The GradientLLM class is used to interact with Gradient AI inference Endpoint models. This requires your Gradient AI Access Token which is autoloaded if not specified.

Hierarchy

  • LLM<BaseLLMCallOptions>
    • GradientLLM

Constructors

Properties

ParsedCallOptions: Omit<BaseLLMCallOptions,
    | "tags"
    | "configurable"
    | "recursionLimit"
    | "runName"
    | "metadata"
    | "callbacks"
    | "runId">
adapterId?: string
cache?: BaseCache<Generation[]>
callbacks?: Callbacks
caller: AsyncCaller

The async caller should be used by subclasses to make any async calls, which will thus benefit from the concurrency and retry logic.

gradientAccessKey?: string
inferenceParameters?: Record<string, unknown>
metadata?: Record<string, unknown>
model: any
modelSlug: string = "llama2-7b-chat"
name?: string
tags?: string[]
verbose: boolean

Whether to print out response text.

workspaceId?: string

Accessors

  • get callKeys(): string[]
  • Keys that the language model accepts as call options.

    Returns string[]

Methods

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

    Type Parameters

    • T extends BaseLanguageModelInput = BaseLanguageModelInput

    Parameters

    • fields: {
          description?: string;
          name?: string;
          schema: ZodType<T, ZodTypeDef, T>;
      }
      • Optionaldescription?: string

        The description of the tool. Falls back to the description on the Zod schema if not provided, or undefined if neither are provided.

      • Optionalname?: string

        The name of the tool. If not provided, it will default to the name of the runnable.

      • schema: ZodType<T, ZodTypeDef, T>

        The Zod schema for the input of the tool. Infers the Zod type from the input type of the runnable.

    Returns RunnableToolLike<ZodType<ToolCall | T, ZodTypeDef, ToolCall | T>, string>

    An instance of RunnableToolLike which is a runnable that can be used as a tool.

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

    Parameters

    • mapping: RunnableMapLike<Record<string, unknown>, Record<string, unknown>>

    Returns Runnable<any, any, RunnableConfig<Record<string, any>>>

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

    Parameters

    • inputs: BaseLanguageModelInput[]

      Array of inputs to each batch call.

    • Optionaloptions: Partial<BaseLLMCallOptions> | Partial<BaseLLMCallOptions>[]

      Either a single call options object to apply to each batch call or an array for each call.

    • OptionalbatchOptions: RunnableBatchOptions & {
          returnExceptions?: false;
      }

    Returns Promise<string[]>

    An array of RunOutputs, or mixed RunOutputs and errors if batchOptions.returnExceptions is set

  • Parameters

    • inputs: BaseLanguageModelInput[]
    • Optionaloptions: Partial<BaseLLMCallOptions> | Partial<BaseLLMCallOptions>[]
    • OptionalbatchOptions: RunnableBatchOptions & {
          returnExceptions: true;
      }

    Returns Promise<(string | Error)[]>

  • Parameters

    • inputs: BaseLanguageModelInput[]
    • Optionaloptions: Partial<BaseLLMCallOptions> | Partial<BaseLLMCallOptions>[]
    • OptionalbatchOptions: RunnableBatchOptions

    Returns Promise<(string | Error)[]>

  • Bind arguments to a Runnable, returning a new Runnable.

    Parameters

    • kwargs: Partial<BaseLLMCallOptions>

    Returns Runnable<BaseLanguageModelInput, string, BaseLLMCallOptions>

    A new RunnableBinding that, when invoked, will apply the bound args.

  • Parameters

    • prompt: string
    • Optionaloptions: string[] | BaseLLMCallOptions
    • Optionalcallbacks: Callbacks

    Returns Promise<string>

    Use .invoke() instead. Will be removed in 0.2.0. Convenience wrapper for generate that takes in a single string prompt and returns a single string output.

  • Run the LLM on the given prompts and input, handling caching.

    Parameters

    • prompts: string[]
    • Optionaloptions: string[] | BaseLLMCallOptions
    • Optionalcallbacks: Callbacks

    Returns Promise<LLMResult>

  • This method takes prompt values, options, and callbacks, and generates a result based on the prompts.

    Parameters

    • promptValues: BasePromptValueInterface[]

      Prompt values for the LLM.

    • Optionaloptions: string[] | BaseLLMCallOptions

      Options for the LLM call.

    • Optionalcallbacks: Callbacks

      Callbacks for the LLM call.

    Returns Promise<LLMResult>

    An LLMResult based on the prompts.

  • Parameters

    • Optional_: RunnableConfig<Record<string, any>>

    Returns Graph

  • Parameters

    • Optionalsuffix: string

    Returns string

  • Parameters

    • content: MessageContent

    Returns Promise<number>

  • Get the parameters used to invoke the model

    Parameters

    • Optional_options: Omit<BaseLLMCallOptions,
          | "tags"
          | "configurable"
          | "recursionLimit"
          | "runName"
          | "metadata"
          | "callbacks"
          | "runId">

    Returns any

  • This method takes an input and options, and returns a string. It converts the input to a prompt value and generates a result based on the prompt.

    Parameters

    • input: BaseLanguageModelInput

      Input for the LLM.

    • Optionaloptions: BaseLLMCallOptions

      Options for the LLM call.

    Returns Promise<string>

    A string result based on the prompt.

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

    Returns Runnable<BaseLanguageModelInput[], string[], BaseLLMCallOptions>

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

    Parameters

    • keys: string | string[]

    Returns Runnable<any, any, RunnableConfig<Record<string, any>>>

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

    Type Parameters

    • NewRunOutput

    Parameters

    • coerceable: RunnableLike<string, NewRunOutput, RunnableConfig<Record<string, any>>>

      A runnable, function, or object whose values are functions or runnables.

    Returns Runnable<BaseLanguageModelInput, Exclude<NewRunOutput, Error>, RunnableConfig<Record<string, any>>>

    A new runnable sequence.

  • Parameters

    • text: string

      Input text for the prediction.

    • Optionaloptions: string[] | BaseLLMCallOptions

      Options for the LLM call.

    • Optionalcallbacks: Callbacks

      Callbacks for the LLM call.

    Returns Promise<string>

    A prediction based on the input text.

    Use .invoke() instead. Will be removed in 0.2.0.

    This method is similar to call, but it's used for making predictions based on the input text.

  • Parameters

    • messages: BaseMessage[]

      A list of messages for the prediction.

    • Optionaloptions: string[] | BaseLLMCallOptions

      Options for the LLM call.

    • Optionalcallbacks: Callbacks

      Callbacks for the LLM call.

    Returns Promise<BaseMessage>

    A predicted message based on the list of messages.

    Use .invoke() instead. Will be removed in 0.2.0.

    This method takes a list of messages, options, and callbacks, and returns a predicted message.

  • Returns SerializedLLM

    Return a json-like object representing this LLM.

  • Stream output in chunks.

    Parameters

    • input: BaseLanguageModelInput
    • Optionaloptions: Partial<BaseLLMCallOptions>

    Returns Promise<IterableReadableStream<string>>

    A readable stream that is also an iterable.

  • 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                | 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]]} | AIMessageChunk(content="hello world")           |
    +----------------------+------------------+---------------------------------+-----------------------------------------------+-------------------------------------------------+
    | on_llm_start         | [model name]     |                                 | {'input': 'hello'}                            |                                                 |
    +----------------------+------------------+---------------------------------+-----------------------------------------------+-------------------------------------------------+
    | on_llm_stream        | [model name]     | 'Hello'                         |                                               |                                                 |
    +----------------------+------------------+---------------------------------+-----------------------------------------------+-------------------------------------------------+
    | on_llm_end           | [model name]     |                                 | 'Hello human!'                                |                                                 |
    +----------------------+------------------+---------------------------------+-----------------------------------------------+-------------------------------------------------+
    | on_chain_start       | some_runnable    |                                 |                                               |                                                 |
    +----------------------+------------------+---------------------------------+-----------------------------------------------+-------------------------------------------------+
    | on_chain_stream      | some_runnable    | "hello world!, goodbye world!"  |                                               |                                                 |
    +----------------------+------------------+---------------------------------+-----------------------------------------------+-------------------------------------------------+
    | on_chain_end         | some_runnable    |                                 | [Document(...)]                               | "hello world!, goodbye world!"                  |
    +----------------------+------------------+---------------------------------+-----------------------------------------------+-------------------------------------------------+
    | on_tool_start        | some_tool        |                                 | {"x": 1, "y": "2"}                            |                                                 |
    +----------------------+------------------+---------------------------------+-----------------------------------------------+-------------------------------------------------+
    | on_tool_end          | some_tool        |                                 |                                               | {"x": 1, "y": "2"}                              |
    +----------------------+------------------+---------------------------------+-----------------------------------------------+-------------------------------------------------+
    | on_retriever_start   | [retriever name] |                                 | {"query": "hello"}                            |                                                 |
    +----------------------+------------------+---------------------------------+-----------------------------------------------+-------------------------------------------------+
    | on_retriever_end     | [retriever name] |                                 | {"query": "hello"}                            | [Document(...), ..]                             |
    +----------------------+------------------+---------------------------------+-----------------------------------------------+-------------------------------------------------+
    | on_prompt_start      | [template_name]  |                                 | {"question": "hello"}                         |                                                 |
    +----------------------+------------------+---------------------------------+-----------------------------------------------+-------------------------------------------------+
    | on_prompt_end        | [template_name]  |                                 | {"question": "hello"}                         | ChatPromptValue(messages: [SystemMessage, ...]) |
    +----------------------+------------------+---------------------------------+-----------------------------------------------+-------------------------------------------------+
    

    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, though we suggest making it JSON serializable.  |
    +-----------+------+-----------------------------------------------------------------------------------------------------------+
    

    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);
    }
    }

    Parameters

    • input: BaseLanguageModelInput
    • options: Partial<BaseLLMCallOptions> & {
          version: "v1" | "v2";
      }
    • OptionalstreamOptions: Omit<EventStreamCallbackHandlerInput, "autoClose">

    Returns IterableReadableStream<StreamEvent>

  • Parameters

    • input: BaseLanguageModelInput
    • options: Partial<BaseLLMCallOptions> & {
          encoding: "text/event-stream";
          version: "v1" | "v2";
      }
    • OptionalstreamOptions: Omit<EventStreamCallbackHandlerInput, "autoClose">

    Returns IterableReadableStream<Uint8Array>

  • 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: BaseLanguageModelInput
    • Optionaloptions: Partial<BaseLLMCallOptions>
    • OptionalstreamOptions: Omit<LogStreamCallbackHandlerInput, "autoClose">

    Returns AsyncGenerator<RunLogPatch, any, unknown>

  • Returns Serialized

  • 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.

    Parameters

    • generator: AsyncGenerator<BaseLanguageModelInput, any, unknown>
    • options: Partial<BaseLLMCallOptions>

    Returns AsyncGenerator<string, any, unknown>

  • Bind config to a Runnable, returning a new Runnable.

    Parameters

    • config: RunnableConfig<Record<string, any>>

      New configuration parameters to attach to the new runnable.

    Returns RunnableBinding<BaseLanguageModelInput, string, BaseLLMCallOptions>

    A new RunnableBinding with a config matching what's passed.

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

    Parameters

    • fields: {
          fallbacks: Runnable<BaseLanguageModelInput, string, RunnableConfig<Record<string, any>>>[];
      } | Runnable<BaseLanguageModelInput, string, RunnableConfig<Record<string, any>>>[]

    Returns RunnableWithFallbacks<BaseLanguageModelInput, string>

    A new RunnableWithFallbacks.

  • 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.

    Parameters

    • params: {
          onEnd?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>);
          onError?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>);
          onStart?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>);
      }

      The object containing the callback functions.

      • OptionalonEnd?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>)

        Called after the runnable finishes running, with the Run object.

          • (run, config?): void | Promise<void>
          • Parameters

            • run: Run
            • Optionalconfig: RunnableConfig<Record<string, any>>

            Returns void | Promise<void>

      • OptionalonError?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>)

        Called if the runnable throws an error, with the Run object.

          • (run, config?): void | Promise<void>
          • Parameters

            • run: Run
            • Optionalconfig: RunnableConfig<Record<string, any>>

            Returns void | Promise<void>

      • OptionalonStart?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>)

        Called before the runnable starts running, with the Run object.

          • (run, config?): void | Promise<void>
          • Parameters

            • run: Run
            • Optionalconfig: RunnableConfig<Record<string, any>>

            Returns void | Promise<void>

    Returns Runnable<BaseLanguageModelInput, string, BaseLLMCallOptions>

  • Add retry logic to an existing runnable.

    Parameters

    • Optionalfields: {
          onFailedAttempt?: RunnableRetryFailedAttemptHandler;
          stopAfterAttempt?: number;
      }
      • OptionalonFailedAttempt?: RunnableRetryFailedAttemptHandler
      • OptionalstopAfterAttempt?: number

    Returns RunnableRetry<BaseLanguageModelInput, string, BaseLLMCallOptions>

    A new RunnableRetry that, when invoked, will retry according to the parameters.

  • Type Parameters

    • RunOutput extends Record<string, any> = Record<string, any>

    Parameters

    • schema: Record<string, any> | ZodType<RunOutput, ZodTypeDef, RunOutput>
    • Optionalconfig: StructuredOutputMethodOptions<false>

    Returns Runnable<BaseLanguageModelInput, RunOutput, RunnableConfig<Record<string, any>>>

  • Type Parameters

    • RunOutput extends Record<string, any> = Record<string, any>

    Parameters

    • schema: Record<string, any> | ZodType<RunOutput, ZodTypeDef, RunOutput>
    • Optionalconfig: StructuredOutputMethodOptions<true>

    Returns Runnable<BaseLanguageModelInput, {
        parsed: RunOutput;
        raw: BaseMessage;
    }, RunnableConfig<Record<string, any>>>

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

    Type Parameters

    • RunOutput extends Record<string, any> = Record<string, any>

      The output type for the Runnable, expected to be a Zod schema object for structured output validation.

    Parameters

    • schema: Record<string, any> | ZodType<RunOutput, ZodTypeDef, RunOutput>

      The schema for the structured output. Either as a Zod schema or a valid JSON schema object. If a Zod schema is passed, the returned attributes will be validated, whereas with JSON schema they will not be.

    • Optionalconfig: StructuredOutputMethodOptions<boolean>

    Returns Runnable<BaseLanguageModelInput, RunOutput, RunnableConfig<Record<string, any>>> | Runnable<BaseLanguageModelInput, {
        parsed: RunOutput;
        raw: BaseMessage;
    }, RunnableConfig<Record<string, any>>>

    A new runnable that calls the LLM with structured output.

  • Parameters

    • _data: SerializedLLM

    Returns Promise<BaseLanguageModel<any, BaseLanguageModelCallOptions>>

    Load an LLM from a json-like object describing it.

  • Parameters

    • thing: any

    Returns thing is Runnable<any, any, RunnableConfig<Record<string, any>>>