class

OpenAI::CreateBatchRequestBody

Inherits JSON::Serializable < Reference < Object

Constructors

new(input_file_id : String = "", endpoint : CreateBatchRequestBodyEndpoint = CreateBatchRequestBodyEndpoint::V1Responses, completion_window : CreateBatchRequestBodyCompletionWindow = CreateBatchRequestBodyCompletionWindow::N24H, metadata : Metadata | Nil = nil, output_expires_after : BatchFileExpirationAfter | Nil = nil)

Source

new(*, __pull_for_json_serializable pull : JSON::PullParser)

Source

Instance methods

completion_window

The time frame within which the batch should be processed. Currently only 24h is supported.

Source

completion_window=(completion_window : CreateBatchRequestBodyCompletionWindow)

The time frame within which the batch should be processed. Currently only 24h is supported.

Source

endpoint

The endpoint to be used for all requests in the batch. Currently /v1/responses, /v1/chat/completions, /v1/embeddings, /v1/completions, and /v1/moderations are supported. Note that /v1/embeddings batches are also restricted to a maximum of 50,000 embedding inputs across all requests in the batch.

Source

endpoint=(endpoint : CreateBatchRequestBodyEndpoint)

Source

input_file_id

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 200 MB in size.

Source

input_file_id=(input_file_id : 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 200 MB in size.

Source

metadata

Source

metadata=(metadata : Metadata | Nil)

Source

output_expires_after

Source

output_expires_after=(output_expires_after : BatchFileExpirationAfter | Nil)

Source