mindee
    Preparing search index...

    Class ExtractionParameters

    Parameters accepted by the asynchronous inference v2 endpoint.

    All fields are optional except modelId.

    const params = {
    modelId: "YOUR_MODEL_ID",
    rag: true,
    alias: "YOUR_ALIAS",
    webhookIds: ["YOUR_WEBHOOK_ID_1", "YOUR_WEBHOOK_ID_2"],
    pollingOptions: {
    initialDelaySec: 2,
    delaySec: 1.5,
    }
    };

    Hierarchy (View Summary)

    Index

    Constructors

    Properties

    alias?: string

    Optional: a free-form string to tag the request with your own identifier. For example, an internal document ID, reference number, or database key. If set, it will be included in the job and result responses.

    closeFile?: boolean

    By default, the file is closed once the upload is finished. Set to false to keep it open.

    confidence?: boolean

    Calculate confidence scores for values, and fill the confidence attribute of fields. Useful for automation.

    dataSchema?: string | StringDict | DataSchema

    Dynamic changes to the data schema of the model for this inference. Not recommended, for specific use only.

    modelId: string

    Model ID to use for the inference. Required.

    polygon?: boolean

    Calculate bounding box polygons for values, and fill the locations attribute of fields.

    rag?: boolean

    Use Retrieval-Augmented Generation during inference.

    rawText?: boolean

    Extract the entire text from the document as strings, and fill the rawText attribute.

    textContext?: string

    Additional text context used by the model during inference. Not recommended, for specific use only.

    webhookIds?: string[]

    Webhook IDs to call after all processing is finished. If empty, no webhooks will be used.

    Methods