Represents the parameters for configuring WebBaseLoaders. It extends the AsyncCallerParams interface and adds additional parameters specific to web-based loaders.

interface WebBaseLoaderParams {
    headers?: HeadersInit;
    maxConcurrency?: number;
    maxRetries?: number;
    onFailedAttempt?: FailedAttemptHandler;
    selector?: any;
    textDecoder?: TextDecoder;
    timeout?: number;
}

Hierarchy (view full)

Properties

headers?: HeadersInit

The headers to use in the fetch request.

maxConcurrency?: number

The maximum number of concurrent calls that can be made. Defaults to Infinity, which means no limit.

maxRetries?: number

The maximum number of retries that can be made for a single call, with an exponential backoff between each attempt. Defaults to 6.

onFailedAttempt?: FailedAttemptHandler

Custom handler to handle failed attempts. Takes the originally thrown error object as input, and should itself throw an error if the input error is not retryable.

selector?: any

The selector to use to extract the text from the document. Defaults to "body".

Use CheerioWebBaseLoaderParams from @langchain/community/document_loaders/web/cheerio instead.

textDecoder?: TextDecoder

The text decoder to use to decode the response. Defaults to UTF-8.

timeout?: number

The timeout in milliseconds for the fetch request. Defaults to 10s.