langchain.js
    Preparing search index...

    Class LLMChain<T, Model>

    Chain to run queries against LLMs.

    import { ChatPromptTemplate } from "@langchain/core/prompts";
    import { ChatOpenAI } from "@langchain/openai";

    const prompt = ChatPromptTemplate.fromTemplate("Tell me a {adjective} joke");
    const llm = new ChatOpenAI({ model: "gpt-4o-mini" });
    const chain = prompt.pipe(llm);

    const response = await chain.invoke({ adjective: "funny" });

    Type Parameters

    • T extends string | object = string
    • Model extends LLMType = LLMType

    Hierarchy (View Summary)

    Implements

    Index

    Constructors

    constructor

    Properties

    lc_serializable llm llmKwargs? memory? outputKey outputParser? prompt

    Accessors

    inputKeys lc_namespace outputKeys

    Methods

    _chainType _formatValues _getNumTokens apply call invoke predict prepOutputs run serialize deserialize lc_name

    Constructors

    Properties

    lc_serializable: boolean = true
    llm: Model

    LLM Wrapper to use

    llmKwargs?: CallOptionsIfAvailable<Model>

    Kwargs to pass to LLM

    memory?: any
    outputKey: string = "text"

    Key to use for output, defaults to text

    outputParser?: any

    OutputParser to use

    prompt: BasePromptTemplate

    Prompt object to use

    Accessors

    • get inputKeys(): any

      Returns any

    • get lc_namespace(): string[]

      Returns string[]

    • get outputKeys(): string[]

      Returns string[]

    Methods

    _chainType

    • _chainType(): "llm"

      Return the string type key uniquely identifying this class of chain.

      Returns "llm"

    Protected_formatValues

    • _formatValues(values: any): Promise<any>

      Parameters

      • values: any

      Returns Promise<any>

    _getNumTokens

    • _getNumTokens(text: string): Promise<number>

      Parameters

      • text: string

      Returns Promise<number>

    • Parameters

      • inputs: ChainValues[]
      • Optionalconfig: any[]

      Returns Promise<ChainValues[]>

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

      Call the chain on all inputs in the list

    • Run the core logic of this chain and add to output if desired.

      Wraps _call and handles memory.

      Parameters

      • values: any
      • Optionalconfig: any

      Returns Promise<ChainValues>

    • Invoke the chain with the provided input and returns the output.

      Parameters

      • input: ChainValues

        Input values for the chain run.

      • Optionaloptions: any

      Returns Promise<ChainValues>

      Promise that resolves with the output of the chain run.

    • Format prompt with values and pass to LLM

      Parameters

      • values: any

        keys to pass to prompt template

      • OptionalcallbackManager: any

        CallbackManager to use

      Returns Promise<T>

      Completion from LLM.

      llm.predict({ adjective: "funny" })

    • Parameters

      • inputs: Record<string, unknown>
      • outputs: Record<string, unknown>
      • returnOnlyOutputs: boolean = false

      Returns Promise<Record<string, unknown>>

    • Parameters

      • input: any
      • Optionalconfig: any

      Returns Promise<string>

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

    • Returns string

    Settings

    Member Visibility

    On This Page

    Constructors
    Properties
    Accessors
    Methods