FakeListChatModel

_batchWithConfig→ Promise<Error | RunOutput[]>

Internal method that handles batching and configuration for a runnable It takes a function, input values, and optional configuration, and returns a promise that resolves to the output values.

_callWithConfig

_combineLLMOutput→ Record<string, any> | undefined

_createResponseChunk→ ChatGenerationChunk

_currentResponse→ string

_formatGeneration→ __type

_generate→ Promise<ChatResult>

_generateCached→ Promise<LLMResult & __type>

_getOptionsList

_getSerializedCacheKeyParametersForCall→ string

Create a unique cache key for a specific call to a specific language model.

_identifyingParams→ Record<string, any>

Get the identifying parameters of the LLM.

_separateRunnableConfigFromCallOptions

_separateRunnableConfigFromCallOptionsCompat

_sleep→ Promise<void>

_sleepIfRequested→ Promise<void>

_streamIterator→ AsyncGenerator<RunOutput>

Default streaming implementation. Subclasses should override this method if they support streaming output.

_streamLog

_streamResponseChunks→ AsyncGenerator<ChatGenerationChunk>

_transformStreamWithConfig

assign→ Runnable

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

asTool→ RunnableToolLike<InteropZodType<ToolCall<string, Record<string, any>> | T>, RunOutput>

Convert a runnable to a tool. Return a new instance of RunnableToolLike which contains the runnable, name, description and schema.

batch→ Promise<RunOutput[]>

Default implementation of batch, which calls invoke N times. Subclasses should override this method if they can batch more efficiently.

bindTools→ Runnable<BaseLanguageModelInput, OutputMessageType, CallOptions>

Bind tool-like objects to this chat model.

generate→ Promise<LLMResult>

Generates chat based on the input messages.

generatePrompt→ Promise<LLMResult>

getGraph→ Graph

getLsParams→ LangSmithParams

getName→ string

getNumTokens→ Promise<number>

Get the number of tokens in the content.

invocationParams→ any

Get the parameters used to invoke the model

invoke→ Promise<RunOutput>

Method to invoke the document transformation. This method calls the transformDocuments method with the provided input.

pick→ Runnable

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

pipe→ Runnable<RunInput, Exclude<NewRunOutput, Error>>

Create a new runnable sequence that runs each individual runnable in series, piping the output of one runnable into another runnable or runnable-like.

stream→ Promise<IterableReadableStream<RunOutput>>

Stream output in chunks.

streamEvents→ IterableReadableStream<StreamEvent>

Generate a stream of events emitted by the internal steps of the runnable.

Use to create an iterator over 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: string - Event names are of the format: on_[runnable_type]_(start|stream|end).
name: string - The name of the runnable that generated the event.
run_id: string - 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: string[] - The tags of the runnable that generated the event.
metadata: Record<string, any> - The metadata of the runnable that generated the event.
data: Record<string, any>

Below is a table that illustrates some events 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.

ATTENTION This reference table is for the V2 version of the schema.

+----------------------+-----------------------------+------------------------------------------+
| event                | input                       | output/chunk                             |
+======================+=============================+==========================================+
| on_chat_model_start  | {"messages": BaseMessage[]} |                                          |
+----------------------+-----------------------------+------------------------------------------+
| on_chat_model_stream |                             | AIMessageChunk("hello")                  |
+----------------------+-----------------------------+------------------------------------------+
| on_chat_model_end    | {"messages": BaseMessage[]} | AIMessageChunk("hello world")            |
+----------------------+-----------------------------+------------------------------------------+
| on_llm_start         | {'input': 'hello'}          |                                          |
+----------------------+-----------------------------+------------------------------------------+
| on_llm_stream        |                             | 'Hello'                                  |
+----------------------+-----------------------------+------------------------------------------+
| on_llm_end           | 'Hello human!'              |                                          |
+----------------------+-----------------------------+------------------------------------------+
| on_chain_start       |                             |                                          |
+----------------------+-----------------------------+------------------------------------------+
| on_chain_stream      |                             | "hello world!"                           |
+----------------------+-----------------------------+------------------------------------------+
| on_chain_end         | [Document(...)]             | "hello world!, goodbye world!"           |
+----------------------+-----------------------------+------------------------------------------+
| on_tool_start        | {"x": 1, "y": "2"}          |                                          |
+----------------------+-----------------------------+------------------------------------------+
| on_tool_end          |                             | {"x": 1, "y": "2"}                       |
+----------------------+-----------------------------+------------------------------------------+
| on_retriever_start   | {"query": "hello"}          |                                          |
+----------------------+-----------------------------+------------------------------------------+
| on_retriever_end     | {"query": "hello"}          | [Document(...), ..]                      |
+----------------------+-----------------------------+------------------------------------------+
| on_prompt_start      | {"question": "hello"}       |                                          |
+----------------------+-----------------------------+------------------------------------------+
| on_prompt_end        | {"question": "hello"}       | ChatPromptValue(messages: BaseMessage[]) |
+----------------------+-----------------------------+------------------------------------------+

The "on_chain_*" events are the default for Runnables that don't fit one of the above categories.

In addition to the standard events above, users can also dispatch custom events.

Custom events will be only be surfaced with in the v2 version of the API!

A custom event has following format:

+-----------+------+------------------------------------------------------------+
| Attribute | Type | Description                                                |
+===========+======+============================================================+
| name      | str  | A user defined name for the event.                         |
+-----------+------+------------------------------------------------------------+
| data      | Any  | The data associated with the event. This can be anything.  |
+-----------+------+------------------------------------------------------------+

Here's an example:

import { RunnableLambda } from "@langchain/core/runnables";
import { dispatchCustomEvent } from "@langchain/core/callbacks/dispatch";
// Use this import for web environments that don't support "async_hooks"
// and manually pass config to child runs.
// import { dispatchCustomEvent } from "@langchain/core/callbacks/dispatch/web";

const slowThing = RunnableLambda.from(async (someInput: string) => {
  // Placeholder for some slow operation
  await new Promise((resolve) => setTimeout(resolve, 100));
  await dispatchCustomEvent("progress_event", {
   message: "Finished step 1 of 2",
 });
 await new Promise((resolve) => setTimeout(resolve, 100));
 return "Done";
});

const eventStream = await slowThing.streamEvents("hello world", {
  version: "v2",
});

for await (const event of eventStream) {
 if (event.event === "on_custom_event") {
   console.log(event);
 }
}

streamLog→ AsyncGenerator<RunLogPatch>

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.

toJSON→ Serialized

toJSONNotImplemented→ SerializedNotImplemented

transform→ AsyncGenerator<RunOutput>

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.

withConfig→ Runnable<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Bind config to a Runnable, returning a new Runnable.

withFallbacks→ RunnableWithFallbacks<RunInput, RunOutput>

Create a new runnable from the current one that will try invoking other passed fallback runnables if the initial invocation fails.

withListeners→ Runnable<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Bind lifecycle listeners to a Runnable, returning a new Runnable. The Run object contains information about the run, including its id, type, input, output, error, startTime, endTime, and any tags or metadata added to the run.

withRetry→ RunnableRetry<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Add retry logic to an existing runnable.

withStructuredOutput→ Runnable<BaseLanguageModelInput, RunOutput>

Model wrapper that returns outputs formatted to match the given schema.

_convertInputToPromptValue

isRunnable→ thing is Runnable<any, any, RunnableConfig<Record<string, any>>>

deserialize→ Promise<BaseLanguageModel<any, BaseLanguageModelCallOptions>>

lc_name→ string

The name of the serializable. Override to provide an alias or to preserve the serialized module name in minified environments.

Implemented as a static method to support loading logic.

deprecatedmethod

serialize→ SerializedLLM

deprecatedmethod

Inherited fromBaseChatModel

Properties

Pcache: BaseCache<Generation[]>Pcallbacks: Callbacks

Callbacks for this call and any sub-calls (eg. a Chain calling an LLM).

Pcaller: AsyncCaller

PdisableStreaming: boolean Plc_kwargs: SerializedFields Plc_namespace: ["langchain_core", "callbacks", string]

The async caller should be used by subclasses to make any async calls,

Plc_runnable Plc_serializable: boolean Pmetadata: Record<string, unknown>Pname: string PoutputVersion: MessageOutputVersion PParsedCallOptions: Omit<CallOptions, Exclude<keyof RunnableConfig, "signal" | "timeout" | "maxConcurrency">>Ptags: string[]Pverbose: boolean PcallKeys: string[]Plc_aliases: __type | undefined Plc_attributes: __type | undefined Plc_id: string[]Plc_secrets: __type | undefined Plc_serializable_keys: string[] | undefined Pprofile: ModelProfile

A path to the module that contains the class, eg. ["langchain", "llms"]

Methods

M_callWithConfig M_combineLLMOutput→ Record<string, any> | undefined M_generate→ Promise<ChatResult>M_generateCached→ Promise<LLMResult & __type>M_getOptionsList M_getSerializedCacheKeyParametersForCall→ string

Internal method that handles batching and configuration for a runnable

M_identifyingParams→ Record<string, any>

Create a unique cache key for a specific call to a specific language model.

M_llmType→ string M_modelType→ string M_separateRunnableConfigFromCallOptions M_separateRunnableConfigFromCallOptionsCompat M_streamIterator→ AsyncGenerator<RunOutput>

Get the identifying parameters of the LLM.

M_streamLog M_streamResponseChunks→ AsyncGenerator<ChatGenerationChunk>M_transformStreamWithConfig Massign→ Runnable

Default streaming implementation.

MasTool→ RunnableToolLike<InteropZodType<ToolCall<string, Record<string, any>> | T>, RunOutput>

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

Convert a runnable to a tool. Return a new instance of RunnableToolLike

MbindTools→ Runnable<BaseLanguageModelInput, OutputMessageType, CallOptions>

Default implementation of batch, which calls invoke N times.

Mgenerate→ Promise<LLMResult>

Bind tool-like objects to this chat model.

MgeneratePrompt→ Promise<LLMResult>MgetGraph→ Graph MgetLsParams→ LangSmithParams MgetName→ string MgetNumTokens→ Promise<number>

Generates chat based on the input messages.

Get the number of tokens in the content.

MinvocationParams→ any

Minvoke→ Promise<RunOutput>

Get the parameters used to invoke the model

Method to invoke the document transformation. This method calls the

Mpipe→ Runnable<RunInput, Exclude<NewRunOutput, Error>>

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

Mserialize→ SerializedLLM Mstream→ Promise<IterableReadableStream<RunOutput>>

Create a new runnable sequence that runs each individual runnable in series,

Stream output in chunks.

Generate a stream of events emitted by the internal steps of the runnable.

MtoJSON→ Serialized MtoJSONNotImplemented→ SerializedNotImplemented Mtransform→ AsyncGenerator<RunOutput>

Stream all output from a runnable, as reported to the callback system.

MwithConfig→ Runnable<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Default implementation of transform, which buffers input and then calls stream.

MwithFallbacks→ RunnableWithFallbacks<RunInput, RunOutput>

Bind config to a Runnable, returning a new Runnable.

MwithListeners→ Runnable<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Create a new runnable from the current one that will try invoking

MwithRetry→ RunnableRetry<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Bind lifecycle listeners to a Runnable, returning a new Runnable.

MwithStructuredOutput→ Runnable<BaseLanguageModelInput, RunOutput>

Add retry logic to an existing runnable.

M_convertInputToPromptValue Mdeserialize→ Promise<BaseLanguageModel<any, BaseLanguageModelCallOptions>>MisRunnable→ thing is Runnable<any, any, RunnableConfig<Record<string, any>>>Mlc_name→ string

Model wrapper that returns outputs formatted to match the given schema.

Pcache: BaseCache<Generation[]>Pcallbacks: Callbacks

The name of the serializable. Override to provide an alias or

Inherited fromBaseLanguageModel

Properties

Callbacks for this call and any sub-calls (eg. a Chain calling an LLM).

Pcaller: AsyncCaller

Plc_kwargs: SerializedFields Plc_namespace: ["langchain_core", "callbacks", string]

The async caller should be used by subclasses to make any async calls,

Plc_runnable Plc_serializable: boolean Pmetadata: Record<string, unknown>Pname: string Ptags: string[]Pverbose: boolean PcallKeys: string[]Plc_aliases: __type | undefined Plc_attributes: __type | undefined Plc_id: string[]Plc_secrets: __type | undefined Plc_serializable_keys: string[] | undefined Pprofile: ModelProfile

A path to the module that contains the class, eg. ["langchain", "llms"]

Methods

M_callWithConfig M_getOptionsList M_getSerializedCacheKeyParametersForCall→ string

Internal method that handles batching and configuration for a runnable

M_identifyingParams→ Record<string, any>

Create a unique cache key for a specific call to a specific language model.

M_llmType→ string M_modelType→ string M_separateRunnableConfigFromCallOptions M_streamIterator→ AsyncGenerator<RunOutput>

Get the identifying parameters of the LLM.

M_streamLog M_transformStreamWithConfig Massign→ Runnable

Default streaming implementation.

MasTool→ RunnableToolLike<InteropZodType<ToolCall<string, Record<string, any>> | T>, RunOutput>

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

Convert a runnable to a tool. Return a new instance of RunnableToolLike

MgeneratePrompt→ Promise<LLMResult>MgetGraph→ Graph MgetName→ string MgetNumTokens→ Promise<number>

Default implementation of batch, which calls invoke N times.

Minvoke→ Promise<RunOutput>

Get the number of tokens in the content.

Method to invoke the document transformation. This method calls the

Mpipe→ Runnable<RunInput, Exclude<NewRunOutput, Error>>

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

Mserialize→ SerializedLLM Mstream→ Promise<IterableReadableStream<RunOutput>>

Create a new runnable sequence that runs each individual runnable in series,

Stream output in chunks.

Generate a stream of events emitted by the internal steps of the runnable.

MtoJSON→ Serialized MtoJSONNotImplemented→ SerializedNotImplemented Mtransform→ AsyncGenerator<RunOutput>

Stream all output from a runnable, as reported to the callback system.

MwithConfig→ Runnable<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Default implementation of transform, which buffers input and then calls stream.

MwithFallbacks→ RunnableWithFallbacks<RunInput, RunOutput>

Bind config to a Runnable, returning a new Runnable.

MwithListeners→ Runnable<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Create a new runnable from the current one that will try invoking

MwithRetry→ RunnableRetry<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Bind lifecycle listeners to a Runnable, returning a new Runnable.

MwithStructuredOutput→ Runnable<BaseLanguageModelInput, RunOutput>

Add retry logic to an existing runnable.

Model wrapper that returns outputs formatted to match the given schema.

The name of the serializable. Override to provide an alias or

Inherited fromBaseLangChain

Properties

Pcallbacks: Callbacks

Plc_kwargs: SerializedFields Plc_namespace: ["langchain_core", "callbacks", string]

Callbacks for this call and any sub-calls (eg. a Chain calling an LLM).

Plc_runnable Plc_serializable: boolean Pmetadata: Record<string, unknown>Pname: string Ptags: string[]Pverbose: boolean Plc_aliases: __type | undefined Plc_attributes: __type | undefined Plc_id: string[]Plc_secrets: __type | undefined Plc_serializable_keys: string[] | undefined

A path to the module that contains the class, eg. ["langchain", "llms"]

Methods

M_callWithConfig M_getOptionsList M_separateRunnableConfigFromCallOptions M_streamIterator→ AsyncGenerator<RunOutput>

Internal method that handles batching and configuration for a runnable

M_streamLog M_transformStreamWithConfig Massign→ Runnable

Default streaming implementation.

MasTool→ RunnableToolLike<InteropZodType<ToolCall<string, Record<string, any>> | T>, RunOutput>

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

Convert a runnable to a tool. Return a new instance of RunnableToolLike

MgetGraph→ Graph MgetName→ string Minvoke→ Promise<RunOutput>

Default implementation of batch, which calls invoke N times.

Method to invoke the document transformation. This method calls the

Mpipe→ Runnable<RunInput, Exclude<NewRunOutput, Error>>

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

Mstream→ Promise<IterableReadableStream<RunOutput>>

Create a new runnable sequence that runs each individual runnable in series,

Stream output in chunks.

Generate a stream of events emitted by the internal steps of the runnable.

MtoJSON→ Serialized MtoJSONNotImplemented→ SerializedNotImplemented Mtransform→ AsyncGenerator<RunOutput>

Stream all output from a runnable, as reported to the callback system.

MwithConfig→ Runnable<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Default implementation of transform, which buffers input and then calls stream.

MwithFallbacks→ RunnableWithFallbacks<RunInput, RunOutput>

Bind config to a Runnable, returning a new Runnable.

MwithListeners→ Runnable<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Create a new runnable from the current one that will try invoking

MwithRetry→ RunnableRetry<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Bind lifecycle listeners to a Runnable, returning a new Runnable.

MisRunnable→ thing is Runnable<any, any, RunnableConfig<Record<string, any>>>Mlc_name→ string

Add retry logic to an existing runnable.

Plc_kwargs: SerializedFields Plc_namespace: ["langchain_core", "callbacks", string]

The name of the serializable. Override to provide an alias or

Inherited fromRunnable

Properties

Plc_runnable Plc_serializable: boolean Pname: string Plc_aliases: __type | undefined Plc_attributes: __type | undefined Plc_id: string[]Plc_secrets: __type | undefined Plc_serializable_keys: string[] | undefined

A path to the module that contains the class, eg. ["langchain", "llms"]

Methods

M_callWithConfig M_getOptionsList M_separateRunnableConfigFromCallOptions M_streamIterator→ AsyncGenerator<RunOutput>

Internal method that handles batching and configuration for a runnable

M_streamLog M_transformStreamWithConfig Massign→ Runnable

Default streaming implementation.

MasTool→ RunnableToolLike<InteropZodType<ToolCall<string, Record<string, any>> | T>, RunOutput>

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

Convert a runnable to a tool. Return a new instance of RunnableToolLike

MgetGraph→ Graph MgetName→ string Minvoke→ Promise<RunOutput>

Default implementation of batch, which calls invoke N times.

Method to invoke the document transformation. This method calls the

Mpipe→ Runnable<RunInput, Exclude<NewRunOutput, Error>>

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

Mstream→ Promise<IterableReadableStream<RunOutput>>

Create a new runnable sequence that runs each individual runnable in series,

Stream output in chunks.

Generate a stream of events emitted by the internal steps of the runnable.

MtoJSON→ Serialized MtoJSONNotImplemented→ SerializedNotImplemented Mtransform→ AsyncGenerator<RunOutput>

Stream all output from a runnable, as reported to the callback system.

MwithConfig→ Runnable<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Default implementation of transform, which buffers input and then calls stream.

MwithFallbacks→ RunnableWithFallbacks<RunInput, RunOutput>

Bind config to a Runnable, returning a new Runnable.

MwithListeners→ Runnable<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Create a new runnable from the current one that will try invoking

MwithRetry→ RunnableRetry<RunInput, RunOutput, RunnableConfig<Record<string, any>>>

Bind lifecycle listeners to a Runnable, returning a new Runnable.

MisRunnable→ thing is Runnable<any, any, RunnableConfig<Record<string, any>>>Mlc_name→ string

Add retry logic to an existing runnable.

Plc_kwargs: SerializedFields Plc_namespace: ["langchain_core", "callbacks", string]

The name of the serializable. Override to provide an alias or

Inherited fromSerializable

Properties

Plc_serializable: boolean Plc_aliases: __type | undefined Plc_attributes: __type | undefined Plc_id: string[]Plc_secrets: __type | undefined Plc_serializable_keys: string[] | undefined

A path to the module that contains the class, eg. ["langchain", "llms"]

Methods

MtoJSON→ Serialized MtoJSONNotImplemented→ SerializedNotImplemented Mlc_name→ string