Create a corpus

//native

type Vectara = {

	apiKey: string

}

/**

 * Create a corpus

 * Create a corpus, which is a container to store documents and associated metadata. This is where you 

create the unique `corpus_key` that identifies the corpus. The `corpus_key` can be custom-defined 

following your preferred naming convention, allowing you to easily manage the corpus's data and 

reference it in queries. For more information, see 

[Corpus Key Definition](https://docs.vectara.com/docs/api-reference/search-apis/search#corpus-key-definition).

 */

export async function main(

	auth: Vectara,

	body: {

		key: string

		name?: string

		description?: string

		queries_are_answers?: false | true

		documents_are_questions?: false | true

		encoder_id?: string

		encoder_name?: string

		filter_attributes?: {

			name: string

			level: 'document' | 'part'

			description?: string

			indexed?: false | true

			type:

				| 'boolean'

				| 'integer'

				| 'real_number'

				| 'text'

				| 'list[integer]'

				| 'list[real_number]'

				| 'list[text]'

		}[]

		custom_dimensions?: {

			name: string

			description?: string

			indexing_default?: number

			querying_default?: number

		}[]

	}

) {

	const url = new URL(`https://api.vectara.io/v2/corpora`)

	const response = await fetch(url, {

		method: 'POST',

		headers: {

			'Content-Type': 'application/json',

			'x-api-key': auth.apiKey

		},

		body: JSON.stringify(body)

	})

	if (!response.ok) {

		const text = await response.text()

		throw new Error(`${response.status} ${text}`)

	}

	return await response.json()

}