langchain.js
    Preparing search index...

    A class that extends the BaseDocumentLoader and implements the DocumentLoader interface. It represents a document loader that loads documents from an Apify dataset.

    const loader = new ApifyDatasetLoader("your-dataset-id", {
    datasetMappingFunction: (item) =>
    new Document({
    pageContent: item.text || "",
    metadata: { source: item.url },
    }),
    clientOptions: {
    token: "your-apify-token",
    },
    });

    const docs = await loader.load();

    const chain = new RetrievalQAChain();
    const res = await chain.invoke({ query: "What is LangChain?" });

    console.log(res.text);
    console.log(res.sourceDocuments.map((d) => d.metadata.source));

    Type Parameters

    • Metadata extends Record<string, any>

    Hierarchy (View Summary)

    Implements

    Index

    Constructors

    Properties

    apifyClient: ApifyClient
    caller: AsyncCaller
    datasetId: string
    datasetMappingFunction: ApifyDatasetMappingFunction<Metadata>

    Methods

    • Retrieves the dataset items from the Apify platform and applies the datasetMappingFunction to each item to create an array of Document instances.

      Returns Promise<Document<Metadata>[]>

      An array of Document instances.

    • Create an ApifyDatasetLoader by calling an Actor on the Apify platform and waiting for its results to be ready.

      Type Parameters

      • Metadata extends Record<string, any>

      Parameters

      • actorId: string

        The ID or name of the Actor on the Apify platform.

      • input: Record<string | number, unknown>

        The input object of the Actor that you're trying to run.

      • config: {
            callOptions?: ActorCallOptions;
            clientOptions?: ApifyClientOptions;
            datasetMappingFunction: ApifyDatasetMappingFunction<Metadata>;
        }

        Options specifying settings for the Actor run.

        • OptionalcallOptions?: ActorCallOptions
        • OptionalclientOptions?: ApifyClientOptions
        • datasetMappingFunction: ApifyDatasetMappingFunction<Metadata>

          A function that takes a single object (an Apify dataset item) and converts it to an instance of the Document class.

      Returns Promise<ApifyDatasetLoader<Metadata>>

      An instance of ApifyDatasetLoader with the results from the Actor run.

    • Create an ApifyDatasetLoader by calling a saved Actor task on the Apify platform and waiting for its results to be ready.

      Type Parameters

      • Metadata extends Record<string, any>

      Parameters

      • taskId: string

        The ID or name of the task on the Apify platform.

      • input: Record<string | number, unknown>

        The input object of the task that you're trying to run. Overrides the task's saved input.

      • config: {
            callOptions?: TaskCallOptions;
            clientOptions?: ApifyClientOptions;
            datasetMappingFunction: ApifyDatasetMappingFunction<Metadata>;
        }

        Options specifying settings for the task run.

        • OptionalcallOptions?: TaskCallOptions

          Options specifying settings for the task run.

        • OptionalclientOptions?: ApifyClientOptions

          Options specifying settings for the Apify client.

        • datasetMappingFunction: ApifyDatasetMappingFunction<Metadata>

          A function that takes a single object (an Apify dataset item) and converts it to an instance of the Document class.

      Returns Promise<ApifyDatasetLoader<Metadata>>

      An instance of ApifyDatasetLoader with the results from the task's run.