langchain.js
    Preparing search index...

    Class representing a chain for moderating text using the OpenAI Moderation API. It extends the BaseChain class and implements the OpenAIModerationChainInput interface.

    const moderation = new OpenAIModerationChain({ throwError: true });

    const badString = "Bad naughty words from user";

    try {
    const { output: moderatedContent, results } = await moderation.call({
    input: badString,
    });

    if (results[0].category_scores["harassment/threatening"] > 0.01) {
    throw new Error("Harassment detected!");
    }

    const model = new OpenAI({ temperature: 0 });
    const promptTemplate = "Hello, how are you today {person}?";
    const prompt = new PromptTemplate({
    template: promptTemplate,
    inputVariables: ["person"],
    });
    const chain = new LLMChain({ llm: model, prompt });
    const response = await chain.call({ person: moderatedContent });
    console.log({ response });
    } catch (error) {
    console.error("Naughty words detected!");
    }

    Hierarchy (View Summary)

    Implements

    Index

    Constructors

    Properties

    caller: AsyncCaller
    client: OpenAIClient
    clientConfig: ClientOptions
    inputKey: string = "input"
    memory?: any
    openAIApiKey?: string

    Use "apiKey" instead.

    openAIOrganization?: string
    outputKey: string = "output"
    throwError: boolean

    Accessors

    • get inputKeys(): string[]

      Returns string[]

    • get lc_namespace(): string[]

      Returns string[]

    • get lc_secrets(): undefined | { [key: string]: string }

      Returns undefined | { [key: string]: string }

    • get outputKeys(): string[]

      Returns string[]

    Methods

    • Run the core logic of this chain and return the output

      Parameters

      • values: ChainValues

      Returns Promise<ChainValues>

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

      Returns string

    • Parameters

      • values: any

      Returns Promise<any>

    • Parameters

      • text: string
      • results: Moderation

      Returns string

    • 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

    • Parameters

      • values: any
      • Optionalconfig: any
      • Optionaltags: string[]

      Returns Promise<ChainValues>

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

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

      Wraps _call and handles memory.

    • 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.

    • 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.

    • Load a chain from a json-like object describing it.

      Parameters

      Returns Promise<BaseChain<ChainValues, ChainValues>>

    • Returns string