly properties inherited from langchain_core.language_models.base.BaseLanguageModel:
- InputType
- Get the input type for this runnable.
Methods inherited from langchain_core.runnables.base.RunnableSerializable:
- configurable_alternatives(self, which: 'ConfigurableField', *, default_key: 'str' = 'default', prefix_keys: 'bool' = False, **kwargs: 'Union[Runnable[Input, Output], Callable[[], Runnable[Input, Output]]]') -> 'RunnableSerializable[Input, Output]'
- configurable_fields(self, **kwargs: 'AnyConfigurableField') -> 'RunnableSerializable[Input, Output]'
Data descriptors inherited from langchain_core.runnables.base.RunnableSerializable:
- __weakref__
- list of weak references to the object (if defined)
Methods inherited from langchain_core.load.serializable.Serializable:
- __repr_args__(self) -> Any
- Returns the attributes to show in __str__, __repr__, and __pretty__ this is generally overridden.
Can either return:
* name - value pairs, e.g.: `[('foo_name', 'foo'), ('bar_name', ['b', 'a', 'r'])]`
* or, just values, e.g.: `[(None, 'foo'), (None, ['b', 'a', 'r'])]`
- to_json(self) -> Union[langchain_core.load.serializable.SerializedConstructor, langchain_core.load.serializable.SerializedNotImplemented]
- to_json_not_implemented(self) -> langchain_core.load.serializable.SerializedNotImplemented
Class methods inherited from langchain_core.load.serializable.Serializable:
- lc_id() -> List[str] from pydantic.v1.main.ModelMetaclass
- A unique identifier for this class for serialization purposes.
The unique identifier is a list of strings that describes the path
to the object.
Methods inherited from pydantic.v1.main.BaseModel:
- __eq__(self, other: Any) -> bool
- Return self==value.
- __getstate__(self) -> 'DictAny'
- __iter__(self) -> 'TupleGenerator'
- so `dict(model)` works
- __setattr__(self, name, value)
- Implement setattr(self, name, value).
- __setstate__(self, state: 'DictAny') -> None
- copy(self: 'Model', *, include: Union[ForwardRef('AbstractSetIntStr'), ForwardRef('MappingIntStrAny'), NoneType] = None, exclude: Union[ForwardRef('AbstractSetIntStr'), ForwardRef('MappingIntStrAny'), NoneType] = None, update: Optional[ForwardRef('DictStrAny')] = None, deep: bool = False) -> 'Model'
- Duplicate a model, optionally choose which fields to include, exclude and change.
:param include: fields to include in new model
:param exclude: fields to exclude from new model, as with values this takes precedence over include
:param update: values to change/add in the new model. Note: the data is not validated before creating
the new model: you should trust this data
:param deep: set to `True` to make a deep copy of the model
:return: new model instance
- json(self, *, include: Union[ForwardRef('AbstractSetIntStr'), ForwardRef('MappingIntStrAny'), NoneType] = None, exclude: Union[ForwardRef('AbstractSetIntStr'), ForwardRef('MappingIntStrAny'), NoneType] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) -> str
- Generate a JSON representation of the model, `include` and `exclude` arguments as per `dict()`.
`encoder` is an optional function to supply as `default` to json.dumps(), other arguments as per `json.dumps()`.
Class methods inherited from pydantic.v1.main.BaseModel:
- __get_validators__() -> 'CallableGenerator' from pydantic.v1.main.ModelMetaclass
- __try_update_forward_refs__(**localns: Any) -> None from pydantic.v1.main.ModelMetaclass
- Same as update_forward_refs but will not raise exception
when forward references are not defined.
- construct(_fields_set: Optional[ForwardRef('SetStr')] = None, **values: Any) -> 'Model' from pydantic.v1.main.ModelMetaclass
- Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data.
Default values are respected, but no other validation is performed.
Behaves as if `Config.extra = 'allow'` was set since it adds all passed values
- from_orm(obj: Any) -> 'Model' from pydantic.v1.main.ModelMetaclass
- parse_file(path: Union[str, pathlib.Path], *, content_type: str = None, encoding: str = 'utf8', proto: pydantic.v1.parse.Protocol = None, allow_pickle: bool = False) -> 'Model' from pydantic.v1.main.ModelMetaclass
- parse_obj(obj: Any) -> 'Model' from pydantic.v1.main.ModelMetaclass
- parse_raw(b: Union[str, bytes], *, content_type: str = None, encoding: str = 'utf8', proto: pydantic.v1.parse.Protocol = None, allow_pickle: bool = False) -> 'Model' from pydantic.v1.main.ModelMetaclass
- schema(by_alias: bool = True, ref_template: str = '#/definitions/{model}') -> 'DictStrAny' from pydantic.v1.main.ModelMetaclass
- schema_json(*, by_alias: bool = True, ref_template: str = '#/definitions/{model}', **dumps_kwargs: Any) -> str from pydantic.v1.main.ModelMetaclass
- update_forward_refs(**localns: Any) -> None from pydantic.v1.main.ModelMetaclass
- Try to update ForwardRefs on fields based on this Model, globalns and localns.
- validate(value: Any) -> 'Model' from pydantic.v1.main.ModelMetaclass
Data descriptors inherited from pydantic.v1.main.BaseModel:
- __dict__
- dictionary for instance variables (if defined)
- __fields_set__
Methods inherited from pydantic.v1.utils.Representation:
- __pretty__(self, fmt: Callable[[Any], Any], **kwargs: Any) -> Generator[Any, NoneType, NoneType]
- Used by devtools (https://python-devtools.helpmanual.io/) to provide a human readable representations of objects
- __repr__(self) -> str
- Return repr(self).
- __repr_name__(self) -> str
- Name of the instance's class, used in __repr__.
- __repr_str__(self, join_str: str) -> str
- __rich_repr__(self) -> 'RichReprResult'
- Get fields for Rich library
- __str__(self) -> str
- Return str(self).
Methods inherited from langchain_core.runnables.base.Runnable:
- __or__(self, other: 'Union[Runnable[Any, Other], Callable[[Any], Other], Callable[[Iterator[Any]], Iterator[Other]], Mapping[str, Union[Runnable[Any, Other], Callable[[Any], Other], Any]]]') -> 'RunnableSerializable[Input, Other]'
- Compose this runnable with another object to create a RunnableSequence.
- __ror__(self, other: 'Union[Runnable[Other, Any], Callable[[Other], Any], Callable[[Iterator[Other]], Iterator[Any]], Mapping[str, Union[Runnable[Other, Any], Callable[[Other], Any], Any]]]') -> 'RunnableSerializable[Other, Output]'
- Compose this runnable with another object to create a RunnableSequence.
- async abatch(self, inputs: 'List[Input]', config: 'Optional[Union[RunnableConfig, List[RunnableConfig]]]' = None, *, return_exceptions: 'bool' = False, **kwargs: 'Optional[Any]') -> 'List[Output]'
- Default implementation runs ainvoke in parallel using asyncio.gather.
The default implementation of batch works well for IO bound runnables.
Subclasses should override this method if they can batch more efficiently;
e.g., if the underlying runnable uses an API which supports a batch mode.
- assign(self, **kwargs: 'Union[Runnable[Dict[str, Any], Any], Callable[[Dict[str, Any]], Any], Mapping[str, Union[Runnable[Dict[str, Any], Any], Callable[[Dict[str, Any]], Any]]]]') -> 'RunnableSerializable[Any, Any]'
- Assigns new fields to the dict output of this runnable.
Returns a new runnable.
- astream_events(self, input: 'Any', config: 'Optional[RunnableConfig]' = None, *, version: "Literal['v1']", include_names: 'Optional[Sequence[str]]' = None, include_types: 'Optional[Sequence[str]]' = None, include_tags: 'Optional[Sequence[str]]' = None, exclude_names: 'Optional[Sequence[str]]' = None, exclude_types: 'Optional[Sequence[str]]' = None, exclude_tags: 'Optional[Sequence[str]]' = None, **kwargs: 'Any') -> 'AsyncIterator[StreamEvent]'
- [*Beta*] Generate a stream of events.
Use to create an iterator ove StreamEvents that provide real-time information
about the progress of the runnable, including StreamEvents from intermediate
results.
A StreamEvent is a dictionary with the following schema:
* ``event``: str - Event names are of the
format: on_[runnable_type]_(start|stream|end).
* ``name``: str - The name of the runnable that generated the event.
* ``run_id``: str - randomly generated ID associated with the given execution of
the runnable that emitted the event.
A child runnable that gets invoked as part of the execution of a
parent runnable is assigned its own unique ID.
* ``tags``: Optional[List[str]] - The tags of the runnable that generated
the event.
* ``metadata``: Optional[Dict[str, Any]] - The metadata of the runnable
that generated the event.
* ``data``: Dict[str, Any]
Below is a table that illustrates some evens that might be emitted by various
chains. Metadata fields have been omitted from the table for brevity.
Chain definitions have been included after the table.
| event | name | chunk | input | output |
|----------------------|------------------|---------------------------------|-----------------------------------------------|-------------------------------------------------|
| on_chat_model_start | [model name] | | {"messages": [[SystemMessage, HumanMessage]]} | |
| on_chat_model_stream | [model name] | AIMessageChunk(content="hello") | | |
| on_chat_model_end | [model name] | | {"messages": [[SystemMessage, HumanMessage]]} | {"generations": [...], "llm_output": None, ...} |
| on_llm_start | [model name] | | {'input': 'hello'} | |
| on_llm_stream | [model name] | 'Hello' | | |
| on_llm_end | [model name] | | 'Hello human!' |
| on_chain_start | format_docs | | | |
| on_chain_stream | format_docs | "hello world!, goodbye world!" | | |
| on_chain_end | format_docs | | [Document(...)] | "hello world!, goodbye world!" |
| on_tool_start | some_tool | | {"x": 1, "y": "2"} | |
| on_tool_stream | some_tool | {"x": 1, "y": "2"} | | |
| on_tool_end | some_tool | | | {"x": 1, "y": "2"} |
| on_retriever_start | [retriever name] | | {"query": "hello"} | |
| on_retriever_chunk | [retriever name] | {documents: [...]} | | |
| on_retriever_end | [retriever name] | | {"query": "hello"} | {documents: [...]} |
| on_prompt_start | [template_name] | | {"question": "hello"} | |
| on_prompt_end | [template_name] | | {"question": "hello"} | ChatPromptValue(messages: [SystemMessage, ...]) |
Here are declarations associated with the events shown above:
`format_docs`:
```python
def format_docs(docs: List[Document]) -> str:
'''Format the docs.'''
return ", ".join([doc.page_content for doc in docs])
format_docs = RunnableLambda(format_docs)
```
`some_tool`:
```python
@tool
def some_tool(x: int, y: str) -> dict:
'''Some_tool.'''
return {"x": x, "y": y}
```
`prompt`:
```python
template = ChatPromptTemplate.from_messages(
[("system", "You are Cat Agent 007"), ("human", "{question}")]
).with_config({"run_name": "my_template", "tags": ["my_template"]})
```
Example:
.. code-block:: python
from langchain_core.runnables import RunnableLambda
async def reverse(s: str) -> str:
return s[::-1]
chain = RunnableLambda(func=reverse)
events = [
event async for event in chain.astream_events("hello", version="v1")
]
# will produce the following events (run_id has been omitted for brevity):
[
{
"data": {"input": "hello"},
"event": "on_chain_start",
"metadata": {},
"name": "reverse",
"tags": [],
},
{
"data": {"chunk": "olleh"},
"event": "on_chain_stream",
"metadata": {},
"name": "reverse",
"tags": [],
},
{
"data": {"output": "olleh"},
"event": "on_chain_end",
"metadata": {},
"name": "reverse",
"tags": [],
},
]
Args:
input: The input to the runnable.
config: The config to use for the runnable.
version: The version of the schema to use.
Currently only version 1 is available.
No default will be assigned until the API is stabilized.
include_names: Only include events from runnables with matching names.
include_types: Only include events from runnables with matching types.
include_tags: Only include events from runnables with matching tags.
exclude_names: Exclude events from runnables with matching names.
exclude_types: Exclude events from runnables with matching types.
exclude_tags: Exclude events from runnables with matching tags.
kwargs: Additional keyword arguments to pass to the runnable.
These will be passed to astream_log as this implementation
of astream_events is built on top of astream_log.
Returns:
An async stream of StreamEvents.[*Beta*] Generate a stream of events.
Use to create an iterator ove StreamEvents that provide real-time information
about the progress of the runnable, including StreamEvents from intermediate
results.
A StreamEvent is a dictionary with the following schema:
* ``event``: str - Event names are of the
format: on_[runnable_type]_(start|stream|end).
* ``name``: str - The name of the runnable that generated the event.
* ``run_id``: str - randomly generated ID associated with the given execution of
the runnable that emitted the event.
A child runnable that gets invoked as part of the execution of a
parent runnable is assigned its own unique ID.
* ``tags``: Optional[List[str]] - The tags of the runnable that generated
the event.
* ``metadata``: Optional[Dict[str, Any]] - The metadata of the runnable
that generated the event.
* ``data``: Dict[str, Any]
Below is a table that illustrates some evens that might be emitted by various
chains. Metadata fields have been omitted from the table for brevity.
Chain definitions have been included after the table.
| event | name | chunk | input | output |
|----------------------|------------------|---------------------------------|-----------------------------------------------|-------------------------------------------------|
| on_chat_model_start | [model name] | | {"messages": [[SystemMessage, HumanMessage]]} | |
| on_chat_model_stream | [model name] | AIMessageChunk(content="hello") | | |
| on_chat_model_end | [model name] | | {"messages": [[SystemMessage, HumanMessage]]} | {"generations": [...], "llm_output": None, ...} |
| on_llm_start | [model name] | | {'input': 'hello'} | |
| on_llm_stream | [model name] | 'Hello' | | |
| on_llm_end | [model name] | | 'Hello human!' |
| on_chain_start | format_docs | | | |
| on_chain_stream | format_docs | "hello world!, goodbye world!" | | |
| on_chain_end | format_docs | | [Document(...)] | "hello world!, goodbye world!" |
| on_tool_start | some_tool | | {"x": 1, "y": "2"} | |
| on_tool_stream | some_tool | {"x": 1, "y": "2"} | | |
| on_tool_end | some_tool | | | {"x": 1, "y": "2"} |
| on_retriever_start | [retriever name] | | {"query": "hello"} | |
| on_retriever_chunk | [retriever name] | {documents: [...]} | | |
| on_retriever_end | [retriever name] | | {"query": "hello"} | {documents: [...]} |
| on_prompt_start | [template_name] | | {"question": "hello"} | |
| on_prompt_end | [template_name] | | {"question": "hello"} | ChatPromptValue(messages: [SystemMessage, ...]) |
Here are declarations associated with the events shown above:
`format_docs`:
```python
def format_docs(docs: List[Document]) -> str:
'''Format the docs.'''
return ", ".join([doc.page_content for doc in docs])
format_docs = RunnableLambda(format_docs)
```
`some_tool`:
```python
@tool
def some_tool(x: int, y: str) -> dict:
'''Some_tool.'''
return {"x": x, "y": y}
```
`prompt`:
```python
template = ChatPromptTemplate.from_messages(
[("system", "You are Cat Agent 007"), ("human", "{question}")]
).with_config({"run_name": "my_template", "tags": ["my_template"]})
```
Example:
.. code-block:: python
from langchain_core.runnables import RunnableLambda
async def reverse(s: str) -> str:
return s[::-1]
chain = RunnableLambda(func=reverse)
events = [
event async for event in chain.astream_events("hello", version="v1")
]
# will produce the following events (run_id has been omitted for brevity):
[
{
"data": {"input": "hello"},
"event": "on_chain_start",
"metadata": {},
"name": "reverse",
"tags": [],
},
{
"data": {"chunk": "olleh"},
"event": "on_chain_stream",
"metadata": {},
"name": "reverse",
"tags": [],
},
{
"data": {"output": "olleh"},
"event": "on_chain_end",
"metadata": {},
"name": "reverse",
"tags": [],
},
]
Args:
input: The input to the runnable.
config: The config to use for the runnable.
version: The version of the schema to use.
Currently only version 1 is available.
No default will be assigned until the API is stabilized.
include_names: Only include events from runnables with matching names.
include_types: Only include events from runnables with matching types.
include_tags: Only include events from runnables with matching tags.
exclude_names: Exclude events from runnables with matching names.
exclude_types: Exclude events from runnables with matching types.
exclude_tags: Exclude events from runnables with matching tags.
kwargs: Additional keyword arguments to pass to the runnable.
These will be passed to astream_log as this implementation
of astream_events is built on top of astream_log.
Returns:
An async stream of StreamEvents.
Notes
-----
.. beta::
This API is in beta and may change in the future.
- async astream_log(self, input: 'Any', config: 'Optional[RunnableConfig]' = None, *, diff: 'bool' = True, with_streamed_output_list: 'bool' = True, include_names: 'Optional[Sequence[str]]' = None, include_types: 'Optional[Sequence[str]]' = None, include_tags: 'Optional[Sequence[str]]' = None, exclude_names: 'Optional[Sequence[str]]' = None, exclude_types: 'Optional[Sequence[str]]' = None, exclude_tags: 'Optional[Sequence[str]]' = None, **kwargs: 'Any') -> 'Union[AsyncIterator[RunLogPatch], AsyncIterator[RunLog]]'
- Stream all output from a runnable, as reported to the callback system.
This includes all inner runs of LLMs, Retrievers, Tools, etc.
Output is streamed as Log objects, which include a list of
jsonpatch ops that describe how the state of the run has changed in each
step, and the final state of the run.
The jsonpatch ops can be applied in order to construct state.
Args:
input: The input to the runnable.
config: The config to use for the runnable.
diff: Whether to yield diffs between each step, or the current state.
with_streamed_output_list: Whether to yield the streamed_output list.
include_names: Only include logs with these names.
include_types: Only include logs with these types.
include_tags: Only include logs with these tags.
exclude_names: Exclude logs with these names.
exclude_types: Exclude logs with these types.
exclude_tags: Exclude logs with these tags.
- async atransform(self, input: 'AsyncIterator[Input]', config: 'Optional[RunnableConfig]' = None, **kwargs: 'Optional[Any]') -> 'AsyncIterator[Output]'
- Default implementation of atransform, which buffers input and calls astream.
Subclasses should override this method if they can start producing output while
input is still being generated.
- batch(self, inputs: 'List[Input]', config: 'Optional[Union[RunnableConfig, List[RunnableConfig]]]' = None, *, return_exceptions: 'bool' = False, **kwargs: 'Optional[Any]') -> 'List[Output]'
- Default implementation runs invoke in parallel using a thread pool executor.
The default implementation of batch works well for IO bound runnables.
Subclasses should override this method if they can batch more efficiently;
e.g., if the underlying runnable uses an API which supports a batch mode.
- bind(self, **kwargs: 'Any') -> 'Runnable[Input, Output]'
- Bind arguments to a Runnable, returning a new Runnable.
- config_schema(self, *, include: 'Optional[Sequence[str]]' = None) -> 'Type[BaseModel]'
- The type of config this runnable accepts specified as a pydantic model.
To mark a field as configurable, see the `configurable_fields`
and `configurable_alternatives` methods.
Args:
include: A list of fields to include in the config schema.
Returns:
A pydantic model that can be used to validate config.
- get_graph(self, config: 'Optional[RunnableConfig]' = None) -> 'Graph'
- Return a graph representation of this runnable.
- get_input_schema(self, config: 'Optional[RunnableConfig]' = None) -> 'Type[BaseModel]'
- Get a pydantic model that can be used to validate input to the runnable.
Runnables that leverage the configurable_fields and configurable_alternatives
methods will have a dynamic input schema that depends on which
configuration the runnable is invoked with.
This method allows to get an input schema for a specific configuration.
Args:
config: A config to use when generating the schema.
Returns:
A pydantic model that can be used to validate input.
- get_name(self, suffix: 'Optional[str]' = None, *, name: 'Optional[str]' = None) -> 'str'
- Get the name of the runnable.
- get_output_schema(self, config: 'Optional[RunnableConfig]' = None) -> 'Type[BaseModel]'
- Get a pydantic model that can be used to validate output to the runnable.
Runnables that leverage the configurable_fields and configurable_alternatives
methods will have a dynamic output schema that depends on which
configuration the runnable is invoked with.
This method allows to get an output schema for a specific configuration.
Args:
config: A config to use when generating the schema.
Returns:
A pydantic model that can be used to validate output.
- get_prompts(self, config: 'Optional[RunnableConfig]' = None) -> 'List[BasePromptTemplate]'
- map(self) -> 'Runnable[List[Input], List[Output]]'
- Return a new Runnable that maps a list of inputs to a list of outputs,
by calling invoke() with each input.
- pick(self, keys: 'Union[str, List[str]]') -> 'RunnableSerializable[Any, Any]'
- Pick keys from the dict output of this runnable.
Returns a new runnable.
- pipe(self, *others: 'Union[Runnable[Any, Other], Callable[[Any], Other]]', name: 'Optional[str]' = None) -> 'RunnableSerializable[Input, Other]'
- Compose this runnable with another object to create a RunnableSequence.
- transform(self, input: 'Iterator[Input]', config: 'Optional[RunnableConfig]' = None, **kwargs: 'Optional[Any]') -> 'Iterator[Output]'
- Default implementation of transform, which buffers input and then calls stream.
Subclasses should override this method if they can start producing output while
input is still being generated.
- with_config(self, config: 'Optional[RunnableConfig]' = None, **kwargs: 'Any') -> 'Runnable[Input, Output]'
- Bind config to a Runnable, returning a new Runnable.
- with_fallbacks(self, fallbacks: 'Sequence[Runnable[Input, Output]]', *, exceptions_to_handle: 'Tuple[Type[BaseException], ...]' = (<class 'Exception'>,), exception_key: 'Optional[str]' = None) -> 'RunnableWithFallbacksT[Input, Output]'
- Add fallbacks to a runnable, returning a new Runnable.
Args:
fallbacks: A sequence of runnables to try if the original runnable fails.
exceptions_to_handle: A tuple of exception types to handle.
exception_key: If string is specified then handled exceptions will be passed
to fallbacks as part of the input under the specified key. If None,
exceptions will not be passed to fallbacks. If used, the base runnable
and its fallbacks must accept a dictionary as input.
Returns:
A new Runnable that will try the original runnable, and then each
fallback in order, upon failures.
- with_listeners(self, *, on_start: 'Optional[Listener]' = None, on_end: 'Optional[Listener]' = None, on_error: 'Optional[Listener]' = None) -> 'Runnable[Input, Output]'
- Bind lifecycle listeners to a Runnable, returning a new Runnable.
on_start: Called before the runnable starts running, with the Run object.
on_end: Called after the runnable finishes running, with the Run object.
on_error: Called if the runnable throws an error, with the Run object.
The Run object contains information about the run, including its id,
type, input, output, error, start_time, end_time, and any tags or metadata
added to the run.
- with_retry(self, *, retry_if_exception_type: 'Tuple[Type[BaseException], ...]' = (<class 'Exception'>,), wait_exponential_jitter: 'bool' = True, stop_after_attempt: 'int' = 3) -> 'Runnable[Input, Output]'
- Create a new Runnable that retries the original runnable on exceptions.
Args:
retry_if_exception_type: A tuple of exception types to retry on
wait_exponential_jitter: Whether to add jitter to the wait time
between retries
stop_after_attempt: The maximum number of attempts to make before giving up
Returns:
A new Runnable that retries the original runnable on exceptions.
- with_types(self, *, input_type: 'Optional[Type[Input]]' = None, output_type: 'Optional[Type[Output]]' = None) -> 'Runnable[Input, Output]'
- Bind input and output types to a Runnable, returning a new Runnable.
Readonly properties inherited from langchain_core.runnables.base.Runnable:
- config_specs
- List configurable fields for this runnable.
- input_schema
- The type of input this runnable accepts specified as a pydantic model.
- output_schema
- The type of output this runnable produces specified as a pydantic model.
Data and other attributes inherited from langchain_core.runnables.base.Runnable:
- name = None
Class methods inherited from typing.Generic:
- __class_getitem__(params) from pydantic.v1.main.ModelMetaclass
- __init_subclass__(*args, **kwargs) from pydantic.v1.main.ModelMetaclass
- This method is called when a class is subclassed.
The default implementation does nothing. It may be
overridden to extend subclasses.
|
class OpenAI(ProxyOpenAI, langchain_openai.llms.base.OpenAI) |
|
OpenAI(*, name: Optional[str] = None, cache: Optional[bool] = None, verbose: bool = None, callbacks: Union[List[langchain_core.callbacks.base.BaseCallbackHandler], langchain_core.callbacks.base.BaseCallbackManager, NoneType] = None, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, callback_manager: Optional[langchain_core.callbacks.base.BaseCallbackManager] = None, client: Any = None, async_client: Any = None, model_name: Optional[str] = None, temperature: float = 0.7, max_tokens: int = 256, top_p: float = 1, frequency_penalty: float = 0, presence_penalty: float = 0, n: int = 1, best_of: int = 1, model_kwargs: Dict[str, Any] = None, api_key: Optional[str] = None, base_url: Optional[str] = None, organization: Optional[str] = None, openai_proxy: Optional[str] = None, batch_size: int = 20, timeout: Union[float, Tuple[float, float], Any, NoneType] = None, logit_bias: Optional[Dict[str, float]] = None, max_retries: int = 2, streaming: bool = False, allowed_special: Union[Literal['all'], AbstractSet[str]] = set(), disallowed_special: Union[Literal['all'], Collection[str]] = 'all', tiktoken_model_name: Optional[str] = None, default_headers: Optional[Mapping[str, str]] = None, default_query: Optional[Mapping[str, object]] = None, http_client: Optional[Any] = None, proxy_client: Optional[Any] = None, deployment_id: Optional[str] = None, config_name: Optional[str] = None, config_id: Optional[str] = None, proxy_model_name: Optional[str] = None, api_version: Optional[str] = None) -> None
|
|
- Method resolution order:
- OpenAI
- ProxyOpenAI
- gen_ai_hub.proxy.langchain.base.BaseAuth
- langchain_openai.llms.base.OpenAI
- langchain_openai.llms.base.BaseOpenAI
- langchain_core.language_models.llms.BaseLLM
- langchain_core.language_models.base.BaseLanguageModel
- langchain_core.runnables.base.RunnableSerializable
- langchain_core.load.serializable.Serializable
- pydantic.v1.main.BaseModel
- pydantic.v1.utils.Representation
- langchain_core.runnables.base.Runnable
- typing.Generic
- abc.ABC
- builtins.object
Class methods defined here:
- validate_environment(values: Dict) -> Dict from pydantic.v1.main.ModelMetaclass
- Validates the environment.
:param values: The input values
:type values: Dict
:return: The validated values
:rtype: Dict
Static methods defined here:
- __json_encoder__ = pydantic_encoder(obj: Any) -> Any
- __new__(cls, **data: Any)
- Initialize the OpenAI object.
Data and other attributes defined here:
- __abstractmethods__ = frozenset()
- __annotations__ = {'model_name': typing.Optional[str], 'openai_api_version': typing.Optional[str]}
- __class_vars__ = set()
- __config__ = <class 'pydantic.v1.config.Config'>
- __custom_root_type__ = False
- __exclude_fields__ = {'async_client': True, 'callback_manager': True, 'callbacks': True, 'client': True, 'metadata': True, 'tags': True}
- __fields__ = {'allowed_special': ModelField(name='allowed_special', type=Union[Li...AbstractSet[str]], required=False, default=set()), 'async_client': ModelField(name='async_client', type=Optional[Any], required=False, default=None), 'batch_size': ModelField(name='batch_size', type=int, required=False, default=20), 'best_of': ModelField(name='best_of', type=int, required=False, default=1), 'cache': ModelField(name='cache', type=Optional[bool], required=False, default=None), 'callback_manager': ModelField(name='callback_manager', type=Optiona...seCallbackManager], required=False, default=None), 'callbacks': ModelField(name='callbacks', type=Union[List[lan...Manager, NoneType], required=False, default=None), 'client': ModelField(name='client', type=Optional[Any], required=False, default=None), 'config_id': ModelField(name='config_id', type=Optional[str], required=False, default=None), 'config_name': ModelField(name='config_name', type=Optional[str], required=False, default=None), ...}
- __hash__ = None
- __include_fields__ = None
- __parameters__ = ()
- __post_root_validators__ = [(False, <function BaseLLM.raise_deprecation>), (False, <function OpenAI.validate_environment>)]
- __pre_root_validators__ = [<function BaseOpenAI.build_extra>]
- __private_attributes__ = {'_lc_kwargs': ModelPrivateAttr(default=PydanticUndefined, default_factory=<class 'dict'>)}
- __schema_cache__ = {}
- __signature__ = <Signature (*, name: Optional[str] = None, cache...None, api_version: Optional[str] = None) -> None>
- __validators__ = {'verbose': [<pydantic.v1.class_validators.Validator object>]}
Class methods inherited from ProxyOpenAI:
- validate_clients(values: Dict) -> Dict from pydantic.v1.main.ModelMetaclass
Class methods inherited from langchain_openai.llms.base.OpenAI:
- get_lc_namespace() -> 'List[str]' from pydantic.v1.main.ModelMetaclass
- Get the namespace of the langchain object.
- is_lc_serializable() -> 'bool' from pydantic.v1.main.ModelMetaclass
- Return whether this model can be serialized by Langchain.
Methods inherited from langchain_openai.llms.base.BaseOpenAI:
- create_llm_result(self, choices: 'Any', prompts: 'List[str]', params: 'Dict[str, Any]', token_usage: 'Dict[str, int]', *, system_fingerprint: 'Optional[str]' = None) -> 'LLMResult'
- Create the LLMResult from the choices and prompts.
- get_sub_prompts(self, params: 'Dict[str, Any]', prompts: 'List[str]', stop: 'Optional[List[str]]' = None) -> 'List[List[str]]'
- Get the sub prompts for llm call.
- get_token_ids(self, text: 'str') -> 'List[int]'
- Get the token IDs using the tiktoken package.
- max_tokens_for_prompt(self, prompt: 'str') -> 'int'
- Calculate the maximum number of tokens possible to generate for a prompt.
Args:
prompt: The prompt to pass into the model.
Returns:
The maximum number of tokens to generate for a prompt.
Example:
.. code-block:: python
max_tokens = openai.max_token_for_prompt("Tell me a joke.")
Class methods inherited from langchain_openai.llms.base.BaseOpenAI:
- build_extra(values: 'Dict[str, Any]') -> 'Dict[str, Any]' from pydantic.v1.main.ModelMetaclass
- Build extra kwargs from additional params that were passed in.
Static methods inherited from langchain_openai.llms.base.BaseOpenAI:
- modelname_to_contextsize(modelname: 'str') -> 'int'
- Calculate the maximum number of tokens possible to generate for a model.
Args:
modelname: The modelname we want to know the context size for.
Returns:
The maximum context size
Example:
.. code-block:: python
max_tokens = openai.modelname_to_contextsize("gpt-3.5-turbo-instruct")
Readonly properties inherited from langchain_openai.llms.base.BaseOpenAI:
- lc_attributes
- List of attribute names that should be included in the serialized kwargs.
These attributes must be accepted by the constructor.
- lc_secrets
- A map of constructor argument names to secret ids.
For example,
{"openai_api_key": "OPENAI_API_KEY"}
- max_context_size
- Get max context size for this model.
Data and other attributes inherited from langchain_openai.llms.base.BaseOpenAI:
- Config = <class 'langchain_openai.llms.base.BaseOpenAI.Config'>
- Configuration for this pydantic object.
Methods inherited from langchain_core.language_models.llms.BaseLLM:
- __call__(self, prompt: 'str', stop: 'Optional[List[str]]' = None, callbacks: 'Callbacks' = None, *, tags: 'Optional[List[str]]' = None, metadata: 'Optional[Dict[str, Any]]' = None, **kwargs: 'Any') -> 'str'
- [*Deprecated*] Check Cache and run the LLM on the given prompt and input.[*Deprecated*] Check Cache and run the LLM on the given prompt and input.
Notes
-----
.. deprecated:: 0.1.7
Use invoke instead.
- __str__(self) -> 'str'
- Get a string representation of the object for printing.
- async abatch(self, inputs: 'List[LanguageModelInput]', config: 'Optional[Union[RunnableConfig, List[RunnableConfig]]]' = None, *, return_exceptions: 'bool' = False, **kwargs: 'Any') -> 'List[str]'
- Default implementation runs ainvoke in parallel using asyncio.gather.
The default implementation of batch works well for IO bound runnables.
Subclasses should override this method if they can batch more efficiently;
e.g., if the underlying runnable uses an API which supports a batch mode.
- async agenerate(self, prompts: 'List[str]', stop: 'Optional[List[str]]' = None, callbacks: 'Optional[Union[Callbacks, List[Callbacks]]]' = None, *, tags: 'Optional[Union[List[str], List[List[str]]]]' = None, metadata: 'Optional[Union[Dict[str, Any], List[Dict[str, Any]]]]' = None, run_name: 'Optional[Union[str, List[str]]]' = None, **kwargs: 'Any') -> 'LLMResult'
- Asynchronously pass a sequence of prompts to a model and return generations.
This method should make use of batched calls for models that expose a batched
API.
Use this method when you want to:
1. take advantage of batched calls,
2. need more output from the model than just the top generated value,
3. are building chains that are agnostic to the underlying language model
type (e.g., pure text completion models vs chat models).
Args:
prompts: List of string prompts.
stop: Stop words to use when generating. Model output is cut off at the
first occurrence of any of these substrings.
callbacks: Callbacks to pass through. Used for executing additional
functionality, such as logging or streaming, throughout generation.
**kwargs: Arbitrary additional keyword arguments. These are usually passed
to the model provider API call.
Returns:
An LLMResult, which contains a list of candidate Generations for each input
prompt and additional model provider-specific output.
- async agenerate_prompt(self, prompts: 'List[PromptValue]', stop: 'Optional[List[str]]' = None, callbacks: 'Optional[Union[Callbacks, List[Callbacks]]]' = None, **kwargs: 'Any') -> 'LLMResult'
- Asynchronously pass a sequence of prompts and return model generations.
This method should make use of batched calls for models that expose a batched
API.
Use this method when you want to:
1. take advantage of batched calls,
2. need more output from the model than just the top generated value,
3. are building chains that are agnostic to the underlying language model
type (e.g., pure text completion models vs chat models).
Args:
prompts: List of PromptValues. A PromptValue is an object that can be
converted to match the format of any language model (string for pure
text generation models and BaseMessages for chat models).
stop: Stop words to use when generating. Model output is cut off at the
first occurrence of any of these substrings.
callbacks: Callbacks to pass through. Used for executing additional
functionality, such as logging or streaming, throughout generation.
**kwargs: Arbitrary additional keyword arguments. These are usually passed
to the model provider API call.
Returns:
An LLMResult, which contains a list of candidate Generations for each input
prompt and additional model provider-specific output.
- async ainvoke(self, input: 'LanguageModelInput', config: 'Optional[RunnableConfig]' = None, *, stop: 'Optional[List[str]]' = None, **kwargs: 'Any') -> 'str'
- Default implementation of ainvoke, calls invoke from a thread.
The default implementation allows usage of async code even if
the runnable did not implement a native async version of invoke.
Subclasses should override this method if they can run asynchronously.
- async apredict(self, text: 'str', *, stop: 'Optional[Sequence[str]]' = None, **kwargs: 'Any') -> 'str'
- [*Deprecated*][*Deprecated*]
Notes
-----
.. deprecated:: 0.1.7
Use ainvoke instead.
- async apredict_messages(self, messages: 'List[BaseMessage]', *, stop: 'Optional[Sequence[str]]' = None, **kwargs: 'Any') -> 'BaseMessage'
- [*Deprecated*][*Deprecated*]
Notes
-----
.. deprecated:: 0.1.7
Use ainvoke instead.
- async astream(self, input: 'LanguageModelInput', config: 'Optional[RunnableConfig]' = None, *, stop: 'Optional[List[str]]' = None, **kwargs: 'Any') -> 'AsyncIterator[str]'
- Default implementation of astream, which calls ainvoke.
Subclasses should override this method if they support streaming output.
- batch(self, inputs: 'List[LanguageModelInput]', config: 'Optional[Union[RunnableConfig, List[RunnableConfig]]]' = None, *, return_exceptions: 'bool' = False, **kwargs: 'Any') -> 'List[str]'
- Default implementation runs invoke in parallel using a thread pool executor.
The default implementation of batch works well for IO bound runnables.
Subclasses should override this method if they can batch more efficiently;
e.g., if the underlying runnable uses an API which supports a batch mode.
- dict(self, **kwargs: 'Any') -> 'Dict'
- Return a dictionary of the LLM.
- generate(self, prompts: 'List[str]', stop: 'Optional[List[str]]' = None, callbacks: 'Optional[Union[Callbacks, List[Callbacks]]]' = None, *, tags: 'Optional[Union[List[str], List[List[str]]]]' = None, metadata: 'Optional[Union[Dict[str, Any], List[Dict[str, Any]]]]' = None, run_name: 'Optional[Union[str, List[str]]]' = None, **kwargs: 'Any') -> 'LLMResult'
- Pass a sequence of prompts to a model and return generations.
This method should make use of batched calls for models that expose a batched
API.
Use this method when you want to:
1. take advantage of batched calls,
2. need more output from the model than just the top generated value,
3. are building chains that are agnostic to the underlying language model
type (e.g., pure text completion models vs chat models).
Args:
prompts: List of string prompts.
stop: Stop words to use when generating. Model output is cut off at the
first occurrence of any of these substrings.
callbacks: Callbacks to pass through. Used for executing additional
functionality, such as logging or streaming, throughout generation.
**kwargs: Arbitrary additional keyword arguments. These are usually passed
to the model provider API call.
Returns:
An LLMResult, which contains a list of candidate Generations for each input
prompt and additional model provider-specific output.
- generate_prompt(self, prompts: 'List[PromptValue]', stop: 'Optional[List[str]]' = None, callbacks: 'Optional[Union[Callbacks, List[Callbacks]]]' = None, **kwargs: 'Any') -> 'LLMResult'
- Pass a sequence of prompts to the model and return model generations.
This method should make use of batched calls for models that expose a batched
API.
Use this method when you want to:
1. take advantage of batched calls,
2. need more output from the model than just the top generated value,
3. are building chains that are agnostic to the underlying language model
type (e.g., pure text completion models vs chat models).
Args:
prompts: List of PromptValues. A PromptValue is an object that can be
converted to match the format of any language model (string for pure
text generation models and BaseMessages for chat models).
stop: Stop words to use when generating. Model output is cut off at the
first occurrence of any of these substrings.
callbacks: Callbacks to pass through. Used for executing additional
functionality, such as logging or streaming, throughout generation.
**kwargs: Arbitrary additional keyword arguments. These are usually passed
to the model provider API call.
Returns:
An LLMResult, which contains a list of candidate Generations for each input
prompt and additional model provider-specific output.
- invoke(self, input: 'LanguageModelInput', config: 'Optional[RunnableConfig]' = None, *, stop: 'Optional[List[str]]' = None, **kwargs: 'Any') -> 'str'
- Transform a single input into an output. Override to implement.
Args:
input: The input to the runnable.
config: A config to use when invoking the runnable.
The config supports standard keys like 'tags', 'metadata' for tracing
purposes, 'max_concurrency' for controlling how much work to do
in parallel, and other keys. Please refer to the RunnableConfig
for more details.
Returns:
The output of the runnable.
- predict(self, text: 'str', *, stop: 'Optional[Sequence[str]]' = None, **kwargs: 'Any') -> 'str'
- [*Deprecated*][*Deprecated*]
Notes
-----
.. deprecated:: 0.1.7
Use invoke instead.
- predict_messages(self, messages: 'List[BaseMessage]', *, stop: 'Optional[Sequence[str]]' = None, **kwargs: 'Any') -> 'BaseMessage'
- [*Deprecated*][*Deprecated*]
Notes
-----
.. deprecated:: 0.1.7
Use invoke instead.
- save(self, file_path: 'Union[Path, str]') -> 'None'
- Save the LLM.
Args:
file_path: Path to file to save the LLM to.
Example:
.. code-block:: python
llm.save(file_path="path/llm.yaml")
- stream(self, input: 'LanguageModelInput', config: 'Optional[RunnableConfig]' = None, *, stop: 'Optional[List[str]]' = None, **kwargs: 'Any') -> 'Iterator[str]'
- Default implementation of stream, which calls invoke.
Subclasses should override this method if they support streaming output.
Class methods inherited from langchain_core.language_models.llms.BaseLLM:
- raise_deprecation(values: 'Dict') -> 'Dict' from pydantic.v1.main.ModelMetaclass
- Raise deprecation warning if callback_manager is used.
- set_verbose(verbose: 'Optional[bool]') -> 'bool' from pydantic.v1.main.ModelMetaclass
- If verbose is None, set it.
This allows users to pass in None as verbose to access the global setting.
Readonly properties inherited from langchain_core.language_models.llms.BaseLLM:
- OutputType
- Get the input type for this runnable.
Data and other attributes inherited from langchain_core.language_models.llms.BaseLLM:
- __orig_bases__ = (langchain_core.language_models.base.BaseLanguageModel[str], <class 'abc.ABC'>)
Methods inherited from langchain_core.language_models.base.BaseLanguageModel:
- get_num_tokens(self, text: 'str') -> 'int'
- Get the number of tokens present in the text.
Useful for checking if an input will fit in a model's context window.
Args:
text: The string input to tokenize.
Returns:
The integer number of tokens in the text.
- get_num_tokens_from_messages(self, messages: 'List[BaseMessage]') -> 'int'
- Get the number of tokens in the messages.
Useful for checking if an input will fit in a model's context window.
Args:
messages: The message inputs to tokenize.
Returns:
The sum of the number of tokens across the messages.
Readonly properties inherited from langchain_core.language_models.base.BaseLanguageModel:
- InputType
- Get the input type for this runnable.
Methods inherited from langchain_core.runnables.base.RunnableSerializable:
- configurable_alternatives(self, which: 'ConfigurableField', *, default_key: 'str' = 'default', prefix_keys: 'bool' = False, **kwargs: 'Union[Runnable[Input, Output], Callable[[], Runnable[Input, Output]]]') -> 'RunnableSerializable[Input, Output]'
- configurable_fields(self, **kwargs: 'AnyConfigurableField') -> 'RunnableSerializable[Input, Output]'
Data descriptors inherited from langchain_core.runnables.base.RunnableSerializable:
- __weakref__
- list of weak references to the object (if defined)
Methods inherited from langchain_core.load.serializable.Serializable:
- __init__(self, **kwargs: Any) -> None
- Create a new model by parsing and validating input data from keyword arguments.
Raises ValidationError if the input data cannot be parsed to form a valid model.
- __repr_args__(self) -> Any
- Returns the attributes to show in __str__, __repr__, and __pretty__ this is generally overridden.
Can either return:
* name - value pairs, e.g.: `[('foo_name', 'foo'), ('bar_name', ['b', 'a', 'r'])]`
* or, just values, e.g.: `[(None, 'foo'), (None, ['b', 'a', 'r'])]`
- to_json(self) -> Union[langchain_core.load.serializable.SerializedConstructor, langchain_core.load.serializable.SerializedNotImplemented]
- to_json_not_implemented(self) -> langchain_core.load.serializable.SerializedNotImplemented
Class methods inherited from langchain_core.load.serializable.Serializable:
- lc_id() -> List[str] from pydantic.v1.main.ModelMetaclass
- A unique identifier for this class for serialization purposes.
The unique identifier is a list of strings that describes the path
to the object.
Methods inherited from pydantic.v1.main.BaseModel:
- __eq__(self, other: Any) -> bool
- Return self==value.
- __getstate__(self) -> 'DictAny'
- __iter__(self) -> 'TupleGenerator'
- so `dict(model)` works
- __setattr__(self, name, value)
- Implement setattr(self, name, value).
- __setstate__(self, state: 'DictAny') -> None
- copy(self: 'Model', *, include: Union[ForwardRef('AbstractSetIntStr'), ForwardRef('MappingIntStrAny'), NoneType] = None, exclude: Union[ForwardRef('AbstractSetIntStr'), ForwardRef('MappingIntStrAny'), NoneType] = None, update: Optional[ForwardRef('DictStrAny')] = None, deep: bool = False) -> 'Model'
- Duplicate a model, optionally choose which fields to include, exclude and change.
:param include: fields to include in new model
:param exclude: fields to exclude from new model, as with values this takes precedence over include
:param update: values to change/add in the new model. Note: the data is not validated before creating
the new model: you should trust this data
:param deep: set to `True` to make a deep copy of the model
:return: new model instance
- json(self, *, include: Union[ForwardRef('AbstractSetIntStr'), ForwardRef('MappingIntStrAny'), NoneType] = None, exclude: Union[ForwardRef('AbstractSetIntStr'), ForwardRef('MappingIntStrAny'), NoneType] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) -> str
- Generate a JSON representation of the model, `include` and `exclude` arguments as per `dict()`.
`encoder` is an optional function to supply as `default` to json.dumps(), other arguments as per `json.dumps()`.
Class methods inherited from pydantic.v1.main.BaseModel:
- __get_validators__() -> 'CallableGenerator' from pydantic.v1.main.ModelMetaclass
- __try_update_forward_refs__(**localns: Any) -> None from pydantic.v1.main.ModelMetaclass
- Same as update_forward_refs but will not raise exception
when forward references are not defined.
- construct(_fields_set: Optional[ForwardRef('SetStr')] = None, **values: Any) -> 'Model' from pydantic.v1.main.ModelMetaclass
- Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data.
Default values are respected, but no other validation is performed.
Behaves as if `Config.extra = 'allow'` was set since it adds all passed values
- from_orm(obj: Any) -> 'Model' from pydantic.v1.main.ModelMetaclass
- parse_file(path: Union[str, pathlib.Path], *, content_type: str = None, encoding: str = 'utf8', proto: pydantic.v1.parse.Protocol = None, allow_pickle: bool = False) -> 'Model' from pydantic.v1.main.ModelMetaclass
- parse_obj(obj: Any) -> 'Model' from pydantic.v1.main.ModelMetaclass
- parse_raw(b: Union[str, bytes], *, content_type: str = None, encoding: str = 'utf8', proto: pydantic.v1.parse.Protocol = None, allow_pickle: bool = False) -> 'Model' from pydantic.v1.main.ModelMetaclass
- schema(by_alias: bool = True, ref_template: str = '#/definitions/{model}') -> 'DictStrAny' from pydantic.v1.main.ModelMetaclass
- schema_json(*, by_alias: bool = True, ref_template: str = '#/definitions/{model}', **dumps_kwargs: Any) -> str from pydantic.v1.main.ModelMetaclass
- update_forward_refs(**localns: Any) -> None from pydantic.v1.main.ModelMetaclass
- Try to update ForwardRefs on fields based on this Model, globalns and localns.
- validate(value: Any) -> 'Model' from pydantic.v1.main.ModelMetaclass
Data descriptors inherited from pydantic.v1.main.BaseModel:
- __dict__
- dictionary for instance variables (if defined)
- __fields_set__
Methods inherited from pydantic.v1.utils.Representation:
- __pretty__(self, fmt: Callable[[Any], Any], **kwargs: Any) -> Generator[Any, NoneType, NoneType]
- Used by devtools (https://python-devtools.helpmanual.io/) to provide a human readable representations of objects
- __repr__(self) -> str
- Return repr(self).
- __repr_name__(self) -> str
- Name of the instance's class, used in __repr__.
- __repr_str__(self, join_str: str) -> str
- __rich_repr__(self) -> 'RichReprResult'
- Get fields for Rich library
Methods inherited from langchain_core.runnables.base.Runnable:
- __or__(self, other: 'Union[Runnable[Any, Other], Callable[[Any], Other], Callable[[Iterator[Any]], Iterator[Other]], Mapping[str, Union[Runnable[Any, Other], Callable[[Any], Other], Any]]]') -> 'RunnableSerializable[Input, Other]'
- Compose this runnable with another object to create a RunnableSequence.
- __ror__(self, other: 'Union[Runnable[Other, Any], Callable[[Other], Any], Callable[[Iterator[Other]], Iterator[Any]], Mapping[str, Union[Runnable[Other, Any], Callable[[Other], Any], Any]]]') -> 'RunnableSerializable[Other, Output]'
- Compose this runnable with another object to create a RunnableSequence.
- assign(self, **kwargs: 'Union[Runnable[Dict[str, Any], Any], Callable[[Dict[str, Any]], Any], Mapping[str, Union[Runnable[Dict[str, Any], Any], Callable[[Dict[str, Any]], Any]]]]') -> 'RunnableSerializable[Any, Any]'
- Assigns new fields to the dict output of this runnable.
Returns a new runnable.
- astream_events(self, input: 'Any', config: 'Optional[RunnableConfig]' = None, *, version: "Literal['v1']", include_names: 'Optional[Sequence[str]]' = None, include_types: 'Optional[Sequence[str]]' = None, include_tags: 'Optional[Sequence[str]]' = None, exclude_names: 'Optional[Sequence[str]]' = None, exclude_types: 'Optional[Sequence[str]]' = None, exclude_tags: 'Optional[Sequence[str]]' = None, **kwargs: 'Any') -> 'AsyncIterator[StreamEvent]'
- [*Beta*] Generate a stream of events.
Use to create an iterator ove StreamEvents that provide real-time information
about the progress of the runnable, including StreamEvents from intermediate
results.
A StreamEvent is a dictionary with the following schema:
* ``event``: str - Event names are of the
format: on_[runnable_type]_(start|stream|end).
* ``name``: str - The name of the runnable that generated the event.
* ``run_id``: str - randomly generated ID associated with the given execution of
the runnable that emitted the event.
A child runnable that gets invoked as part of the execution of a
parent runnable is assigned its own unique ID.
* ``tags``: Optional[List[str]] - The tags of the runnable that generated
the event.
* ``metadata``: Optional[Dict[str, Any]] - The metadata of the runnable
that generated the event.
* ``data``: Dict[str, Any]
Below is a table that illustrates some evens that might be emitted by various
chains. Metadata fields have been omitted from the table for brevity.
Chain definitions have been included after the table.
| event | name | chunk | input | output |
|----------------------|------------------|---------------------------------|-----------------------------------------------|-------------------------------------------------|
| on_chat_model_start | [model name] | | {"messages": [[SystemMessage, HumanMessage]]} | |
| on_chat_model_stream | [model name] | AIMessageChunk(content="hello") | | |
| on_chat_model_end | [model name] | | {"messages": [[SystemMessage, HumanMessage]]} | {"generations": [...], "llm_output": None, ...} |
| on_llm_start | [model name] | | {'input': 'hello'} | |
| on_llm_stream | [model name] | 'Hello' | | |
| on_llm_end | [model name] | | 'Hello human!' |
| on_chain_start | format_docs | | | |
| on_chain_stream | format_docs | "hello world!, goodbye world!" | | |
| on_chain_end | format_docs | | [Document(...)] | "hello world!, goodbye world!" |
| on_tool_start | some_tool | | {"x": 1, "y": "2"} | |
| on_tool_stream | some_tool | {"x": 1, "y": "2"} | | |
| on_tool_end | some_tool | | | {"x": 1, "y": "2"} |
| on_retriever_start | [retriever name] | | {"query": "hello"} | |
| on_retriever_chunk | [retriever name] | {documents: [...]} | | |
| on_retriever_end | [retriever name] | | {"query": "hello"} | {documents: [...]} |
| on_prompt_start | [template_name] | | {"question": "hello"} | |
| on_prompt_end | [template_name] | | {"question": "hello"} | ChatPromptValue(messages: [SystemMessage, ...]) |
Here are declarations associated with the events shown above:
`format_docs`:
```python
def format_docs(docs: List[Document]) -> str:
'''Format the docs.'''
return ", ".join([doc.page_content for doc in docs])
format_docs = RunnableLambda(format_docs)
```
`some_tool`:
```python
@tool
def some_tool(x: int, y: str) -> dict:
'''Some_tool.'''
return {"x": x, "y": y}
```
`prompt`:
```python
template = ChatPromptTemplate.from_messages(
[("system", "You are Cat Agent 007"), ("human", "{question}")]
).with_config({"run_name": "my_template", "tags": ["my_template"]})
```
Example:
.. code-block:: python
from langchain_core.runnables import RunnableLambda
async def reverse(s: str) -> str:
return s[::-1]
chain = RunnableLambda(func=reverse)
events = [
event async for event in chain.astream_events("hello", version="v1")
]
# will produce the following events (run_id has been omitted for brevity):
[
{
"data": {"input": "hello"},
"event": "on_chain_start",
"metadata": {},
"name": "reverse",
"tags": [],
},
{
"data": {"chunk": "olleh"},
"event": "on_chain_stream",
"metadata": {},
"name": "reverse",
"tags": [],
},
{
"data": {"output": "olleh"},
"event": "on_chain_end",
"metadata": {},
"name": "reverse",
"tags": [],
},
]
Args:
input: The input to the runnable.
config: The config to use for the runnable.
version: The version of the schema to use.
Currently only version 1 is available.
No default will be assigned until the API is stabilized.
include_names: Only include events from runnables with matching names.
include_types: Only include events from runnables with matching types.
include_tags: Only include events from runnables with matching tags.
exclude_names: Exclude events from runnables with matching names.
exclude_types: Exclude events from runnables with matching types.
exclude_tags: Exclude events from runnables with matching tags.
kwargs: Additional keyword arguments to pass to the runnable.
These will be passed to astream_log as this implementation
of astream_events is built on top of astream_log.
Returns:
An async stream of StreamEvents.[*Beta*] Generate a stream of events.
Use to create an iterator ove StreamEvents that provide real-time information
about the progress of the runnable, including StreamEvents from intermediate
results.
A StreamEvent is a dictionary with the following schema:
* ``event``: str - Event names are of the
format: on_[runnable_type]_(start|stream|end).
* ``name``: str - The name of the runnable that generated the event.
* ``run_id``: str - randomly generated ID associated with the given execution of
the runnable that emitted the event.
A child runnable that gets invoked as part of the execution of a
parent runnable is assigned its own unique ID.
* ``tags``: Optional[List[str]] - The tags of the runnable that generated
the event.
* ``metadata``: Optional[Dict[str, Any]] - The metadata of the runnable
that generated the event.
* ``data``: Dict[str, Any]
Below is a table that illustrates some evens that might be emitted by various
chains. Metadata fields have been omitted from the table for brevity.
Chain definitions have been included after the table.
| event | name | chunk | input | output |
|----------------------|------------------|---------------------------------|-----------------------------------------------|-------------------------------------------------|
| on_chat_model_start | [model name] | | {"messages": [[SystemMessage, HumanMessage]]} | |
| on_chat_model_stream | [model name] | AIMessageChunk(content="hello") | | |
| on_chat_model_end | [model name] | | {"messages": [[SystemMessage, HumanMessage]]} | {"generations": [...], "llm_output": None, ...} |
| on_llm_start | [model name] | | {'input': 'hello'} | |
| on_llm_stream | [model name] | 'Hello' | | |
| on_llm_end | [model name] | | 'Hello human!' |
| on_chain_start | format_docs | | | |
| on_chain_stream | format_docs | "hello world!, goodbye world!" | | |
| on_chain_end | format_docs | | [Document(...)] | "hello world!, goodbye world!" |
| on_tool_start | some_tool | | {"x": 1, "y": "2"} | |
| on_tool_stream | some_tool | {"x": 1, "y": "2"} | | |
| on_tool_end | some_tool | | | {"x": 1, "y": "2"} |
| on_retriever_start | [retriever name] | | {"query": "hello"} | |
| on_retriever_chunk | [retriever name] | {documents: [...]} | | |
| on_retriever_end | [retriever name] | | {"query": "hello"} | {documents: [...]} |
| on_prompt_start | [template_name] | | {"question": "hello"} | |
| on_prompt_end | [template_name] | | {"question": "hello"} | ChatPromptValue(messages: [SystemMessage, ...]) |
Here are declarations associated with the events shown above:
`format_docs`:
```python
def format_docs(docs: List[Document]) -> str:
'''Format the docs.'''
return ", ".join([doc.page_content for doc in docs])
format_docs = RunnableLambda(format_docs)
```
`some_tool`:
```python
@tool
def some_tool(x: int, y: str) -> dict:
'''Some_tool.'''
return {"x": x, "y": y}
```
`prompt`:
```python
template = ChatPromptTemplate.from_messages(
[("system", "You are Cat Agent 007"), ("human", "{question}")]
).with_config({"run_name": "my_template", "tags": ["my_template"]})
```
Example:
.. code-block:: python
from langchain_core.runnables import RunnableLambda
async def reverse(s: str) -> str:
return s[::-1]
chain = RunnableLambda(func=reverse)
events = [
event async for event in chain.astream_events("hello", version="v1")
]
# will produce the following events (run_id has been omitted for brevity):
[
{
"data": {"input": "hello"},
"event": "on_chain_start",
"metadata": {},
"name": "reverse",
"tags": [],
},
{
"data": {"chunk": "olleh"},
"event": "on_chain_stream",
"metadata": {},
"name": "reverse",
"tags": [],
},
{
"data": {"output": "olleh"},
"event": "on_chain_end",
"metadata": {},
"name": "reverse",
"tags": [],
},
]
Args:
input: The input to the runnable.
config: The config to use for the runnable.
version: The version of the schema to use.
Currently only version 1 is available.
No default will be assigned until the API is stabilized.
include_names: Only include events from runnables with matching names.
include_types: Only include events from runnables with matching types.
include_tags: Only include events from runnables with matching tags.
exclude_names: Exclude events from runnables with matching names.
exclude_types: Exclude events from runnables with matching types.
exclude_tags: Exclude events from runnables with matching tags.
kwargs: Additional keyword arguments to pass to the runnable.
These will be passed to astream_log as this implementation
of astream_events is built on top of astream_log.
Returns:
An async stream of StreamEvents.
Notes
-----
.. beta::
This API is in beta and may change in the future.
- async astream_log(self, input: 'Any', config: 'Optional[RunnableConfig]' = None, *, diff: 'bool' = True, with_streamed_output_list: 'bool' = True, include_names: 'Optional[Sequence[str]]' = None, include_types: 'Optional[Sequence[str]]' = None, include_tags: 'Optional[Sequence[str]]' = None, exclude_names: 'Optional[Sequence[str]]' = None, exclude_types: 'Optional[Sequence[str]]' = None, exclude_tags: 'Optional[Sequence[str]]' = None, **kwargs: 'Any') -> 'Union[AsyncIterator[RunLogPatch], AsyncIterator[RunLog]]'
- Stream all output from a runnable, as reported to the callback system.
This includes all inner runs of LLMs, Retrievers, Tools, etc.
Output is streamed as Log objects, which include a list of
jsonpatch ops that describe how the state of the run has changed in each
step, and the final state of the run.
The jsonpatch ops can be applied in order to construct state.
Args:
input: The input to the runnable.
config: The config to use for the runnable.
diff: Whether to yield diffs between each step, or the current state.
with_streamed_output_list: Whether to yield the streamed_output list.
include_names: Only include logs with these names.
include_types: Only include logs with these types.
include_tags: Only include logs with these tags.
exclude_names: Exclude logs with these names.
exclude_types: Exclude logs with these types.
exclude_tags: Exclude logs with these tags.
- async atransform(self, input: 'AsyncIterator[Input]', config: 'Optional[RunnableConfig]' = None, **kwargs: 'Optional[Any]') -> 'AsyncIterator[Output]'
- Default implementation of atransform, which buffers input and calls astream.
Subclasses should override this method if they can start producing output while
input is still being generated.
- bind(self, **kwargs: 'Any') -> 'Runnable[Input, Output]'
- Bind arguments to a Runnable, returning a new Runnable.
- config_schema(self, *, include: 'Optional[Sequence[str]]' = None) -> 'Type[BaseModel]'
- The type of config this runnable accepts specified as a pydantic model.
To mark a field as configurable, see the `configurable_fields`
and `configurable_alternatives` methods.
Args:
include: A list of fields to include in the config schema.
Returns:
A pydantic model that can be used to validate config.
- get_graph(self, config: 'Optional[RunnableConfig]' = None) -> 'Graph'
- Return a graph representation of this runnable.
- get_input_schema(self, config: 'Optional[RunnableConfig]' = None) -> 'Type[BaseModel]'
- Get a pydantic model that can be used to validate input to the runnable.
Runnables that leverage the configurable_fields and configurable_alternatives
methods will have a dynamic input schema that depends on which
configuration the runnable is invoked with.
This method allows to get an input schema for a specific configuration.
Args:
config: A config to use when generating the schema.
Returns:
A pydantic model that can be used to validate input.
- get_name(self, suffix: 'Optional[str]' = None, *, name: 'Optional[str]' = None) -> 'str'
- Get the name of the runnable.
- get_output_schema(self, config: 'Optional[RunnableConfig]' = None) -> 'Type[BaseModel]'
- Get a pydantic model that can be used to validate output to the runnable.
Runnables that leverage the configurable_fields and configurable_alternatives
methods will have a dynamic output schema that depends on which
configuration the runnable is invoked with.
This method allows to get an output schema for a specific configuration.
Args:
config: A config to use when generating the schema.
Returns:
A pydantic model that can be used to validate output.
- get_prompts(self, config: 'Optional[RunnableConfig]' = None) -> 'List[BasePromptTemplate]'
- map(self) -> 'Runnable[List[Input], List[Output]]'
- Return a new Runnable that maps a list of inputs to a list of outputs,
by calling invoke() with each input.
- pick(self, keys: 'Union[str, List[str]]') -> 'RunnableSerializable[Any, Any]'
- Pick keys from the dict output of this runnable.
Returns a new runnable.
- pipe(self, *others: 'Union[Runnable[Any, Other], Callable[[Any], Other]]', name: 'Optional[str]' = None) -> 'RunnableSerializable[Input, Other]'
- Compose this runnable with another object to create a RunnableSequence.
- transform(self, input: 'Iterator[Input]', config: 'Optional[RunnableConfig]' = None, **kwargs: 'Optional[Any]') -> 'Iterator[Output]'
- Default implementation of transform, which buffers input and then calls stream.
Subclasses should override this method if they can start producing output while
input is still being generated.
- with_config(self, config: 'Optional[RunnableConfig]' = None, **kwargs: 'Any') -> 'Runnable[Input, Output]'
- Bind config to a Runnable, returning a new Runnable.
- with_fallbacks(self, fallbacks: 'Sequence[Runnable[Input, Output]]', *, exceptions_to_handle: 'Tuple[Type[BaseException], ...]' = (<class 'Exception'>,), exception_key: 'Optional[str]' = None) -> 'RunnableWithFallbacksT[Input, Output]'
- Add fallbacks to a runnable, returning a new Runnable.
Args:
fallbacks: A sequence of runnables to try if the original runnable fails.
exceptions_to_handle: A tuple of exception types to handle.
exception_key: If string is specified then handled exceptions will be passed
to fallbacks as part of the input under the specified key. If None,
exceptions will not be passed to fallbacks. If used, the base runnable
and its fallbacks must accept a dictionary as input.
Returns:
A new Runnable that will try the original runnable, and then each
fallback in order, upon failures.
- with_listeners(self, *, on_start: 'Optional[Listener]' = None, on_end: 'Optional[Listener]' = None, on_error: 'Optional[Listener]' = None) -> 'Runnable[Input, Output]'
- Bind lifecycle listeners to a Runnable, returning a new Runnable.
on_start: Called before the runnable starts running, with the Run object.
on_end: Called after the runnable finishes running, with the Run object.
on_error: Called if the runnable throws an error, with the Run object.
The Run object contains information about the run, including its id,
type, input, output, error, start_time, end_time, and any tags or metadata
added to the run.
- with_retry(self, *, retry_if_exception_type: 'Tuple[Type[BaseException], ...]' = (<class 'Exception'>,), wait_exponential_jitter: 'bool' = True, stop_after_attempt: 'int' = 3) -> 'Runnable[Input, Output]'
- Create a new Runnable that retries the original runnable on exceptions.
Args:
retry_if_exception_type: A tuple of exception types to retry on
wait_exponential_jitter: Whether to add jitter to the wait time
between retries
stop_after_attempt: The maximum number of attempts to make before giving up
Returns:
A new Runnable that retries the original runnable on exceptions.
- with_types(self, *, input_type: 'Optional[Type[Input]]' = None, output_type: 'Optional[Type[Output]]' = None) -> 'Runnable[Input, Output]'
- Bind input and output types to a Runnable, returning a new Runnable.
Readonly properties inherited from langchain_core.runnables.base.Runnable:
- config_specs
- List configurable fields for this runnable.
- input_schema
- The type of input this runnable accepts specified as a pydantic model.
- output_schema
- The type of output this runnable produces specified as a pydantic model.
Data and other attributes inherited from langchain_core.runnables.base.Runnable:
- name = None
Class methods inherited from typing.Generic:
- __class_getitem__(params) from pydantic.v1.main.ModelMetaclass
- __init_subclass__(*args, **kwargs) from pydantic.v1.main.ModelMetaclass
- This method is called when a class is subclassed.
The default implementation does nothing. It may be
overridden to extend subclasses.
|
class OpenAIEmbeddings(ProxyOpenAI, langchain_openai.embeddings.base.OpenAIEmbeddings) |
|
OpenAIEmbeddings(*args, client: Any = None, async_client: Any = None, model: Optional[str] = None, dimensions: Optional[int] = None, deployment: Optional[str] = 'text-embedding-ada-002', api_version: Optional[str] = None, base_url: Optional[str] = None, openai_api_type: Optional[str] = None, openai_proxy: Optional[str] = None, embedding_ctx_length: int = 8191, api_key: Optional[str] = None, organization: Optional[str] = None, allowed_special: Union[Literal['all'], Set[str]] = set(), disallowed_special: Union[Literal['all'], Set[str], Sequence[str]] = 'all', chunk_size: int = 16, max_retries: int = 2, timeout: Union[float, Tuple[float, float], Any, NoneType] = None, headers: Any = None, tiktoken_enabled: bool = True, tiktoken_model_name: Optional[str] = 'text-embedding-ada-002', show_progress_bar: bool = False, model_kwargs: Dict[str, Any] = None, skip_empty: bool = False, default_headers: Optional[Mapping[str, str]] = None, default_query: Optional[Mapping[str, object]] = None, retry_min_seconds: int = 4, retry_max_seconds: int = 20, http_client: Optional[Any] = None, proxy_client: Optional[Any] = None, deployment_id: Optional[str] = None, config_name: Optional[str] = None, config_id: Optional[str] = None, proxy_model_name: Optional[str] = None) -> None
|
|
- Method resolution order:
- OpenAIEmbeddings
- ProxyOpenAI
- gen_ai_hub.proxy.langchain.base.BaseAuth
- langchain_openai.embeddings.base.OpenAIEmbeddings
- pydantic.v1.main.BaseModel
- pydantic.v1.utils.Representation
- langchain_core.embeddings.Embeddings
- abc.ABC
- builtins.object
Methods defined here:
- __init__(self, *args, **kwargs)
- Create a new model by parsing and validating input data from keyword arguments.
Raises ValidationError if the input data cannot be parsed to form a valid model.
Class methods defined here:
- validate_environment(values: Dict) -> Dict from pydantic.v1.main.ModelMetaclass
- Validates the environment.
:param values: The input values
:type values: Dict
:return: The validated values
:rtype: Dict
Static methods defined here:
- __json_encoder__ = pydantic_encoder(obj: Any) -> Any
Data descriptors defined here:
- __weakref__
- list of weak references to the object (if defined)
Data and other attributes defined here:
- __abstractmethods__ = frozenset()
- __annotations__ = {'chunk_size': <class 'int'>, 'model': typing.Optional[str], 'openai_api_version': typing.Optional[str], 'tiktoken_model_name': typing.Optional[str]}
- __class_vars__ = set()
- __config__ = <class 'pydantic.v1.config.Config'>
- __custom_root_type__ = False
- __exclude_fields__ = {'async_client': True, 'client': True}
- __fields__ = {'allowed_special': ModelField(name='allowed_special', type=Union[Li...'all'], Set[str]], required=False, default=set()), 'async_client': ModelField(name='async_client', type=Optional[Any], required=False, default=None), 'chunk_size': ModelField(name='chunk_size', type=int, required=False, default=16), 'client': ModelField(name='client', type=Optional[Any], required=False, default=None), 'config_id': ModelField(name='config_id', type=Optional[str], required=False, default=None), 'config_name': ModelField(name='config_name', type=Optional[str], required=False, default=None), 'default_headers': ModelField(name='default_headers', type=Optional[Mapping[str, str]], required=False, default=None), 'default_query': ModelField(name='default_query', type=Optional[Mapping[str, object]], required=False, default=None), 'deployment': ModelField(name='deployment', type=Optional[str], required=False, default='text-embedding-ada-002'), 'deployment_id': ModelField(name='deployment_id', type=Optional[str], required=False, default=None), ...}
- __hash__ = None
- __include_fields__ = None
- __post_root_validators__ = [(False, <function OpenAIEmbeddings.validate_environment>)]
- __pre_root_validators__ = [<function OpenAIEmbeddings.build_extra>]
- __private_attributes__ = {}
- __schema_cache__ = {}
- __signature__ = <Signature (*args, client: Any = None, async_cli... proxy_model_name: Optional[str] = None) -> None>
- __validators__ = {}
Class methods inherited from ProxyOpenAI:
- validate_clients(values: Dict) -> Dict from pydantic.v1.main.ModelMetaclass
Methods inherited from langchain_openai.embeddings.base.OpenAIEmbeddings:
- async aembed_documents(self, texts: 'List[str]', chunk_size: 'Optional[int]' = 0) -> 'List[List[float]]'
- Call out to OpenAI's embedding endpoint async for embedding search docs.
Args:
texts: The list of texts to embed.
chunk_size: The chunk size of embeddings. If None, will use the chunk size
specified by the class.
Returns:
List of embeddings, one for each text.
- async aembed_query(self, text: 'str') -> 'List[float]'
- Call out to OpenAI's embedding endpoint async for embedding query text.
Args:
text: The text to embed.
Returns:
Embedding for the text.
- embed_documents(self, texts: 'List[str]', chunk_size: 'Optional[int]' = 0) -> 'List[List[float]]'
- Call out to OpenAI's embedding endpoint for embedding search docs.
Args:
texts: The list of texts to embed.
chunk_size: The chunk size of embeddings. If None, will use the chunk size
specified by the class.
Returns:
List of embeddings, one for each text.
- embed_query(self, text: 'str') -> 'List[float]'
- Call out to OpenAI's embedding endpoint for embedding query text.
Args:
text: The text to embed.
Returns:
Embedding for the text.
Class methods inherited from langchain_openai.embeddings.base.OpenAIEmbeddings:
- build_extra(values: 'Dict[str, Any]') -> 'Dict[str, Any]' from pydantic.v1.main.ModelMetaclass
- Build extra kwargs from additional params that were passed in.
Data and other attributes inherited from langchain_openai.embeddings.base.OpenAIEmbeddings:
- Config = <class 'langchain_openai.embeddings.base.OpenAIEmbeddings.Config'>
- Configuration for this pydantic object.
Methods inherited from pydantic.v1.main.BaseModel:
- __eq__(self, other: Any) -> bool
- Return self==value.
- __getstate__(self) -> 'DictAny'
- __iter__(self) -> 'TupleGenerator'
- so `dict(model)` works
- __repr_args__(self) -> 'ReprArgs'
- Returns the attributes to show in __str__, __repr__, and __pretty__ this is generally overridden.
Can either return:
* name - value pairs, e.g.: `[('foo_name', 'foo'), ('bar_name', ['b', 'a', 'r'])]`
* or, just values, e.g.: `[(None, 'foo'), (None, ['b', 'a', 'r'])]`
- __setattr__(self, name, value)
- Implement setattr(self, name, value).
- __setstate__(self, state: 'DictAny') -> None
- copy(self: 'Model', *, include: Union[ForwardRef('AbstractSetIntStr'), ForwardRef('MappingIntStrAny'), NoneType] = None, exclude: Union[ForwardRef('AbstractSetIntStr'), ForwardRef('MappingIntStrAny'), NoneType] = None, update: Optional[ForwardRef('DictStrAny')] = None, deep: bool = False) -> 'Model'
- Duplicate a model, optionally choose which fields to include, exclude and change.
:param include: fields to include in new model
:param exclude: fields to exclude from new model, as with values this takes precedence over include
:param update: values to change/add in the new model. Note: the data is not validated before creating
the new model: you should trust this data
:param deep: set to `True` to make a deep copy of the model
:return: new model instance
- dict(self, *, include: Union[ForwardRef('AbstractSetIntStr'), ForwardRef('MappingIntStrAny'), NoneType] = None, exclude: Union[ForwardRef('AbstractSetIntStr'), ForwardRef('MappingIntStrAny'), NoneType] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) -> 'DictStrAny'
- Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.
- json(self, *, include: Union[ForwardRef('AbstractSetIntStr'), ForwardRef('MappingIntStrAny'), NoneType] = None, exclude: Union[ForwardRef('AbstractSetIntStr'), ForwardRef('MappingIntStrAny'), NoneType] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) -> str
- Generate a JSON representation of the model, `include` and `exclude` arguments as per `dict()`.
`encoder` is an optional function to supply as `default` to json.dumps(), other arguments as per `json.dumps()`.
Class methods inherited from pydantic.v1.main.BaseModel:
- __get_validators__() -> 'CallableGenerator' from pydantic.v1.main.ModelMetaclass
- __try_update_forward_refs__(**localns: Any) -> None from pydantic.v1.main.ModelMetaclass
- Same as update_forward_refs but will not raise exception
when forward references are not defined.
- construct(_fields_set: Optional[ForwardRef('SetStr')] = None, **values: Any) -> 'Model' from pydantic.v1.main.ModelMetaclass
- Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data.
Default values are respected, but no other validation is performed.
Behaves as if `Config.extra = 'allow'` was set since it adds all passed values
- from_orm(obj: Any) -> 'Model' from pydantic.v1.main.ModelMetaclass
- parse_file(path: Union[str, pathlib.Path], *, content_type: str = None, encoding: str = 'utf8', proto: pydantic.v1.parse.Protocol = None, allow_pickle: bool = False) -> 'Model' from pydantic.v1.main.ModelMetaclass
- parse_obj(obj: Any) -> 'Model' from pydantic.v1.main.ModelMetaclass
- parse_raw(b: Union[str, bytes], *, content_type: str = None, encoding: str = 'utf8', proto: pydantic.v1.parse.Protocol = None, allow_pickle: bool = False) -> 'Model' from pydantic.v1.main.ModelMetaclass
- schema(by_alias: bool = True, ref_template: str = '#/definitions/{model}') -> 'DictStrAny' from pydantic.v1.main.ModelMetaclass
- schema_json(*, by_alias: bool = True, ref_template: str = '#/definitions/{model}', **dumps_kwargs: Any) -> str from pydantic.v1.main.ModelMetaclass
- update_forward_refs(**localns: Any) -> None from pydantic.v1.main.ModelMetaclass
- Try to update ForwardRefs on fields based on this Model, globalns and localns.
- validate(value: Any) -> 'Model' from pydantic.v1.main.ModelMetaclass
Data descriptors inherited from pydantic.v1.main.BaseModel:
- __dict__
- dictionary for instance variables (if defined)
- __fields_set__
Methods inherited from pydantic.v1.utils.Representation:
- __pretty__(self, fmt: Callable[[Any], Any], **kwargs: Any) -> Generator[Any, NoneType, NoneType]
- Used by devtools (https://python-devtools.helpmanual.io/) to provide a human readable representations of objects
- __repr__(self) -> str
- Return repr(self).
- __repr_name__(self) -> str
- Name of the instance's class, used in __repr__.
- __repr_str__(self, join_str: str) -> str
- __rich_repr__(self) -> 'RichReprResult'
- Get fields for Rich library
- __str__(self) -> str
- Return str(self).
| |