import { CreateBatchRequestBody } from "argot-open-ai/models/operations";
let value: CreateBatchRequestBody = {
inputFileId: "<id>",
endpoint: "/v1/completions",
completionWindow: "24h",
};
Field | Type | Required | Description |
---|---|---|---|
inputFileId |
string | ✔️ | The ID of an uploaded file that contains requests for the new batch. See upload file for how to upload a file. Your input file must be formatted as a JSONL file, and must be uploaded with the purpose batch . The file can contain up to 50,000 requests, and can be up to 100 MB in size. |
endpoint |
operations.Endpoint | ✔️ | The endpoint to be used for all requests in the batch. Currently /v1/chat/completions , /v1/embeddings , and /v1/completions are supported. Note that /v1/embeddings batches are also restricted to a maximum of 50,000 embedding inputs across all requests in the batch. |
completionWindow |
operations.CompletionWindow | ✔️ | The time frame within which the batch should be processed. Currently only 24h is supported. |
metadata |
Record<string, string> | ➖ | Optional custom metadata for the batch. |