import type * as VoyageAI from "../../index.js"; /** * @example * { * inputs: [{}], * model: "model" * } */ export interface MultimodalEmbedRequest { /** * A list of multimodal inputs to be vectorized. * A single input in the list is a dictionary containing a single key "content", whose value represents a sequence of text and images. *

The value of "content" is a list of dictionaries, each representing a single piece of text or image. The dictionaries have four possible keys: *
1. type: Specifies the type of the piece of the content. Allowed values are text, image_url, or image_base64.
2. text: Only present when type is text. The value should be a text string.
3. image_base64: Only present when type is image_base64. The value should be a Base64-encoded image in the data URL format data:[<mediatype>];base64,<data>. Currently supported mediatypes are: image/png, image/jpeg, image/webp, and image/gif.
4. image_url: Only present when type is image_url. The value should be a URL linking to the image. We support PNG, JPEG, WEBP, and GIF images.
*

Note: Only one of the keys, image_base64 or image_url, should be present in each dictionary for image data. Consistency is required within a request, meaning each request should use either image_base64 or image_url exclusively for images, not both.
*
*

Example payload where inputs contains an image as a URL

*
* The inputs list contains a single input, which consists of a piece of text and an image (which is provided via a URL). *


     *       {
     *         "inputs": [
     *           {
     *             "content": [
     *               {
     *                 "type": "text",
     *                 "text": "This is a banana."
     *               },
     *               {
     *                 "type": "image_url",
     *                 "image_url": "https://raw.githubusercontent.com/voyage-ai/voyage-multimodal-3/refs/heads/main/images/banana.jpg"
     *               }
     *             ]
     *           }
     *         ],
     *         "model": "voyage-multimodal-3"
     *       }
     *

Example payload where inputs contains a Base64 image

*
* Below is an equivalent example to the one above where the image content is a Base64 image instead of a URL. (Base64 images can be lengthy, so the example only shows a shortened version.) *


     *       {
     *         "inputs": [
     *           {
     *             "content": [
     *               {
     *                 "type": "text",
     *                 "text": "This is a banana."
     *               },
     *               {
     *                 "type": "image_base64",
     *                 "image_base64": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAA..."
     *               }
     *             ]
     *           }
     *         ],
     *         "model": "voyage-multimodal-3"
     *       }
     *

*/ inputs: VoyageAI.MultimodalEmbedRequestInputsItem[]; /** Name of the model. Supported models are: `voyage-multimodal-3` and `voyage-multimodal-3.5`. */ model: string; /** * Type of the input text. Defaults to `null`. Other options: `query`, `document`. *

When input_type is null, the embedding model directly converts your input data into numerical vectors. For retrieval/search purposes—where an input (called a "query") is used to search for relevant pieces of information (referred to as "documents")—we recommend specifying whether your inputs are intended as queries or documents by setting input_type to query or document, respectively. In these cases, Voyage prepends a prompt to your input before vectorizing it, helping the model create more effective vectors tailored for retrieval/search tasks. Since inputs can be multimodal, queries and documents can be text, images, or an interleaving of both modalities. Embeddings generated with and without the input_type argument are compatible.
For transparency, the following prompts are prepended to your input.

For query, the prompt is "Represent the query for retrieving supporting documents: ".
For document, the prompt is "Represent the query for retrieving supporting documents: ".

*/ inputType?: VoyageAI.MultimodalEmbedRequestInputType; /** Whether to truncate the input texts to fit within the context length. Defaults to `true`.

If `true`, over-length input texts will be truncated to fit within the context length, before vectorized by the embedding model.
If `false`, an error will be raised if any given text exceeds the context length.

*/ truncation?: boolean; /** Format in which the embeddings are encoded. We support two options:

If not specified (defaults to `null`): the embeddings are represented as lists of floating-point numbers;
`base64`: the embeddings are compressed to [base64](https://docs.python.org/3/library/base64.html) encodings.

*/ encodingFormat?: VoyageAI.MultimodalEmbedRequestEncodingFormat; }