@squidcloud/client
    Preparing search index...

    Interface BulkIngestionContext

    One context to stage through bulk ingestion.

    interface BulkIngestionContext {
        extractImages?: boolean;
        format?: "markdown" | "html" | "plain";
        metadata?: Record<string, unknown>;
        preferredExtractionMethod?: DocumentExtractionMethod;
        stagedObjectKey?: string;
        text?: string;
        title?: string;
        type?: "text" | "file";
    }
    Index
    extractImages? format? metadata? preferredExtractionMethod? stagedObjectKey? text? title? type?
    extractImages?: boolean

    Whether to extract images: inline markdown/HTML images for text contexts, embedded images for files.

    format?: "markdown" | "html" | "plain"

    Hint about a text context's format; only meaningful for type: 'text'.

    metadata?: Record<string, unknown>

    Optional metadata associated with the context item; mirrors BaseAiKnowledgeBaseContextRequest.metadata. Squid-reserved keys are stripped server-side, and values are validated/normalized against the target knowledge base's metadataFields schema when one is declared.

    preferredExtractionMethod?: DocumentExtractionMethod

    The preferred method for extracting data from a file context; mirrors the sync lane's field of the same name, so a caller's choice survives whichever lane a deployment routes the upload through.

    stagedObjectKey?: string

    Key returned by bulk/createUploadUrls; the server ingests the staged object as this context's file. Mutually exclusive with a positional multipart file.

    Optionaltext

    text?: string

    The text content to stage; required for type: 'text'.

    title?: string

    Title for a text context (required); optional display title for a file context.

    type?: "text" | "file"

    'text' (the default) stages a text context; 'file' consumes the next uploaded file positionally.

    Settings
    Member Visibility

    On This Page
    Properties