langchain.js
    Preparing search index...

    Class ChatVectorDBQAChain

    use ConversationalRetrievalQAChain instead.

    Hierarchy (View Summary)

    Implements

    Index

    Constructors

    Properties

    chatHistoryKey: string = "chat_history"
    combineDocumentsChain: BaseChain
    inputKey: string = "question"
    k: number = 4
    memory?: any
    outputKey: string = "result"
    questionGeneratorChain: LLMChain
    returnSourceDocuments: boolean = false
    vectorstore: VectorStoreInterface

    Accessors

    • get inputKeys(): string[]

      Returns string[]

    • get lc_namespace(): string[]

      Returns string[]

    • get outputKeys(): string[]

      Returns string[]

    Methods

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

      Returns "chat-vector-db"

    • Parameters

      • values: any

      Returns Promise<any>

    • 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.

    • Creates an instance of ChatVectorDBQAChain using a BaseLanguageModel and other options.

      Parameters

      • llm: BaseLanguageModelInterface

        Instance of BaseLanguageModel used to generate a new question.

      • vectorstore: VectorStoreInterface

        Instance of VectorStore used for vector operations.

      • options: {
            inputKey?: string;
            k?: number;
            outputKey?: string;
            qaTemplate?: string;
            questionGeneratorTemplate?: string;
            returnSourceDocuments?: boolean;
            verbose?: boolean;
        } = {}

        (Optional) Additional options for creating the ChatVectorDBQAChain instance.

      Returns ChatVectorDBQAChain

      New instance of ChatVectorDBQAChain.