@gpuai/sdk 0.3.12 → 0.3.13

package/.openapi-generator/FILES

@@ -22,6 +22,11 @@ docs/CreateRegistryCredentialRequest.md
 docs/CreateSshKeyRequest.md
 docs/CreateWebhookEndpointRequest.md
 docs/CryptoDeposit.md
+docs/Embedding.md
+docs/EmbeddingsRequest.md
+docs/EmbeddingsRequestInput.md
+docs/EmbeddingsResponse.md
+docs/EmbeddingsUsage.md
 docs/Environments.md
 docs/EnvironmentsApi.md
 docs/FileObject.md
@@ -129,6 +134,11 @@ src/models/CreateRegistryCredentialRequest.ts
 src/models/CreateSshKeyRequest.ts
 src/models/CreateWebhookEndpointRequest.ts
 src/models/CryptoDeposit.ts
+src/models/Embedding.ts
+src/models/EmbeddingsRequest.ts
+src/models/EmbeddingsRequestInput.ts
+src/models/EmbeddingsResponse.ts
+src/models/EmbeddingsUsage.ts
 src/models/Environments.ts
 src/models/FileObject.ts
 src/models/FineTuningJob.ts

package/README.md

@@ -1,4 +1,4 @@
-# @gpuai/sdk@0.3.12
+# @gpuai/sdk@0.3.13
 
 A TypeScript SDK client for the api.gpu.ai API.
 
@@ -76,6 +76,7 @@ All URIs are relative to *https://api.gpu.ai/v1*
 *GpuTypesApi* | [**listGpuTypes**](docs/GpuTypesApi.md#listgputypes) | **GET** /gpu-types | List available GPU types (no auth required)
 *InferenceApi* | [**cancelVideo**](docs/InferenceApi.md#cancelvideo) | **POST** /videos/{id}/cancel | Cancel a video generation job
 *InferenceApi* | [**createChatCompletion**](docs/InferenceApi.md#createchatcompletion) | **POST** /chat/completions | Create a chat completion (OpenAI-compatible)
+*InferenceApi* | [**createEmbeddings**](docs/InferenceApi.md#createembeddings) | **POST** /embeddings | Create embeddings (OpenAI-compatible)
 *InferenceApi* | [**createImage**](docs/InferenceApi.md#createimage) | **POST** /images/generations | Create image (OpenAI-compatible)
 *InferenceApi* | [**createVideo**](docs/InferenceApi.md#createvideo) | **POST** /videos | Create a video generation job (async)
 *InferenceApi* | [**getModel**](docs/InferenceApi.md#getmodel) | **GET** /models/{id} | Get a specific model (OpenAI-compatible)
@@ -129,6 +130,11 @@ All URIs are relative to *https://api.gpu.ai/v1*
 - [CreateSshKeyRequest](docs/CreateSshKeyRequest.md)
 - [CreateWebhookEndpointRequest](docs/CreateWebhookEndpointRequest.md)
 - [CryptoDeposit](docs/CryptoDeposit.md)
+- [Embedding](docs/Embedding.md)
+- [EmbeddingsRequest](docs/EmbeddingsRequest.md)
+- [EmbeddingsRequestInput](docs/EmbeddingsRequestInput.md)
+- [EmbeddingsResponse](docs/EmbeddingsResponse.md)
+- [EmbeddingsUsage](docs/EmbeddingsUsage.md)
 - [Environments](docs/Environments.md)
 - [FileObject](docs/FileObject.md)
 - [FineTuningJob](docs/FineTuningJob.md)
@@ -204,7 +210,7 @@ and is automatically generated by the
 [OpenAPI Generator](https://openapi-generator.tech) project:
 
 - API version: `1.0.0`
-- Package version: `0.3.12`
+- Package version: `0.3.13`
 - Generator version: `7.24.0`
 - Build package: `org.openapitools.codegen.languages.TypeScriptFetchClientCodegen`
 

package/dist/apis/InferenceApi.d.ts

@@ -12,6 +12,8 @@
 import * as runtime from '../runtime';
 import { type ChatCompletionRequest } from '../models/ChatCompletionRequest';
 import { type ChatCompletionResponse } from '../models/ChatCompletionResponse';
+import { type EmbeddingsRequest } from '../models/EmbeddingsRequest';
+import { type EmbeddingsResponse } from '../models/EmbeddingsResponse';
 import { type ImagesGenerationsRequest } from '../models/ImagesGenerationsRequest';
 import { type ImagesResponse } from '../models/ImagesResponse';
 import { type Model } from '../models/Model';
@@ -25,6 +27,9 @@ export interface CancelVideoRequest {
 export interface CreateChatCompletionRequest {
     chatCompletionRequest: ChatCompletionRequest;
 }
+export interface CreateEmbeddingsRequest {
+    embeddingsRequest: EmbeddingsRequest;
+}
 export interface CreateImageRequest {
     imagesGenerationsRequest: ImagesGenerationsRequest;
     idempotencyKey?: string;
@@ -77,6 +82,20 @@ export declare class InferenceApi extends runtime.BaseAPI {
      * Create a chat completion (OpenAI-compatible)
      */
     createChatCompletion(requestParameters: CreateChatCompletionRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<ChatCompletionResponse>;
+    /**
+     * Creates request options for createEmbeddings without sending the request
+     */
+    createEmbeddingsRequestOpts(requestParameters: CreateEmbeddingsRequest): Promise<runtime.RequestOpts>;
+    /**
+     * Synchronous text embeddings. Accepts a single string or an array of up to 2048 strings, bounded so the response stays under 64 MiB (about 680 inputs at 4096 dimensions; fewer at a larger `dimensions` value) — over-limit requests are rejected with 400 before any processing. Returns one float vector per input, in request order. Billed on the upstream\'s reported prompt tokens at the model\'s listed input rate, rounded up to the next whole cent per request; an embeddings call emits no completion tokens, so `usage` carries `prompt_tokens` and `total_tokens` only. `encoding_format` accepts only `float` — a value of `base64` is rejected with `unsupported_parameter`. A chat model id on this route returns 404 `model_not_found`: the id is valid, but not on this surface.
+     * Create embeddings (OpenAI-compatible)
+     */
+    createEmbeddingsRaw(requestParameters: CreateEmbeddingsRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<EmbeddingsResponse>>;
+    /**
+     * Synchronous text embeddings. Accepts a single string or an array of up to 2048 strings, bounded so the response stays under 64 MiB (about 680 inputs at 4096 dimensions; fewer at a larger `dimensions` value) — over-limit requests are rejected with 400 before any processing. Returns one float vector per input, in request order. Billed on the upstream\'s reported prompt tokens at the model\'s listed input rate, rounded up to the next whole cent per request; an embeddings call emits no completion tokens, so `usage` carries `prompt_tokens` and `total_tokens` only. `encoding_format` accepts only `float` — a value of `base64` is rejected with `unsupported_parameter`. A chat model id on this route returns 404 `model_not_found`: the id is valid, but not on this surface.
+     * Create embeddings (OpenAI-compatible)
+     */
+    createEmbeddings(requestParameters: CreateEmbeddingsRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<EmbeddingsResponse>;
     /**
      * Creates request options for createImage without sending the request
      */

package/dist/apis/InferenceApi.js

@@ -26,6 +26,8 @@ exports.ListModelsModalityEnum = exports.InferenceApi = void 0;
 const runtime = require("../runtime");
 const ChatCompletionRequest_1 = require("../models/ChatCompletionRequest");
 const ChatCompletionResponse_1 = require("../models/ChatCompletionResponse");
+const EmbeddingsRequest_1 = require("../models/EmbeddingsRequest");
+const EmbeddingsResponse_1 = require("../models/EmbeddingsResponse");
 const ImagesGenerationsRequest_1 = require("../models/ImagesGenerationsRequest");
 const ImagesResponse_1 = require("../models/ImagesResponse");
 const Model_1 = require("../models/Model");
@@ -130,6 +132,55 @@ class InferenceApi extends runtime.BaseAPI {
             return yield response.value();
         });
     }
+    /**
+     * Creates request options for createEmbeddings without sending the request
+     */
+    createEmbeddingsRequestOpts(requestParameters) {
+        return __awaiter(this, void 0, void 0, function* () {
+            if (requestParameters['embeddingsRequest'] == null) {
+                throw new runtime.RequiredError('embeddingsRequest', 'Required parameter "embeddingsRequest" was null or undefined when calling createEmbeddings().');
+            }
+            const queryParameters = {};
+            const headerParameters = {};
+            headerParameters['Content-Type'] = 'application/json';
+            if (this.configuration && this.configuration.accessToken) {
+                const token = this.configuration.accessToken;
+                const tokenString = yield token("bearerAuth", []);
+                if (tokenString) {
+                    headerParameters["Authorization"] = `Bearer ${tokenString}`;
+                }
+            }
+            let urlPath = `/embeddings`;
+            return {
+                path: urlPath,
+                method: 'POST',
+                headers: headerParameters,
+                query: queryParameters,
+                body: (0, EmbeddingsRequest_1.EmbeddingsRequestToJSON)(requestParameters['embeddingsRequest']),
+            };
+        });
+    }
+    /**
+     * Synchronous text embeddings. Accepts a single string or an array of up to 2048 strings, bounded so the response stays under 64 MiB (about 680 inputs at 4096 dimensions; fewer at a larger `dimensions` value) — over-limit requests are rejected with 400 before any processing. Returns one float vector per input, in request order. Billed on the upstream\'s reported prompt tokens at the model\'s listed input rate, rounded up to the next whole cent per request; an embeddings call emits no completion tokens, so `usage` carries `prompt_tokens` and `total_tokens` only. `encoding_format` accepts only `float` — a value of `base64` is rejected with `unsupported_parameter`. A chat model id on this route returns 404 `model_not_found`: the id is valid, but not on this surface.
+     * Create embeddings (OpenAI-compatible)
+     */
+    createEmbeddingsRaw(requestParameters, initOverrides) {
+        return __awaiter(this, void 0, void 0, function* () {
+            const requestOptions = yield this.createEmbeddingsRequestOpts(requestParameters);
+            const response = yield this.request(requestOptions, initOverrides);
+            return new runtime.JSONApiResponse(response, (jsonValue) => (0, EmbeddingsResponse_1.EmbeddingsResponseFromJSON)(jsonValue));
+        });
+    }
+    /**
+     * Synchronous text embeddings. Accepts a single string or an array of up to 2048 strings, bounded so the response stays under 64 MiB (about 680 inputs at 4096 dimensions; fewer at a larger `dimensions` value) — over-limit requests are rejected with 400 before any processing. Returns one float vector per input, in request order. Billed on the upstream\'s reported prompt tokens at the model\'s listed input rate, rounded up to the next whole cent per request; an embeddings call emits no completion tokens, so `usage` carries `prompt_tokens` and `total_tokens` only. `encoding_format` accepts only `float` — a value of `base64` is rejected with `unsupported_parameter`. A chat model id on this route returns 404 `model_not_found`: the id is valid, but not on this surface.
+     * Create embeddings (OpenAI-compatible)
+     */
+    createEmbeddings(requestParameters, initOverrides) {
+        return __awaiter(this, void 0, void 0, function* () {
+            const response = yield this.createEmbeddingsRaw(requestParameters, initOverrides);
+            return yield response.value();
+        });
+    }
     /**
      * Creates request options for createImage without sending the request
      */

package/dist/esm/apis/InferenceApi.d.ts

@@ -12,6 +12,8 @@
 import * as runtime from '../runtime';
 import { type ChatCompletionRequest } from '../models/ChatCompletionRequest';
 import { type ChatCompletionResponse } from '../models/ChatCompletionResponse';
+import { type EmbeddingsRequest } from '../models/EmbeddingsRequest';
+import { type EmbeddingsResponse } from '../models/EmbeddingsResponse';
 import { type ImagesGenerationsRequest } from '../models/ImagesGenerationsRequest';
 import { type ImagesResponse } from '../models/ImagesResponse';
 import { type Model } from '../models/Model';
@@ -25,6 +27,9 @@ export interface CancelVideoRequest {
 export interface CreateChatCompletionRequest {
     chatCompletionRequest: ChatCompletionRequest;
 }
+export interface CreateEmbeddingsRequest {
+    embeddingsRequest: EmbeddingsRequest;
+}
 export interface CreateImageRequest {
     imagesGenerationsRequest: ImagesGenerationsRequest;
     idempotencyKey?: string;
@@ -77,6 +82,20 @@ export declare class InferenceApi extends runtime.BaseAPI {
      * Create a chat completion (OpenAI-compatible)
      */
     createChatCompletion(requestParameters: CreateChatCompletionRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<ChatCompletionResponse>;
+    /**
+     * Creates request options for createEmbeddings without sending the request
+     */
+    createEmbeddingsRequestOpts(requestParameters: CreateEmbeddingsRequest): Promise<runtime.RequestOpts>;
+    /**
+     * Synchronous text embeddings. Accepts a single string or an array of up to 2048 strings, bounded so the response stays under 64 MiB (about 680 inputs at 4096 dimensions; fewer at a larger `dimensions` value) — over-limit requests are rejected with 400 before any processing. Returns one float vector per input, in request order. Billed on the upstream\'s reported prompt tokens at the model\'s listed input rate, rounded up to the next whole cent per request; an embeddings call emits no completion tokens, so `usage` carries `prompt_tokens` and `total_tokens` only. `encoding_format` accepts only `float` — a value of `base64` is rejected with `unsupported_parameter`. A chat model id on this route returns 404 `model_not_found`: the id is valid, but not on this surface.
+     * Create embeddings (OpenAI-compatible)
+     */
+    createEmbeddingsRaw(requestParameters: CreateEmbeddingsRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<EmbeddingsResponse>>;
+    /**
+     * Synchronous text embeddings. Accepts a single string or an array of up to 2048 strings, bounded so the response stays under 64 MiB (about 680 inputs at 4096 dimensions; fewer at a larger `dimensions` value) — over-limit requests are rejected with 400 before any processing. Returns one float vector per input, in request order. Billed on the upstream\'s reported prompt tokens at the model\'s listed input rate, rounded up to the next whole cent per request; an embeddings call emits no completion tokens, so `usage` carries `prompt_tokens` and `total_tokens` only. `encoding_format` accepts only `float` — a value of `base64` is rejected with `unsupported_parameter`. A chat model id on this route returns 404 `model_not_found`: the id is valid, but not on this surface.
+     * Create embeddings (OpenAI-compatible)
+     */
+    createEmbeddings(requestParameters: CreateEmbeddingsRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<EmbeddingsResponse>;
     /**
      * Creates request options for createImage without sending the request
      */

package/dist/esm/apis/InferenceApi.js

@@ -23,6 +23,8 @@ var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, ge
 import * as runtime from '../runtime';
 import { ChatCompletionRequestToJSON, } from '../models/ChatCompletionRequest';
 import { ChatCompletionResponseFromJSON, } from '../models/ChatCompletionResponse';
+import { EmbeddingsRequestToJSON, } from '../models/EmbeddingsRequest';
+import { EmbeddingsResponseFromJSON, } from '../models/EmbeddingsResponse';
 import { ImagesGenerationsRequestToJSON, } from '../models/ImagesGenerationsRequest';
 import { ImagesResponseFromJSON, } from '../models/ImagesResponse';
 import { ModelFromJSON, } from '../models/Model';
@@ -127,6 +129,55 @@ export class InferenceApi extends runtime.BaseAPI {
             return yield response.value();
         });
     }
+    /**
+     * Creates request options for createEmbeddings without sending the request
+     */
+    createEmbeddingsRequestOpts(requestParameters) {
+        return __awaiter(this, void 0, void 0, function* () {
+            if (requestParameters['embeddingsRequest'] == null) {
+                throw new runtime.RequiredError('embeddingsRequest', 'Required parameter "embeddingsRequest" was null or undefined when calling createEmbeddings().');
+            }
+            const queryParameters = {};
+            const headerParameters = {};
+            headerParameters['Content-Type'] = 'application/json';
+            if (this.configuration && this.configuration.accessToken) {
+                const token = this.configuration.accessToken;
+                const tokenString = yield token("bearerAuth", []);
+                if (tokenString) {
+                    headerParameters["Authorization"] = `Bearer ${tokenString}`;
+                }
+            }
+            let urlPath = `/embeddings`;
+            return {
+                path: urlPath,
+                method: 'POST',
+                headers: headerParameters,
+                query: queryParameters,
+                body: EmbeddingsRequestToJSON(requestParameters['embeddingsRequest']),
+            };
+        });
+    }
+    /**
+     * Synchronous text embeddings. Accepts a single string or an array of up to 2048 strings, bounded so the response stays under 64 MiB (about 680 inputs at 4096 dimensions; fewer at a larger `dimensions` value) — over-limit requests are rejected with 400 before any processing. Returns one float vector per input, in request order. Billed on the upstream\'s reported prompt tokens at the model\'s listed input rate, rounded up to the next whole cent per request; an embeddings call emits no completion tokens, so `usage` carries `prompt_tokens` and `total_tokens` only. `encoding_format` accepts only `float` — a value of `base64` is rejected with `unsupported_parameter`. A chat model id on this route returns 404 `model_not_found`: the id is valid, but not on this surface.
+     * Create embeddings (OpenAI-compatible)
+     */
+    createEmbeddingsRaw(requestParameters, initOverrides) {
+        return __awaiter(this, void 0, void 0, function* () {
+            const requestOptions = yield this.createEmbeddingsRequestOpts(requestParameters);
+            const response = yield this.request(requestOptions, initOverrides);
+            return new runtime.JSONApiResponse(response, (jsonValue) => EmbeddingsResponseFromJSON(jsonValue));
+        });
+    }
+    /**
+     * Synchronous text embeddings. Accepts a single string or an array of up to 2048 strings, bounded so the response stays under 64 MiB (about 680 inputs at 4096 dimensions; fewer at a larger `dimensions` value) — over-limit requests are rejected with 400 before any processing. Returns one float vector per input, in request order. Billed on the upstream\'s reported prompt tokens at the model\'s listed input rate, rounded up to the next whole cent per request; an embeddings call emits no completion tokens, so `usage` carries `prompt_tokens` and `total_tokens` only. `encoding_format` accepts only `float` — a value of `base64` is rejected with `unsupported_parameter`. A chat model id on this route returns 404 `model_not_found`: the id is valid, but not on this surface.
+     * Create embeddings (OpenAI-compatible)
+     */
+    createEmbeddings(requestParameters, initOverrides) {
+        return __awaiter(this, void 0, void 0, function* () {
+            const response = yield this.createEmbeddingsRaw(requestParameters, initOverrides);
+            return yield response.value();
+        });
+    }
     /**
      * Creates request options for createImage without sending the request
      */

package/dist/esm/models/Embedding.d.ts

@@ -0,0 +1,51 @@
+/**
+ * GPU.ai Public Developer API
+ * Programmatic API for GPU.ai. Authenticate with API keys minted from the dashboard. See https://gpu.ai/docs for details.
+ *
+ * The version of the OpenAPI document: 1.0.0
+ * Contact: support@gpu.ai
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+/**
+ *
+ * @export
+ * @interface Embedding
+ */
+export interface Embedding {
+    /**
+     *
+     * @type {EmbeddingObjectEnum}
+     * @memberof Embedding
+     */
+    object: EmbeddingObjectEnum;
+    /**
+     * The embedding vector as 32-bit floats.
+     * @type {Array<number>}
+     * @memberof Embedding
+     */
+    embedding: Array<number>;
+    /**
+     * Position of this vector's input in the request.
+     * @type {number}
+     * @memberof Embedding
+     */
+    index: number;
+}
+/**
+ * @export
+ */
+export declare const EmbeddingObjectEnum: {
+    readonly Embedding: "embedding";
+};
+export type EmbeddingObjectEnum = typeof EmbeddingObjectEnum[keyof typeof EmbeddingObjectEnum];
+/**
+ * Check if a given object implements the Embedding interface.
+ */
+export declare function instanceOfEmbedding(value: object): value is Embedding;
+export declare function EmbeddingFromJSON(json: any): Embedding;
+export declare function EmbeddingFromJSONTyped(json: any, ignoreDiscriminator: boolean): Embedding;
+export declare function EmbeddingToJSON(json: any): Embedding;
+export declare function EmbeddingToJSONTyped(value?: Embedding | null, ignoreDiscriminator?: boolean): any;

package/dist/esm/models/Embedding.js

@@ -0,0 +1,59 @@
+/* tslint:disable */
+/* eslint-disable */
+/**
+ * GPU.ai Public Developer API
+ * Programmatic API for GPU.ai. Authenticate with API keys minted from the dashboard. See https://gpu.ai/docs for details.
+ *
+ * The version of the OpenAPI document: 1.0.0
+ * Contact: support@gpu.ai
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+/**
+ * @export
+ */
+export const EmbeddingObjectEnum = {
+    Embedding: 'embedding'
+};
+/**
+ * Check if a given object implements the Embedding interface.
+ */
+export function instanceOfEmbedding(value) {
+    if (!('object' in value) || value['object'] === undefined)
+        return false;
+    if (value['object'] !== 'embedding')
+        return false;
+    if (!('embedding' in value) || value['embedding'] === undefined)
+        return false;
+    if (!('index' in value) || value['index'] === undefined)
+        return false;
+    return true;
+}
+export function EmbeddingFromJSON(json) {
+    return EmbeddingFromJSONTyped(json, false);
+}
+export function EmbeddingFromJSONTyped(json, ignoreDiscriminator) {
+    if (json == null) {
+        return json;
+    }
+    return {
+        'object': json['object'],
+        'embedding': json['embedding'],
+        'index': json['index'],
+    };
+}
+export function EmbeddingToJSON(json) {
+    return EmbeddingToJSONTyped(json, false);
+}
+export function EmbeddingToJSONTyped(value, ignoreDiscriminator = false) {
+    if (value == null) {
+        return value;
+    }
+    return {
+        'object': value['object'],
+        'embedding': value['embedding'],
+        'index': value['index'],
+    };
+}

package/dist/esm/models/EmbeddingsRequest.d.ts

@@ -0,0 +1,64 @@
+/**
+ * GPU.ai Public Developer API
+ * Programmatic API for GPU.ai. Authenticate with API keys minted from the dashboard. See https://gpu.ai/docs for details.
+ *
+ * The version of the OpenAPI document: 1.0.0
+ * Contact: support@gpu.ai
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+import type { EmbeddingsRequestInput } from './EmbeddingsRequestInput';
+/**
+ *
+ * @export
+ * @interface EmbeddingsRequest
+ */
+export interface EmbeddingsRequest {
+    /**
+     * Canonical embedding model id, e.g. "gpuai/qwen3-embedding-8b".
+     * @type {string}
+     * @memberof EmbeddingsRequest
+     */
+    model: string;
+    /**
+     *
+     * @type {EmbeddingsRequestInput}
+     * @memberof EmbeddingsRequest
+     */
+    input: EmbeddingsRequestInput;
+    /**
+     * Only "float" is supported. A value of "base64" is rejected with invalid_request_error / unsupported_parameter.
+     * @type {EmbeddingsRequestEncodingFormatEnum}
+     * @memberof EmbeddingsRequest
+     */
+    encodingFormat?: EmbeddingsRequestEncodingFormatEnum;
+    /**
+     * Requested output dimensionality, for models that support truncated (Matryoshka) embeddings. Passed through to the model when set.
+     * @type {number}
+     * @memberof EmbeddingsRequest
+     */
+    dimensions?: number;
+    /**
+     * Opaque end-user identifier for abuse tracing. Optional.
+     * @type {string}
+     * @memberof EmbeddingsRequest
+     */
+    user?: string;
+}
+/**
+ * @export
+ */
+export declare const EmbeddingsRequestEncodingFormatEnum: {
+    readonly Float: "float";
+};
+export type EmbeddingsRequestEncodingFormatEnum = typeof EmbeddingsRequestEncodingFormatEnum[keyof typeof EmbeddingsRequestEncodingFormatEnum];
+/**
+ * Check if a given object implements the EmbeddingsRequest interface.
+ */
+export declare function instanceOfEmbeddingsRequest(value: object): value is EmbeddingsRequest;
+export declare function EmbeddingsRequestFromJSON(json: any): EmbeddingsRequest;
+export declare function EmbeddingsRequestFromJSONTyped(json: any, ignoreDiscriminator: boolean): EmbeddingsRequest;
+export declare function EmbeddingsRequestToJSON(json: any): EmbeddingsRequest;
+export declare function EmbeddingsRequestToJSONTyped(value?: EmbeddingsRequest | null, ignoreDiscriminator?: boolean): any;

package/dist/esm/models/EmbeddingsRequest.js

@@ -0,0 +1,60 @@
+/* tslint:disable */
+/* eslint-disable */
+/**
+ * GPU.ai Public Developer API
+ * Programmatic API for GPU.ai. Authenticate with API keys minted from the dashboard. See https://gpu.ai/docs for details.
+ *
+ * The version of the OpenAPI document: 1.0.0
+ * Contact: support@gpu.ai
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+import { EmbeddingsRequestInputFromJSON, EmbeddingsRequestInputToJSON, } from './EmbeddingsRequestInput';
+/**
+ * @export
+ */
+export const EmbeddingsRequestEncodingFormatEnum = {
+    Float: 'float'
+};
+/**
+ * Check if a given object implements the EmbeddingsRequest interface.
+ */
+export function instanceOfEmbeddingsRequest(value) {
+    if (!('model' in value) || value['model'] === undefined)
+        return false;
+    if (!('input' in value) || value['input'] === undefined)
+        return false;
+    return true;
+}
+export function EmbeddingsRequestFromJSON(json) {
+    return EmbeddingsRequestFromJSONTyped(json, false);
+}
+export function EmbeddingsRequestFromJSONTyped(json, ignoreDiscriminator) {
+    if (json == null) {
+        return json;
+    }
+    return {
+        'model': json['model'],
+        'input': EmbeddingsRequestInputFromJSON(json['input']),
+        'encodingFormat': json['encoding_format'] == null ? undefined : json['encoding_format'],
+        'dimensions': json['dimensions'] == null ? undefined : json['dimensions'],
+        'user': json['user'] == null ? undefined : json['user'],
+    };
+}
+export function EmbeddingsRequestToJSON(json) {
+    return EmbeddingsRequestToJSONTyped(json, false);
+}
+export function EmbeddingsRequestToJSONTyped(value, ignoreDiscriminator = false) {
+    if (value == null) {
+        return value;
+    }
+    return {
+        'model': value['model'],
+        'input': EmbeddingsRequestInputToJSON(value['input']),
+        'encoding_format': value['encodingFormat'],
+        'dimensions': value['dimensions'],
+        'user': value['user'],
+    };
+}

package/dist/esm/models/EmbeddingsRequestInput.d.ts

@@ -0,0 +1,21 @@
+/**
+ * GPU.ai Public Developer API
+ * Programmatic API for GPU.ai. Authenticate with API keys minted from the dashboard. See https://gpu.ai/docs for details.
+ *
+ * The version of the OpenAPI document: 1.0.0
+ * Contact: support@gpu.ai
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+/**
+ * @type EmbeddingsRequestInput
+ * Text to embed: either a single string or an array of up to 2048 strings. Token-id arrays are not supported. The per-request ceiling is bounded so the response stays under 64 MiB — about 680 inputs at 4096 dimensions, fewer at a larger `dimensions` value; an over-limit batch is rejected with 400 invalid_request_error whose message states the limit, before any processing.
+ * @export
+ */
+export type EmbeddingsRequestInput = Array<string> | string;
+export declare function EmbeddingsRequestInputFromJSON(json: any): EmbeddingsRequestInput;
+export declare function EmbeddingsRequestInputFromJSONTyped(json: any, ignoreDiscriminator: boolean): EmbeddingsRequestInput;
+export declare function EmbeddingsRequestInputToJSON(json: any): any;
+export declare function EmbeddingsRequestInputToJSONTyped(value?: EmbeddingsRequestInput | null, ignoreDiscriminator?: boolean): any;

package/dist/esm/models/EmbeddingsRequestInput.js

@@ -0,0 +1,47 @@
+/* tslint:disable */
+/* eslint-disable */
+/**
+ * GPU.ai Public Developer API
+ * Programmatic API for GPU.ai. Authenticate with API keys minted from the dashboard. See https://gpu.ai/docs for details.
+ *
+ * The version of the OpenAPI document: 1.0.0
+ * Contact: support@gpu.ai
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+export function EmbeddingsRequestInputFromJSON(json) {
+    return EmbeddingsRequestInputFromJSONTyped(json, false);
+}
+export function EmbeddingsRequestInputFromJSONTyped(json, ignoreDiscriminator) {
+    if (json == null) {
+        return json;
+    }
+    if (Array.isArray(json)) {
+        if (json.every(item => typeof item === 'string')) {
+            return json;
+        }
+    }
+    if (typeof json === 'string') {
+        return json;
+    }
+    return {};
+}
+export function EmbeddingsRequestInputToJSON(json) {
+    return EmbeddingsRequestInputToJSONTyped(json, false);
+}
+export function EmbeddingsRequestInputToJSONTyped(value, ignoreDiscriminator = false) {
+    if (value == null) {
+        return value;
+    }
+    if (Array.isArray(value)) {
+        if (value.every(item => typeof item === 'string')) {
+            return value;
+        }
+    }
+    if (typeof value === 'string') {
+        return value;
+    }
+    return {};
+}

package/dist/esm/models/EmbeddingsResponse.d.ts

@@ -0,0 +1,59 @@
+/**
+ * GPU.ai Public Developer API
+ * Programmatic API for GPU.ai. Authenticate with API keys minted from the dashboard. See https://gpu.ai/docs for details.
+ *
+ * The version of the OpenAPI document: 1.0.0
+ * Contact: support@gpu.ai
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+import type { Embedding } from './Embedding';
+import type { EmbeddingsUsage } from './EmbeddingsUsage';
+/**
+ *
+ * @export
+ * @interface EmbeddingsResponse
+ */
+export interface EmbeddingsResponse {
+    /**
+     *
+     * @type {EmbeddingsResponseObjectEnum}
+     * @memberof EmbeddingsResponse
+     */
+    object: EmbeddingsResponseObjectEnum;
+    /**
+     *
+     * @type {Array<Embedding>}
+     * @memberof EmbeddingsResponse
+     */
+    data: Array<Embedding>;
+    /**
+     * Canonical (gpuai/...) model id, NEVER the upstream identifier.
+     * @type {string}
+     * @memberof EmbeddingsResponse
+     */
+    model: string;
+    /**
+     *
+     * @type {EmbeddingsUsage}
+     * @memberof EmbeddingsResponse
+     */
+    usage: EmbeddingsUsage;
+}
+/**
+ * @export
+ */
+export declare const EmbeddingsResponseObjectEnum: {
+    readonly List: "list";
+};
+export type EmbeddingsResponseObjectEnum = typeof EmbeddingsResponseObjectEnum[keyof typeof EmbeddingsResponseObjectEnum];
+/**
+ * Check if a given object implements the EmbeddingsResponse interface.
+ */
+export declare function instanceOfEmbeddingsResponse(value: object): value is EmbeddingsResponse;
+export declare function EmbeddingsResponseFromJSON(json: any): EmbeddingsResponse;
+export declare function EmbeddingsResponseFromJSONTyped(json: any, ignoreDiscriminator: boolean): EmbeddingsResponse;
+export declare function EmbeddingsResponseToJSON(json: any): EmbeddingsResponse;
+export declare function EmbeddingsResponseToJSONTyped(value?: EmbeddingsResponse | null, ignoreDiscriminator?: boolean): any;