@depup/openai 6.31.0-depup.0

package/src/resources/chat/completions/index.ts

@@ -0,0 +1,50 @@
+// File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+export {
+  Completions,
+  type ChatCompletion,
+  type ChatCompletionAllowedToolChoice,
+  type ChatCompletionAssistantMessageParam,
+  type ChatCompletionAudio,
+  type ChatCompletionAudioParam,
+  type ChatCompletionChunk,
+  type ChatCompletionContentPart,
+  type ChatCompletionContentPartImage,
+  type ChatCompletionContentPartInputAudio,
+  type ChatCompletionContentPartRefusal,
+  type ChatCompletionContentPartText,
+  type ChatCompletionCustomTool,
+  type ChatCompletionDeleted,
+  type ChatCompletionDeveloperMessageParam,
+  type ChatCompletionFunctionCallOption,
+  type ChatCompletionFunctionMessageParam,
+  type ChatCompletionFunctionTool,
+  type ChatCompletionMessage,
+  type ChatCompletionMessageCustomToolCall,
+  type ChatCompletionMessageFunctionToolCall,
+  type ChatCompletionMessageParam,
+  type ChatCompletionMessageToolCall,
+  type ChatCompletionModality,
+  type ChatCompletionNamedToolChoice,
+  type ChatCompletionNamedToolChoiceCustom,
+  type ChatCompletionPredictionContent,
+  type ChatCompletionRole,
+  type ChatCompletionStoreMessage,
+  type ChatCompletionStreamOptions,
+  type ChatCompletionSystemMessageParam,
+  type ChatCompletionTokenLogprob,
+  type ChatCompletionTool,
+  type ChatCompletionToolChoiceOption,
+  type ChatCompletionToolMessageParam,
+  type ChatCompletionUserMessageParam,
+  type ChatCompletionAllowedTools,
+  type ChatCompletionCreateParams,
+  type ChatCompletionCreateParamsNonStreaming,
+  type ChatCompletionCreateParamsStreaming,
+  type ChatCompletionUpdateParams,
+  type ChatCompletionListParams,
+  type ChatCompletionStoreMessagesPage,
+  type ChatCompletionsPage,
+} from './completions';
+export * from './completions';
+export { Messages, type MessageListParams } from './messages';

package/src/resources/chat/completions/messages.ts

@@ -0,0 +1,53 @@
+// File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+import { APIResource } from '../../../core/resource';
+import * as CompletionsAPI from './completions';
+import { ChatCompletionStoreMessagesPage } from './completions';
+import { CursorPage, type CursorPageParams, PagePromise } from '../../../core/pagination';
+import { RequestOptions } from '../../../internal/request-options';
+import { path } from '../../../internal/utils/path';
+
+/**
+ * Given a list of messages comprising a conversation, the model will return a response.
+ */
+export class Messages extends APIResource {
+  /**
+   * Get the messages in a stored chat completion. Only Chat Completions that have
+   * been created with the `store` parameter set to `true` will be returned.
+   *
+   * @example
+   * ```ts
+   * // Automatically fetches more pages as needed.
+   * for await (const chatCompletionStoreMessage of client.chat.completions.messages.list(
+   *   'completion_id',
+   * )) {
+   *   // ...
+   * }
+   * ```
+   */
+  list(
+    completionID: string,
+    query: MessageListParams | null | undefined = {},
+    options?: RequestOptions,
+  ): PagePromise<ChatCompletionStoreMessagesPage, CompletionsAPI.ChatCompletionStoreMessage> {
+    return this._client.getAPIList(
+      path`/chat/completions/${completionID}/messages`,
+      CursorPage<CompletionsAPI.ChatCompletionStoreMessage>,
+      { query, ...options },
+    );
+  }
+}
+
+export interface MessageListParams extends CursorPageParams {
+  /**
+   * Sort order for messages by timestamp. Use `asc` for ascending order or `desc`
+   * for descending order. Defaults to `asc`.
+   */
+  order?: 'asc' | 'desc';
+}
+
+export declare namespace Messages {
+  export { type MessageListParams as MessageListParams };
+}
+
+export { type ChatCompletionStoreMessagesPage };

package/src/resources/chat/completions.ts

@@ -0,0 +1,3 @@
+// File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+export * from './completions/index';

package/src/resources/chat/index.ts

@@ -0,0 +1,49 @@
+// File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+export { Chat } from './chat';
+export {
+  Completions,
+  type ChatCompletion,
+  type ChatCompletionAllowedToolChoice,
+  type ChatCompletionAssistantMessageParam,
+  type ChatCompletionAudio,
+  type ChatCompletionAudioParam,
+  type ChatCompletionChunk,
+  type ChatCompletionContentPart,
+  type ChatCompletionContentPartImage,
+  type ChatCompletionContentPartInputAudio,
+  type ChatCompletionContentPartRefusal,
+  type ChatCompletionContentPartText,
+  type ChatCompletionCustomTool,
+  type ChatCompletionDeleted,
+  type ChatCompletionDeveloperMessageParam,
+  type ChatCompletionFunctionCallOption,
+  type ChatCompletionFunctionMessageParam,
+  type ChatCompletionFunctionTool,
+  type ChatCompletionMessage,
+  type ChatCompletionMessageCustomToolCall,
+  type ChatCompletionMessageFunctionToolCall,
+  type ChatCompletionMessageParam,
+  type ChatCompletionMessageToolCall,
+  type ChatCompletionModality,
+  type ChatCompletionNamedToolChoice,
+  type ChatCompletionNamedToolChoiceCustom,
+  type ChatCompletionPredictionContent,
+  type ChatCompletionRole,
+  type ChatCompletionStoreMessage,
+  type ChatCompletionStreamOptions,
+  type ChatCompletionSystemMessageParam,
+  type ChatCompletionTokenLogprob,
+  type ChatCompletionTool,
+  type ChatCompletionToolChoiceOption,
+  type ChatCompletionToolMessageParam,
+  type ChatCompletionUserMessageParam,
+  type ChatCompletionAllowedTools,
+  type ChatCompletionCreateParams,
+  type ChatCompletionCreateParamsNonStreaming,
+  type ChatCompletionCreateParamsStreaming,
+  type ChatCompletionUpdateParams,
+  type ChatCompletionListParams,
+  type ChatCompletionStoreMessagesPage,
+  type ChatCompletionsPage,
+} from './completions/index';

package/src/resources/chat.ts

@@ -0,0 +1,3 @@
+// File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+export * from './chat/index';

package/src/resources/completions.ts

@@ -0,0 +1,400 @@
+// File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+import { APIResource } from '../core/resource';
+import * as CompletionsAPI from './completions';
+import * as ChatCompletionsAPI from './chat/completions/completions';
+import { APIPromise } from '../core/api-promise';
+import { Stream } from '../core/streaming';
+import { RequestOptions } from '../internal/request-options';
+
+/**
+ * Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.
+ */
+export class Completions extends APIResource {
+  /**
+   * Creates a completion for the provided prompt and parameters.
+   *
+   * Returns a completion object, or a sequence of completion objects if the request
+   * is streamed.
+   *
+   * @example
+   * ```ts
+   * const completion = await client.completions.create({
+   *   model: 'string',
+   *   prompt: 'This is a test.',
+   * });
+   * ```
+   */
+  create(body: CompletionCreateParamsNonStreaming, options?: RequestOptions): APIPromise<Completion>;
+  create(body: CompletionCreateParamsStreaming, options?: RequestOptions): APIPromise<Stream<Completion>>;
+  create(
+    body: CompletionCreateParamsBase,
+    options?: RequestOptions,
+  ): APIPromise<Stream<Completion> | Completion>;
+  create(
+    body: CompletionCreateParams,
+    options?: RequestOptions,
+  ): APIPromise<Completion> | APIPromise<Stream<Completion>> {
+    return this._client.post('/completions', { body, ...options, stream: body.stream ?? false }) as
+      | APIPromise<Completion>
+      | APIPromise<Stream<Completion>>;
+  }
+}
+
+/**
+ * Represents a completion response from the API. Note: both the streamed and
+ * non-streamed response objects share the same shape (unlike the chat endpoint).
+ */
+export interface Completion {
+  /**
+   * A unique identifier for the completion.
+   */
+  id: string;
+
+  /**
+   * The list of completion choices the model generated for the input prompt.
+   */
+  choices: Array<CompletionChoice>;
+
+  /**
+   * The Unix timestamp (in seconds) of when the completion was created.
+   */
+  created: number;
+
+  /**
+   * The model used for completion.
+   */
+  model: string;
+
+  /**
+   * The object type, which is always "text_completion"
+   */
+  object: 'text_completion';
+
+  /**
+   * This fingerprint represents the backend configuration that the model runs with.
+   *
+   * Can be used in conjunction with the `seed` request parameter to understand when
+   * backend changes have been made that might impact determinism.
+   */
+  system_fingerprint?: string;
+
+  /**
+   * Usage statistics for the completion request.
+   */
+  usage?: CompletionUsage;
+}
+
+export interface CompletionChoice {
+  /**
+   * The reason the model stopped generating tokens. This will be `stop` if the model
+   * hit a natural stop point or a provided stop sequence, `length` if the maximum
+   * number of tokens specified in the request was reached, or `content_filter` if
+   * content was omitted due to a flag from our content filters.
+   */
+  finish_reason: 'stop' | 'length' | 'content_filter';
+
+  index: number;
+
+  logprobs: CompletionChoice.Logprobs | null;
+
+  text: string;
+}
+
+export namespace CompletionChoice {
+  export interface Logprobs {
+    text_offset?: Array<number>;
+
+    token_logprobs?: Array<number>;
+
+    tokens?: Array<string>;
+
+    top_logprobs?: Array<{ [key: string]: number }>;
+  }
+}
+
+/**
+ * Usage statistics for the completion request.
+ */
+export interface CompletionUsage {
+  /**
+   * Number of tokens in the generated completion.
+   */
+  completion_tokens: number;
+
+  /**
+   * Number of tokens in the prompt.
+   */
+  prompt_tokens: number;
+
+  /**
+   * Total number of tokens used in the request (prompt + completion).
+   */
+  total_tokens: number;
+
+  /**
+   * Breakdown of tokens used in a completion.
+   */
+  completion_tokens_details?: CompletionUsage.CompletionTokensDetails;
+
+  /**
+   * Breakdown of tokens used in the prompt.
+   */
+  prompt_tokens_details?: CompletionUsage.PromptTokensDetails;
+}
+
+export namespace CompletionUsage {
+  /**
+   * Breakdown of tokens used in a completion.
+   */
+  export interface CompletionTokensDetails {
+    /**
+     * When using Predicted Outputs, the number of tokens in the prediction that
+     * appeared in the completion.
+     */
+    accepted_prediction_tokens?: number;
+
+    /**
+     * Audio input tokens generated by the model.
+     */
+    audio_tokens?: number;
+
+    /**
+     * Tokens generated by the model for reasoning.
+     */
+    reasoning_tokens?: number;
+
+    /**
+     * When using Predicted Outputs, the number of tokens in the prediction that did
+     * not appear in the completion. However, like reasoning tokens, these tokens are
+     * still counted in the total completion tokens for purposes of billing, output,
+     * and context window limits.
+     */
+    rejected_prediction_tokens?: number;
+  }
+
+  /**
+   * Breakdown of tokens used in the prompt.
+   */
+  export interface PromptTokensDetails {
+    /**
+     * Audio input tokens present in the prompt.
+     */
+    audio_tokens?: number;
+
+    /**
+     * Cached tokens present in the prompt.
+     */
+    cached_tokens?: number;
+  }
+}
+
+export type CompletionCreateParams = CompletionCreateParamsNonStreaming | CompletionCreateParamsStreaming;
+
+export interface CompletionCreateParamsBase {
+  /**
+   * ID of the model to use. You can use the
+   * [List models](https://platform.openai.com/docs/api-reference/models/list) API to
+   * see all of your available models, or see our
+   * [Model overview](https://platform.openai.com/docs/models) for descriptions of
+   * them.
+   */
+  model: (string & {}) | 'gpt-3.5-turbo-instruct' | 'davinci-002' | 'babbage-002';
+
+  /**
+   * The prompt(s) to generate completions for, encoded as a string, array of
+   * strings, array of tokens, or array of token arrays.
+   *
+   * Note that <|endoftext|> is the document separator that the model sees during
+   * training, so if a prompt is not specified the model will generate as if from the
+   * beginning of a new document.
+   */
+  prompt: string | Array<string> | Array<number> | Array<Array<number>> | null;
+
+  /**
+   * Generates `best_of` completions server-side and returns the "best" (the one with
+   * the highest log probability per token). Results cannot be streamed.
+   *
+   * When used with `n`, `best_of` controls the number of candidate completions and
+   * `n` specifies how many to return – `best_of` must be greater than `n`.
+   *
+   * **Note:** Because this parameter generates many completions, it can quickly
+   * consume your token quota. Use carefully and ensure that you have reasonable
+   * settings for `max_tokens` and `stop`.
+   */
+  best_of?: number | null;
+
+  /**
+   * Echo back the prompt in addition to the completion
+   */
+  echo?: boolean | null;
+
+  /**
+   * Number between -2.0 and 2.0. Positive values penalize new tokens based on their
+   * existing frequency in the text so far, decreasing the model's likelihood to
+   * repeat the same line verbatim.
+   *
+   * [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
+   */
+  frequency_penalty?: number | null;
+
+  /**
+   * Modify the likelihood of specified tokens appearing in the completion.
+   *
+   * Accepts a JSON object that maps tokens (specified by their token ID in the GPT
+   * tokenizer) to an associated bias value from -100 to 100. You can use this
+   * [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs.
+   * Mathematically, the bias is added to the logits generated by the model prior to
+   * sampling. The exact effect will vary per model, but values between -1 and 1
+   * should decrease or increase likelihood of selection; values like -100 or 100
+   * should result in a ban or exclusive selection of the relevant token.
+   *
+   * As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
+   * from being generated.
+   */
+  logit_bias?: { [key: string]: number } | null;
+
+  /**
+   * Include the log probabilities on the `logprobs` most likely output tokens, as
+   * well the chosen tokens. For example, if `logprobs` is 5, the API will return a
+   * list of the 5 most likely tokens. The API will always return the `logprob` of
+   * the sampled token, so there may be up to `logprobs+1` elements in the response.
+   *
+   * The maximum value for `logprobs` is 5.
+   */
+  logprobs?: number | null;
+
+  /**
+   * The maximum number of [tokens](/tokenizer) that can be generated in the
+   * completion.
+   *
+   * The token count of your prompt plus `max_tokens` cannot exceed the model's
+   * context length.
+   * [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
+   * for counting tokens.
+   */
+  max_tokens?: number | null;
+
+  /**
+   * How many completions to generate for each prompt.
+   *
+   * **Note:** Because this parameter generates many completions, it can quickly
+   * consume your token quota. Use carefully and ensure that you have reasonable
+   * settings for `max_tokens` and `stop`.
+   */
+  n?: number | null;
+
+  /**
+   * Number between -2.0 and 2.0. Positive values penalize new tokens based on
+   * whether they appear in the text so far, increasing the model's likelihood to
+   * talk about new topics.
+   *
+   * [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
+   */
+  presence_penalty?: number | null;
+
+  /**
+   * If specified, our system will make a best effort to sample deterministically,
+   * such that repeated requests with the same `seed` and parameters should return
+   * the same result.
+   *
+   * Determinism is not guaranteed, and you should refer to the `system_fingerprint`
+   * response parameter to monitor changes in the backend.
+   */
+  seed?: number | null;
+
+  /**
+   * Not supported with latest reasoning models `o3` and `o4-mini`.
+   *
+   * Up to 4 sequences where the API will stop generating further tokens. The
+   * returned text will not contain the stop sequence.
+   */
+  stop?: string | null | Array<string>;
+
+  /**
+   * Whether to stream back partial progress. If set, tokens will be sent as
+   * data-only
+   * [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+   * as they become available, with the stream terminated by a `data: [DONE]`
+   * message.
+   * [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
+   */
+  stream?: boolean | null;
+
+  /**
+   * Options for streaming response. Only set this when you set `stream: true`.
+   */
+  stream_options?: ChatCompletionsAPI.ChatCompletionStreamOptions | null;
+
+  /**
+   * The suffix that comes after a completion of inserted text.
+   *
+   * This parameter is only supported for `gpt-3.5-turbo-instruct`.
+   */
+  suffix?: string | null;
+
+  /**
+   * What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
+   * make the output more random, while lower values like 0.2 will make it more
+   * focused and deterministic.
+   *
+   * We generally recommend altering this or `top_p` but not both.
+   */
+  temperature?: number | null;
+
+  /**
+   * An alternative to sampling with temperature, called nucleus sampling, where the
+   * model considers the results of the tokens with top_p probability mass. So 0.1
+   * means only the tokens comprising the top 10% probability mass are considered.
+   *
+   * We generally recommend altering this or `temperature` but not both.
+   */
+  top_p?: number | null;
+
+  /**
+   * A unique identifier representing your end-user, which can help OpenAI to monitor
+   * and detect abuse.
+   * [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
+   */
+  user?: string;
+}
+
+export namespace CompletionCreateParams {
+  export type CompletionCreateParamsNonStreaming = CompletionsAPI.CompletionCreateParamsNonStreaming;
+  export type CompletionCreateParamsStreaming = CompletionsAPI.CompletionCreateParamsStreaming;
+}
+
+export interface CompletionCreateParamsNonStreaming extends CompletionCreateParamsBase {
+  /**
+   * Whether to stream back partial progress. If set, tokens will be sent as
+   * data-only
+   * [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+   * as they become available, with the stream terminated by a `data: [DONE]`
+   * message.
+   * [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
+   */
+  stream?: false | null;
+}
+
+export interface CompletionCreateParamsStreaming extends CompletionCreateParamsBase {
+  /**
+   * Whether to stream back partial progress. If set, tokens will be sent as
+   * data-only
+   * [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+   * as they become available, with the stream terminated by a `data: [DONE]`
+   * message.
+   * [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
+   */
+  stream: true;
+}
+
+export declare namespace Completions {
+  export {
+    type Completion as Completion,
+    type CompletionChoice as CompletionChoice,
+    type CompletionUsage as CompletionUsage,
+    type CompletionCreateParams as CompletionCreateParams,
+    type CompletionCreateParamsNonStreaming as CompletionCreateParamsNonStreaming,
+    type CompletionCreateParamsStreaming as CompletionCreateParamsStreaming,
+  };
+}