langchain_community.llms.oci_generative_ai.OCIGenAIΒΆ

class langchain_community.llms.oci_generative_ai.OCIGenAI[source]ΒΆ

Bases: LLM, OCIGenAIBase

OCI large language models.

To authenticate, the OCI client uses the methods described in https://docs.oracle.com/en-us/iaas/Content/API/Concepts/sdk_authentication_methods.htm

The authentifcation method is passed through auth_type and should be one of: API_KEY (default), SECURITY_TOKEN, INSTANCE_PRINCIPLE, RESOURCE_PRINCIPLE

Make sure you have the required policies (profile/roles) to access the OCI Generative AI service. If a specific config profile is used, you must pass the name of the profile (from ~/.oci/config) through auth_profile.

To use, you must provide the compartment id along with the endpoint url, and model id as named parameters to the constructor.

Example

from langchain_community.llms import OCIGenAI

llm = OCIGenAI(
        model_id="MY_MODEL_ID",
        service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",
        compartment_id="MY_OCID"
    )

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.

param auth_profile: Optional[str] = 'DEFAULT'ΒΆ

The name of the profile in ~/.oci/config If not specified , DEFAULT will be used

param auth_type: Optional[str] = 'API_KEY'ΒΆ

Authentication type, could be

API_KEY, SECURITY_TOKEN, INSTANCE_PRINCIPLE, RESOURCE_PRINCIPLE

If not specified, API_KEY will be used

param cache: Optional[bool] = NoneΒΆ

Whether to cache the response.

param callback_manager: Optional[BaseCallbackManager] = NoneΒΆ

[DEPRECATED]

param callbacks: Callbacks = NoneΒΆ

Callbacks to add to the run trace.

param compartment_id: str = NoneΒΆ

OCID of compartment

param is_stream: bool = FalseΒΆ

Whether to stream back partial progress

param llm_stop_sequence_mapping: Mapping[str, str] = {'cohere': 'stop_sequences', 'meta': 'stop'}ΒΆ
param metadata: Optional[Dict[str, Any]] = NoneΒΆ

Metadata to add to the run trace.

param model_id: str = NoneΒΆ

Id of the model to call, e.g., cohere.command

param model_kwargs: Optional[Dict] = NoneΒΆ

Keyword arguments to pass to the model

param provider: str = NoneΒΆ

Provider name of the model. Default to None, will try to be derived from the model_id otherwise, requires user input

param service_endpoint: str = NoneΒΆ

service endpoint url

param tags: Optional[List[str]] = NoneΒΆ

Tags to add to the run trace.

param verbose: bool [Optional]ΒΆ

Whether to print out response text.

__call__(prompt: str, stop: Optional[List[str]] = None, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, *, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, **kwargs: Any) strΒΆ

[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 since version 0.1.7: Use invoke instead.

async abatch(inputs: List[Union[PromptValue, str, Sequence[BaseMessage]]], config: Optional[Union[RunnableConfig, List[RunnableConfig]]] = None, *, return_exceptions: bool = False, **kwargs: Any) List[str]ΒΆ

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(prompts: List[str], stop: Optional[List[str]] = None, callbacks: Union[List[BaseCallbackHandler], BaseCallbackManager, None, List[Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]]] = 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) LLMResultΒΆ

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).

Parameters
  • 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(prompts: List[PromptValue], stop: Optional[List[str]] = None, callbacks: Union[List[BaseCallbackHandler], BaseCallbackManager, None, List[Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]]] = None, **kwargs: Any) LLMResultΒΆ

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).

Parameters
  • 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(input: Union[PromptValue, str, Sequence[BaseMessage]], config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) strΒΆ

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(text: str, *, stop: Optional[Sequence[str]] = None, **kwargs: Any) strΒΆ

[Deprecated][Deprecated]

Notes

Deprecated since version 0.1.7: Use ainvoke instead.

async apredict_messages(messages: List[BaseMessage], *, stop: Optional[Sequence[str]] = None, **kwargs: Any) BaseMessageΒΆ

[Deprecated][Deprecated]

Notes

Deprecated since version 0.1.7: Use ainvoke instead.

assign(**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]ΒΆ

Assigns new fields to the dict output of this runnable. Returns a new runnable.

async astream(input: Union[PromptValue, str, Sequence[BaseMessage]], config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) AsyncIterator[str]ΒΆ

Default implementation of astream, which calls ainvoke. Subclasses should override this method if they support streaming output.

astream_events(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]ΒΆ

[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 |

|----------------------|β€”β€”β€”β€”β€”β€”|---------------------------------|———————————————–|-------------------------------------------------| | on_chat_model_start | [model name] | | {β€œmessages”: [[SystemMessage, HumanMessage]]} | | | on_chat_model_stream | [model name] | AIMessageChunk(content=”hello”) | | | | on_chat_model_end | [model name] | | {β€œmessages”: [[SystemMessage, HumanMessage]]} | {β€œgenerations”: […], β€œllm_output”: None, …} | | on_llm_start | [model name] | | {β€˜input’: β€˜hello’} | | | on_llm_stream | [model name] | β€˜Hello’ | | | | on_llm_end | [model name] | | β€˜Hello human!’ | | on_chain_start | format_docs | | | | | on_chain_stream | format_docs | β€œhello world!, goodbye world!” | | | | on_chain_end | format_docs | | [Document(…)] | β€œhello world!, goodbye world!” | | on_tool_start | some_tool | | {β€œx”: 1, β€œy”: β€œ2”} | | | on_tool_stream | some_tool | {β€œx”: 1, β€œy”: β€œ2”} | | | | on_tool_end | some_tool | | | {β€œx”: 1, β€œy”: β€œ2”} | | on_retriever_start | [retriever name] | | {β€œquery”: β€œhello”} | | | on_retriever_chunk | [retriever name] | {documents: […]} | | | | on_retriever_end | [retriever name] | | {β€œquery”: β€œhello”} | {documents: […]} | | on_prompt_start | [template_name] | | {β€œquestion”: β€œhello”} | | | on_prompt_end | [template_name] | | {β€œquestion”: β€œhello”} | ChatPromptValue(messages: [SystemMessage, …]) |

Here are declarations associated with the events shown above:

format_docs:

```python def format_docs(docs: List[Document]) -> str:

β€˜β€™β€™Format the docs.’’’ return β€œ, β€œ.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:

β€˜β€™β€™Some_tool.’’’ return {β€œx”: x, β€œy”: y}

```

prompt:

```python template = ChatPromptTemplate.from_messages(

[(β€œsystem”, β€œYou are Cat Agent 007”), (β€œhuman”, β€œ{question}”)]

).with_config({β€œrun_name”: β€œmy_template”, β€œtags”: [β€œmy_template”]}) ```

Example:

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": [],
    },
]
Parameters
  • 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 |

|----------------------|β€”β€”β€”β€”β€”β€”|---------------------------------|———————————————–|-------------------------------------------------| | on_chat_model_start | [model name] | | {β€œmessages”: [[SystemMessage, HumanMessage]]} | | | on_chat_model_stream | [model name] | AIMessageChunk(content=”hello”) | | | | on_chat_model_end | [model name] | | {β€œmessages”: [[SystemMessage, HumanMessage]]} | {β€œgenerations”: […], β€œllm_output”: None, …} | | on_llm_start | [model name] | | {β€˜input’: β€˜hello’} | | | on_llm_stream | [model name] | β€˜Hello’ | | | | on_llm_end | [model name] | | β€˜Hello human!’ | | on_chain_start | format_docs | | | | | on_chain_stream | format_docs | β€œhello world!, goodbye world!” | | | | on_chain_end | format_docs | | [Document(…)] | β€œhello world!, goodbye world!” | | on_tool_start | some_tool | | {β€œx”: 1, β€œy”: β€œ2”} | | | on_tool_stream | some_tool | {β€œx”: 1, β€œy”: β€œ2”} | | | | on_tool_end | some_tool | | | {β€œx”: 1, β€œy”: β€œ2”} | | on_retriever_start | [retriever name] | | {β€œquery”: β€œhello”} | | | on_retriever_chunk | [retriever name] | {documents: […]} | | | | on_retriever_end | [retriever name] | | {β€œquery”: β€œhello”} | {documents: […]} | | on_prompt_start | [template_name] | | {β€œquestion”: β€œhello”} | | | on_prompt_end | [template_name] | | {β€œquestion”: β€œhello”} | ChatPromptValue(messages: [SystemMessage, …]) |

Here are declarations associated with the events shown above:

format_docs:

```python def format_docs(docs: List[Document]) -> str:

β€˜β€™β€™Format the docs.’’’ return β€œ, β€œ.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:

β€˜β€™β€™Some_tool.’’’ return {β€œx”: x, β€œy”: y}

```

prompt:

```python template = ChatPromptTemplate.from_messages(

[(β€œsystem”, β€œYou are Cat Agent 007”), (β€œhuman”, β€œ{question}”)]

).with_config({β€œrun_name”: β€œmy_template”, β€œtags”: [β€œmy_template”]}) ```

Example:

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": [],
    },
]
Parameters
  • 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

async astream_log(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]]ΒΆ

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.

Parameters
  • 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(input: AsyncIterator[Input], config: Optional[RunnableConfig] = None, **kwargs: Optional[Any]) AsyncIterator[Output]ΒΆ

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(inputs: List[Union[PromptValue, str, Sequence[BaseMessage]]], config: Optional[Union[RunnableConfig, List[RunnableConfig]]] = None, *, return_exceptions: bool = False, **kwargs: Any) List[str]ΒΆ

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(**kwargs: Any) Runnable[Input, Output]ΒΆ

Bind arguments to a Runnable, returning a new Runnable.

config_schema(*, include: Optional[Sequence[str]] = None) Type[BaseModel]ΒΆ

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.

Parameters

include – A list of fields to include in the config schema.

Returns

A pydantic model that can be used to validate config.

configurable_alternatives(which: ConfigurableField, *, default_key: str = 'default', prefix_keys: bool = False, **kwargs: Union[Runnable[Input, Output], Callable[[], Runnable[Input, Output]]]) RunnableSerializable[Input, Output]ΒΆ
configurable_fields(**kwargs: Union[ConfigurableField, ConfigurableFieldSingleOption, ConfigurableFieldMultiOption]) RunnableSerializable[Input, Output]ΒΆ
classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) ModelΒΆ

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 = β€˜allow’ was set since it adds all passed values

copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) ModelΒΆ

Duplicate a model, optionally choose which fields to include, exclude and change.

Parameters
  • include – fields to include in new model

  • exclude – fields to exclude from new model, as with values this takes precedence over include

  • 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

  • deep – set to True to make a deep copy of the model

Returns

new model instance

dict(**kwargs: Any) DictΒΆ

Return a dictionary of the LLM.

classmethod from_orm(obj: Any) ModelΒΆ
generate(prompts: List[str], stop: Optional[List[str]] = None, callbacks: Union[List[BaseCallbackHandler], BaseCallbackManager, None, List[Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]]] = 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) LLMResultΒΆ

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).

Parameters
  • 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(prompts: List[PromptValue], stop: Optional[List[str]] = None, callbacks: Union[List[BaseCallbackHandler], BaseCallbackManager, None, List[Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]]] = None, **kwargs: Any) LLMResultΒΆ

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).

Parameters
  • 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.

get_graph(config: Optional[RunnableConfig] = None) GraphΒΆ

Return a graph representation of this runnable.

get_input_schema(config: Optional[RunnableConfig] = None) Type[BaseModel]ΒΆ

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.

Parameters

config – A config to use when generating the schema.

Returns

A pydantic model that can be used to validate input.

classmethod get_lc_namespace() List[str]ΒΆ

Get the namespace of the langchain object.

For example, if the class is langchain.llms.openai.OpenAI, then the namespace is [β€œlangchain”, β€œllms”, β€œopenai”]

get_name(suffix: Optional[str] = None, *, name: Optional[str] = None) strΒΆ

Get the name of the runnable.

get_num_tokens(text: str) intΒΆ

Get the number of tokens present in the text.

Useful for checking if an input will fit in a model’s context window.

Parameters

text – The string input to tokenize.

Returns

The integer number of tokens in the text.

get_num_tokens_from_messages(messages: List[BaseMessage]) intΒΆ

Get the number of tokens in the messages.

Useful for checking if an input will fit in a model’s context window.

Parameters

messages – The message inputs to tokenize.

Returns

The sum of the number of tokens across the messages.

get_output_schema(config: Optional[RunnableConfig] = None) Type[BaseModel]ΒΆ

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.

Parameters

config – A config to use when generating the schema.

Returns

A pydantic model that can be used to validate output.

get_prompts(config: Optional[RunnableConfig] = None) List[BasePromptTemplate]ΒΆ
get_token_ids(text: str) List[int]ΒΆ

Return the ordered ids of the tokens in a text.

Parameters

text – The string input to tokenize.

Returns

A list of ids corresponding to the tokens in the text, in order they occur

in the text.

invoke(input: Union[PromptValue, str, Sequence[BaseMessage]], config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) strΒΆ

Transform a single input into an output. Override to implement.

Parameters
  • input – The input to the runnable.

  • config – A config to use when invoking the runnable. The config supports standard keys like β€˜tags’, β€˜metadata’ for tracing purposes, β€˜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.

classmethod is_lc_serializable() boolΒΆ

Is this class serializable?

json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = 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) unicodeΒΆ

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().

classmethod lc_id() List[str]ΒΆ

A unique identifier for this class for serialization purposes.

The unique identifier is a list of strings that describes the path to the object.

map() Runnable[List[Input], List[Output]]ΒΆ

Return a new Runnable that maps a list of inputs to a list of outputs, by calling invoke() with each input.

classmethod parse_file(path: Union[str, Path], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) ModelΒΆ
classmethod parse_obj(obj: Any) ModelΒΆ
classmethod parse_raw(b: Union[str, bytes], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) ModelΒΆ
pick(keys: Union[str, List[str]]) RunnableSerializable[Any, Any]ΒΆ

Pick keys from the dict output of this runnable. Returns a new runnable.

pipe(*others: Union[Runnable[Any, Other], Callable[[Any], Other]], name: Optional[str] = None) RunnableSerializable[Input, Other]ΒΆ

Compose this runnable with another object to create a RunnableSequence.

predict(text: str, *, stop: Optional[Sequence[str]] = None, **kwargs: Any) strΒΆ

[Deprecated][Deprecated]

Notes

Deprecated since version 0.1.7: Use invoke instead.

predict_messages(messages: List[BaseMessage], *, stop: Optional[Sequence[str]] = None, **kwargs: Any) BaseMessageΒΆ

[Deprecated][Deprecated]

Notes

Deprecated since version 0.1.7: Use invoke instead.

save(file_path: Union[Path, str]) NoneΒΆ

Save the LLM.

Parameters

file_path – Path to file to save the LLM to.

Example: .. code-block:: python

llm.save(file_path=”path/llm.yaml”)

classmethod schema(by_alias: bool = True, ref_template: unicode = '#/definitions/{model}') DictStrAnyΒΆ
classmethod schema_json(*, by_alias: bool = True, ref_template: unicode = '#/definitions/{model}', **dumps_kwargs: Any) unicodeΒΆ
stream(input: Union[PromptValue, str, Sequence[BaseMessage]], config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) Iterator[str]ΒΆ

Default implementation of stream, which calls invoke. Subclasses should override this method if they support streaming output.

to_json() Union[SerializedConstructor, SerializedNotImplemented]ΒΆ
to_json_not_implemented() SerializedNotImplementedΒΆ
transform(input: Iterator[Input], config: Optional[RunnableConfig] = None, **kwargs: Optional[Any]) Iterator[Output]ΒΆ

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.

classmethod update_forward_refs(**localns: Any) NoneΒΆ

Try to update ForwardRefs on fields based on this Model, globalns and localns.

classmethod validate(value: Any) ModelΒΆ
with_config(config: Optional[RunnableConfig] = None, **kwargs: Any) Runnable[Input, Output]ΒΆ

Bind config to a Runnable, returning a new Runnable.

with_fallbacks(fallbacks: Sequence[Runnable[Input, Output]], *, exceptions_to_handle: Tuple[Type[BaseException], ...] = (<class 'Exception'>,), exception_key: Optional[str] = None) RunnableWithFallbacksT[Input, Output]ΒΆ

Add fallbacks to a runnable, returning a new Runnable.

Parameters
  • 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(*, on_start: Optional[Listener] = None, on_end: Optional[Listener] = None, on_error: Optional[Listener] = None) Runnable[Input, Output]ΒΆ

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(*, retry_if_exception_type: ~typing.Tuple[~typing.Type[BaseException], ...] = (<class 'Exception'>,), wait_exponential_jitter: bool = True, stop_after_attempt: int = 3) Runnable[Input, Output]ΒΆ

Create a new Runnable that retries the original runnable on exceptions.

Parameters
  • 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(*, input_type: Optional[Type[Input]] = None, output_type: Optional[Type[Output]] = None) Runnable[Input, Output]ΒΆ

Bind input and output types to a Runnable, returning a new Runnable.

property InputType: TypeAliasΒΆ

Get the input type for this runnable.

property OutputType: Type[str]ΒΆ

Get the input type for this runnable.

property config_specs: List[ConfigurableFieldSpec]ΒΆ

List configurable fields for this runnable.

property input_schema: Type[BaseModel]ΒΆ

The type of input this runnable accepts specified as a pydantic model.

property lc_attributes: DictΒΆ

List of attribute names that should be included in the serialized kwargs.

These attributes must be accepted by the constructor.

property lc_secrets: Dict[str, str]ΒΆ

A map of constructor argument names to secret ids.

For example,

{β€œopenai_api_key”: β€œOPENAI_API_KEY”}

name: Optional[str] = NoneΒΆ

The name of the runnable. Used for debugging and tracing.

property output_schema: Type[BaseModel]ΒΆ

The type of output this runnable produces specified as a pydantic model.