Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat: Add support for completions and embeddings in batch API in openai_dart #425

Merged
merged 1 commit into from
May 14, 2024
Merged

feat: Add support for completions and embeddings in batch API in openai_dart #425

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion packages/openai_dart/lib/src/generated/schema/batch.dart
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ class Batch with _$Batch {
/// The object type, which is always `batch`.
required BatchObject object,

/// The endpoint to be used for all requests in the batch. Currently only `/v1/chat/completions` is supported.
/// 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.
required BatchEndpoint endpoint,

/// No Description
Expand Down
6 changes: 5 additions & 1 deletion packages/openai_dart/lib/src/generated/schema/batch_endpoint.dart
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,8 +8,12 @@ part of open_a_i_schema;
// ENUM: BatchEndpoint
// ==========================================

/// The endpoint to be used for all requests in the batch. Currently only `/v1/chat/completions` is supported.
/// 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.
enum BatchEndpoint {
@JsonValue('/v1/chat/completions')
v1ChatCompletions,
@JsonValue('/v1/embeddings')
v1Embeddings,
@JsonValue('/v1/completions')
v1Completions,
}
2 changes: 1 addition & 1 deletion packages/openai_dart/lib/src/generated/schema/create_batch_request.dart
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ class CreateBatchRequest with _$CreateBatchRequest {
/// Your input file must be formatted as a JSONL file, and must be uploaded with the purpose `batch`.
@JsonKey(name: 'input_file_id') required String inputFileId,

/// The endpoint to be used for all requests in the batch. Currently only `/v1/chat/completions` is supported.
/// 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.
required BatchEndpoint endpoint,

/// The time frame within which the batch should be processed. Currently only `24h` is supported.
Expand Down
12 changes: 6 additions & 6 deletions packages/openai_dart/lib/src/generated/schema/schema.freezed.dart
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48058,7 +48058,7 @@ mixin _$CreateBatchRequest {
@JsonKey(name: 'input_file_id')
String get inputFileId => throw _privateConstructorUsedError;

/// The endpoint to be used for all requests in the batch. Currently only `/v1/chat/completions` is supported.
/// 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.
BatchEndpoint get endpoint => throw _privateConstructorUsedError;

/// The time frame within which the batch should be processed. Currently only `24h` is supported.
Expand Down Expand Up @@ -48205,7 +48205,7 @@ class _$CreateBatchRequestImpl extends _CreateBatchRequest {
@JsonKey(name: 'input_file_id')
final String inputFileId;

/// The endpoint to be used for all requests in the batch. Currently only `/v1/chat/completions` is supported.
/// 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.
@override
final BatchEndpoint endpoint;

Expand Down Expand Up @@ -48291,7 +48291,7 @@ abstract class _CreateBatchRequest extends CreateBatchRequest {
String get inputFileId;
@override

/// The endpoint to be used for all requests in the batch. Currently only `/v1/chat/completions` is supported.
/// 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.
BatchEndpoint get endpoint;
@override

Expand Down Expand Up @@ -48321,7 +48321,7 @@ mixin _$Batch {
/// The object type, which is always `batch`.
BatchObject get object => throw _privateConstructorUsedError;

/// The endpoint to be used for all requests in the batch. Currently only `/v1/chat/completions` is supported.
/// 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.
BatchEndpoint get endpoint => throw _privateConstructorUsedError;

/// No Description
Expand Down Expand Up @@ -48766,7 +48766,7 @@ class _$BatchImpl extends _Batch {
@override
final BatchObject object;

/// The endpoint to be used for all requests in the batch. Currently only `/v1/chat/completions` is supported.
/// 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.
@override
final BatchEndpoint endpoint;

Expand Down Expand Up @@ -48986,7 +48986,7 @@ abstract class _Batch extends Batch {
BatchObject get object;
@override

/// The endpoint to be used for all requests in the batch. Currently only `/v1/chat/completions` is supported.
/// 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.
BatchEndpoint get endpoint;
@override

Expand Down
2 changes: 2 additions & 0 deletions packages/openai_dart/lib/src/generated/schema/schema.g.dart
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

6 changes: 3 additions & 3 deletions packages/openai_dart/oas/openapi_curated.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6130,8 +6130,8 @@ components:
nullable: true
BatchEndpoint:
type: string
enum: ["/v1/chat/completions"]
description: The endpoint to be used for all requests in the batch. Currently only `/v1/chat/completions` is supported.
enum: ["/v1/chat/completions", "/v1/embeddings", "/v1/completions"]
description: 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.
BatchCompletionWindow:
type: string
enum: ["24h"]
Expand Down Expand Up @@ -6268,7 +6268,7 @@ components:
description: The HTTP method to be used for the request. Currently only `POST` is supported.
url:
type: string
description: The OpenAI API relative URL to be used for the request. Currently only `/v1/chat/completions` is supported.
description: The OpenAI API relative URL to be used for the request. Currently `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions` are supported.
BatchRequestOutput:
type: object
description: The per-line object of the batch output and error files
Expand Down
Loading