@langchain/openai 0.6.16 → 1.0.0-alpha.2

package/dist/embeddings.cjs

@@ -1,208 +1,142 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.OpenAIEmbeddings = void 0;
-const openai_1 = require("openai");
-const env_1 = require("@langchain/core/utils/env");
-const embeddings_1 = require("@langchain/core/embeddings");
-const chunk_array_1 = require("@langchain/core/utils/chunk_array");
-const azure_js_1 = require("./utils/azure.cjs");
-const openai_js_1 = require("./utils/openai.cjs");
+const require_rolldown_runtime = require('./_virtual/rolldown_runtime.cjs');
+const require_azure = require('./utils/azure.cjs');
+const require_client = require('./utils/client.cjs');
+const openai = require_rolldown_runtime.__toESM(require("openai"));
+const __langchain_core_utils_env = require_rolldown_runtime.__toESM(require("@langchain/core/utils/env"));
+const __langchain_core_utils_chunk_array = require_rolldown_runtime.__toESM(require("@langchain/core/utils/chunk_array"));
+const __langchain_core_embeddings = require_rolldown_runtime.__toESM(require("@langchain/core/embeddings"));
+
+//#region src/embeddings.ts
 /**
- * Class for generating embeddings using the OpenAI API.
- *
- * To use with Azure, import the `AzureOpenAIEmbeddings` class.
- *
- * @example
- * ```typescript
- * // Embed a query using OpenAIEmbeddings to generate embeddings for a given text
- * const model = new OpenAIEmbeddings();
- * const res = await model.embedQuery(
- *   "What would be a good company name for a company that makes colorful socks?",
- * );
- * console.log({ res });
- *
- * ```
- */
-class OpenAIEmbeddings extends embeddings_1.Embeddings {
-    constructor(fields) {
-        const fieldsWithDefaults = { maxConcurrency: 2, ...fields };
-        super(fieldsWithDefaults);
-        Object.defineProperty(this, "model", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: "text-embedding-ada-002"
-        });
-        /** @deprecated Use "model" instead */
-        Object.defineProperty(this, "modelName", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "batchSize", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: 512
-        });
-        // TODO: Update to `false` on next minor release (see: https://github.com/langchain-ai/langchainjs/pull/3612)
-        Object.defineProperty(this, "stripNewLines", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: true
-        });
-        /**
-         * The number of dimensions the resulting output embeddings should have.
-         * Only supported in `text-embedding-3` and later models.
-         */
-        Object.defineProperty(this, "dimensions", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "timeout", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "organization", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "encodingFormat", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "client", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "clientConfig", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        const apiKey = fieldsWithDefaults?.apiKey ??
-            fieldsWithDefaults?.openAIApiKey ??
-            (0, env_1.getEnvironmentVariable)("OPENAI_API_KEY");
-        this.organization =
-            fieldsWithDefaults?.configuration?.organization ??
-                (0, env_1.getEnvironmentVariable)("OPENAI_ORGANIZATION");
-        this.model =
-            fieldsWithDefaults?.model ?? fieldsWithDefaults?.modelName ?? this.model;
-        this.modelName = this.model;
-        this.batchSize = fieldsWithDefaults?.batchSize ?? this.batchSize;
-        this.stripNewLines =
-            fieldsWithDefaults?.stripNewLines ?? this.stripNewLines;
-        this.timeout = fieldsWithDefaults?.timeout;
-        this.dimensions = fieldsWithDefaults?.dimensions;
-        this.encodingFormat = fieldsWithDefaults?.encodingFormat;
-        this.clientConfig = {
-            apiKey,
-            organization: this.organization,
-            dangerouslyAllowBrowser: true,
-            ...fields?.configuration,
-        };
-    }
-    /**
-     * Method to generate embeddings for an array of documents. Splits the
-     * documents into batches and makes requests to the OpenAI API to generate
-     * embeddings.
-     * @param texts Array of documents to generate embeddings for.
-     * @returns Promise that resolves to a 2D array of embeddings for each document.
-     */
-    async embedDocuments(texts) {
-        const batches = (0, chunk_array_1.chunkArray)(this.stripNewLines ? texts.map((t) => t.replace(/\n/g, " ")) : texts, this.batchSize);
-        const batchRequests = batches.map((batch) => {
-            const params = {
-                model: this.model,
-                input: batch,
-            };
-            if (this.dimensions) {
-                params.dimensions = this.dimensions;
-            }
-            if (this.encodingFormat) {
-                params.encoding_format = this.encodingFormat;
-            }
-            return this.embeddingWithRetry(params);
-        });
-        const batchResponses = await Promise.all(batchRequests);
-        const embeddings = [];
-        for (let i = 0; i < batchResponses.length; i += 1) {
-            const batch = batches[i];
-            const { data: batchResponse } = batchResponses[i];
-            for (let j = 0; j < batch.length; j += 1) {
-                embeddings.push(batchResponse[j].embedding);
-            }
-        }
-        return embeddings;
-    }
-    /**
-     * Method to generate an embedding for a single document. Calls the
-     * embeddingWithRetry method with the document as the input.
-     * @param text Document to generate an embedding for.
-     * @returns Promise that resolves to an embedding for the document.
-     */
-    async embedQuery(text) {
-        const params = {
-            model: this.model,
-            input: this.stripNewLines ? text.replace(/\n/g, " ") : text,
-        };
-        if (this.dimensions) {
-            params.dimensions = this.dimensions;
-        }
-        if (this.encodingFormat) {
-            params.encoding_format = this.encodingFormat;
-        }
-        const { data } = await this.embeddingWithRetry(params);
-        return data[0].embedding;
-    }
-    /**
-     * Private method to make a request to the OpenAI API to generate
-     * embeddings. Handles the retry logic and returns the response from the
-     * API.
-     * @param request Request to send to the OpenAI API.
-     * @returns Promise that resolves to the response from the API.
-     */
-    async embeddingWithRetry(request) {
-        if (!this.client) {
-            const openAIEndpointConfig = {
-                baseURL: this.clientConfig.baseURL,
-            };
-            const endpoint = (0, azure_js_1.getEndpoint)(openAIEndpointConfig);
-            const params = {
-                ...this.clientConfig,
-                baseURL: endpoint,
-                timeout: this.timeout,
-                maxRetries: 0,
-            };
-            if (!params.baseURL) {
-                delete params.baseURL;
-            }
-            this.client = new openai_1.OpenAI(params);
-        }
-        const requestOptions = {};
-        return this.caller.call(async () => {
-            try {
-                const res = await this.client.embeddings.create(request, requestOptions);
-                return res;
-            }
-            catch (e) {
-                const error = (0, openai_js_1.wrapOpenAIClientError)(e);
-                throw error;
-            }
-        });
-    }
-}
+* Class for generating embeddings using the OpenAI API.
+*
+* To use with Azure, import the `AzureOpenAIEmbeddings` class.
+*
+* @example
+* ```typescript
+* // Embed a query using OpenAIEmbeddings to generate embeddings for a given text
+* const model = new OpenAIEmbeddings();
+* const res = await model.embedQuery(
+*   "What would be a good company name for a company that makes colorful socks?",
+* );
+* console.log({ res });
+*
+* ```
+*/
+var OpenAIEmbeddings = class extends __langchain_core_embeddings.Embeddings {
+	model = "text-embedding-ada-002";
+	/** @deprecated Use "model" instead */
+	modelName;
+	batchSize = 512;
+	stripNewLines = true;
+	/**
+	* The number of dimensions the resulting output embeddings should have.
+	* Only supported in `text-embedding-3` and later models.
+	*/
+	dimensions;
+	timeout;
+	organization;
+	encodingFormat;
+	client;
+	clientConfig;
+	constructor(fields) {
+		const fieldsWithDefaults = {
+			maxConcurrency: 2,
+			...fields
+		};
+		super(fieldsWithDefaults);
+		const apiKey = fieldsWithDefaults?.apiKey ?? fieldsWithDefaults?.openAIApiKey ?? (0, __langchain_core_utils_env.getEnvironmentVariable)("OPENAI_API_KEY");
+		this.organization = fieldsWithDefaults?.configuration?.organization ?? (0, __langchain_core_utils_env.getEnvironmentVariable)("OPENAI_ORGANIZATION");
+		this.model = fieldsWithDefaults?.model ?? fieldsWithDefaults?.modelName ?? this.model;
+		this.modelName = this.model;
+		this.batchSize = fieldsWithDefaults?.batchSize ?? this.batchSize;
+		this.stripNewLines = fieldsWithDefaults?.stripNewLines ?? this.stripNewLines;
+		this.timeout = fieldsWithDefaults?.timeout;
+		this.dimensions = fieldsWithDefaults?.dimensions;
+		this.encodingFormat = fieldsWithDefaults?.encodingFormat;
+		this.clientConfig = {
+			apiKey,
+			organization: this.organization,
+			dangerouslyAllowBrowser: true,
+			...fields?.configuration
+		};
+	}
+	/**
+	* Method to generate embeddings for an array of documents. Splits the
+	* documents into batches and makes requests to the OpenAI API to generate
+	* embeddings.
+	* @param texts Array of documents to generate embeddings for.
+	* @returns Promise that resolves to a 2D array of embeddings for each document.
+	*/
+	async embedDocuments(texts) {
+		const batches = (0, __langchain_core_utils_chunk_array.chunkArray)(this.stripNewLines ? texts.map((t) => t.replace(/\n/g, " ")) : texts, this.batchSize);
+		const batchRequests = batches.map((batch) => {
+			const params = {
+				model: this.model,
+				input: batch
+			};
+			if (this.dimensions) params.dimensions = this.dimensions;
+			if (this.encodingFormat) params.encoding_format = this.encodingFormat;
+			return this.embeddingWithRetry(params);
+		});
+		const batchResponses = await Promise.all(batchRequests);
+		const embeddings = [];
+		for (let i = 0; i < batchResponses.length; i += 1) {
+			const batch = batches[i];
+			const { data: batchResponse } = batchResponses[i];
+			for (let j = 0; j < batch.length; j += 1) embeddings.push(batchResponse[j].embedding);
+		}
+		return embeddings;
+	}
+	/**
+	* Method to generate an embedding for a single document. Calls the
+	* embeddingWithRetry method with the document as the input.
+	* @param text Document to generate an embedding for.
+	* @returns Promise that resolves to an embedding for the document.
+	*/
+	async embedQuery(text) {
+		const params = {
+			model: this.model,
+			input: this.stripNewLines ? text.replace(/\n/g, " ") : text
+		};
+		if (this.dimensions) params.dimensions = this.dimensions;
+		if (this.encodingFormat) params.encoding_format = this.encodingFormat;
+		const { data } = await this.embeddingWithRetry(params);
+		return data[0].embedding;
+	}
+	/**
+	* Private method to make a request to the OpenAI API to generate
+	* embeddings. Handles the retry logic and returns the response from the
+	* API.
+	* @param request Request to send to the OpenAI API.
+	* @returns Promise that resolves to the response from the API.
+	*/
+	async embeddingWithRetry(request) {
+		if (!this.client) {
+			const openAIEndpointConfig = { baseURL: this.clientConfig.baseURL };
+			const endpoint = require_azure.getEndpoint(openAIEndpointConfig);
+			const params = {
+				...this.clientConfig,
+				baseURL: endpoint,
+				timeout: this.timeout,
+				maxRetries: 0
+			};
+			if (!params.baseURL) delete params.baseURL;
+			this.client = new openai.OpenAI(params);
+		}
+		const requestOptions = {};
+		return this.caller.call(async () => {
+			try {
+				const res = await this.client.embeddings.create(request, requestOptions);
+				return res;
+			} catch (e) {
+				const error = require_client.wrapOpenAIClientError(e);
+				throw error;
+			}
+		});
+	}
+};
+
+//#endregion
 exports.OpenAIEmbeddings = OpenAIEmbeddings;
+//# sourceMappingURL=embeddings.cjs.map

package/dist/embeddings.cjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"embeddings.cjs","names":["Embeddings","fields?: Partial<OpenAIEmbeddingsParams> & {\n      verbose?: boolean;\n      /**\n       * The OpenAI API key to use.\n       * Alias for `apiKey`.\n       */\n      openAIApiKey?: string;\n      /** The OpenAI API key to use. */\n      apiKey?: string;\n      configuration?: ClientOptions;\n    }","texts: string[]","params: OpenAIClient.EmbeddingCreateParams","embeddings: TOutput[]","text: string","request: OpenAIClient.EmbeddingCreateParams","openAIEndpointConfig: OpenAIEndpointConfig","getEndpoint","OpenAIClient","wrapOpenAIClientError"],"sources":["../src/embeddings.ts"],"sourcesContent":["import { type ClientOptions, OpenAI as OpenAIClient } from \"openai\";\nimport { getEnvironmentVariable } from \"@langchain/core/utils/env\";\nimport { Embeddings, type EmbeddingsParams } from \"@langchain/core/embeddings\";\nimport { chunkArray } from \"@langchain/core/utils/chunk_array\";\nimport { getEndpoint, OpenAIEndpointConfig } from \"./utils/azure.js\";\nimport { wrapOpenAIClientError } from \"./utils/client.js\";\n\n/**\n * @see https://platform.openai.com/docs/guides/embeddings#embedding-models\n */\nexport type OpenAIEmbeddingModelId =\n  | OpenAIClient.EmbeddingModel\n  | (string & NonNullable<unknown>);\n\n/**\n * Interface for OpenAIEmbeddings parameters. Extends EmbeddingsParams and\n * defines additional parameters specific to the OpenAIEmbeddings class.\n */\nexport interface OpenAIEmbeddingsParams extends EmbeddingsParams {\n  /**\n   * Model name to use\n   * Alias for `model`\n   * @deprecated Use \"model\" instead.\n   */\n  modelName: OpenAIEmbeddingModelId;\n  /** Model name to use */\n  model: OpenAIEmbeddingModelId;\n\n  /**\n   * The number of dimensions the resulting output embeddings should have.\n   * Only supported in `text-embedding-3` and later models.\n   */\n  dimensions?: number;\n\n  /**\n   * Timeout to use when making requests to OpenAI.\n   */\n  timeout?: number;\n\n  /**\n   * The maximum number of documents to embed in a single request. This is\n   * limited by the OpenAI API to a maximum of 2048.\n   */\n  batchSize?: number;\n\n  /**\n   * Whether to strip new lines from the input text. This is recommended by\n   * OpenAI for older models, but may not be suitable for all use cases.\n   * See: https://github.com/openai/openai-python/issues/418#issuecomment-1525939500\n   */\n  stripNewLines?: boolean;\n\n  /**\n   * The format to return the embeddings in. Can be either 'float' or 'base64'.\n   */\n  encodingFormat?: \"float\" | \"base64\";\n}\n\n/**\n * Class for generating embeddings using the OpenAI API.\n *\n * To use with Azure, import the `AzureOpenAIEmbeddings` class.\n *\n * @example\n * ```typescript\n * // Embed a query using OpenAIEmbeddings to generate embeddings for a given text\n * const model = new OpenAIEmbeddings();\n * const res = await model.embedQuery(\n *   \"What would be a good company name for a company that makes colorful socks?\",\n * );\n * console.log({ res });\n *\n * ```\n */\nexport class OpenAIEmbeddings<TOutput = number[]>\n  extends Embeddings<TOutput>\n  implements Partial<OpenAIEmbeddingsParams>\n{\n  model = \"text-embedding-ada-002\";\n\n  /** @deprecated Use \"model\" instead */\n  modelName: string;\n\n  batchSize = 512;\n\n  // TODO: Update to `false` on next minor release (see: https://github.com/langchain-ai/langchainjs/pull/3612)\n  stripNewLines = true;\n\n  /**\n   * The number of dimensions the resulting output embeddings should have.\n   * Only supported in `text-embedding-3` and later models.\n   */\n  dimensions?: number;\n\n  timeout?: number;\n\n  organization?: string;\n\n  encodingFormat?: \"float\" | \"base64\";\n\n  protected client: OpenAIClient;\n\n  protected clientConfig: ClientOptions;\n\n  constructor(\n    fields?: Partial<OpenAIEmbeddingsParams> & {\n      verbose?: boolean;\n      /**\n       * The OpenAI API key to use.\n       * Alias for `apiKey`.\n       */\n      openAIApiKey?: string;\n      /** The OpenAI API key to use. */\n      apiKey?: string;\n      configuration?: ClientOptions;\n    }\n  ) {\n    const fieldsWithDefaults = { maxConcurrency: 2, ...fields };\n\n    super(fieldsWithDefaults);\n\n    const apiKey =\n      fieldsWithDefaults?.apiKey ??\n      fieldsWithDefaults?.openAIApiKey ??\n      getEnvironmentVariable(\"OPENAI_API_KEY\");\n\n    this.organization =\n      fieldsWithDefaults?.configuration?.organization ??\n      getEnvironmentVariable(\"OPENAI_ORGANIZATION\");\n\n    this.model =\n      fieldsWithDefaults?.model ?? fieldsWithDefaults?.modelName ?? this.model;\n    this.modelName = this.model;\n    this.batchSize = fieldsWithDefaults?.batchSize ?? this.batchSize;\n    this.stripNewLines =\n      fieldsWithDefaults?.stripNewLines ?? this.stripNewLines;\n    this.timeout = fieldsWithDefaults?.timeout;\n    this.dimensions = fieldsWithDefaults?.dimensions;\n    this.encodingFormat = fieldsWithDefaults?.encodingFormat;\n\n    this.clientConfig = {\n      apiKey,\n      organization: this.organization,\n      dangerouslyAllowBrowser: true,\n      ...fields?.configuration,\n    };\n  }\n\n  /**\n   * Method to generate embeddings for an array of documents. Splits the\n   * documents into batches and makes requests to the OpenAI API to generate\n   * embeddings.\n   * @param texts Array of documents to generate embeddings for.\n   * @returns Promise that resolves to a 2D array of embeddings for each document.\n   */\n  async embedDocuments(texts: string[]): Promise<TOutput[]> {\n    const batches = chunkArray(\n      this.stripNewLines ? texts.map((t) => t.replace(/\\n/g, \" \")) : texts,\n      this.batchSize\n    );\n\n    const batchRequests = batches.map((batch) => {\n      const params: OpenAIClient.EmbeddingCreateParams = {\n        model: this.model,\n        input: batch,\n      };\n      if (this.dimensions) {\n        params.dimensions = this.dimensions;\n      }\n      if (this.encodingFormat) {\n        params.encoding_format = this.encodingFormat;\n      }\n      return this.embeddingWithRetry(params);\n    });\n    const batchResponses = await Promise.all(batchRequests);\n\n    const embeddings: TOutput[] = [];\n    for (let i = 0; i < batchResponses.length; i += 1) {\n      const batch = batches[i];\n      const { data: batchResponse } = batchResponses[i];\n      for (let j = 0; j < batch.length; j += 1) {\n        embeddings.push(batchResponse[j].embedding as TOutput);\n      }\n    }\n    return embeddings;\n  }\n\n  /**\n   * Method to generate an embedding for a single document. Calls the\n   * embeddingWithRetry method with the document as the input.\n   * @param text Document to generate an embedding for.\n   * @returns Promise that resolves to an embedding for the document.\n   */\n  async embedQuery(text: string): Promise<TOutput> {\n    const params: OpenAIClient.EmbeddingCreateParams = {\n      model: this.model,\n      input: this.stripNewLines ? text.replace(/\\n/g, \" \") : text,\n    };\n    if (this.dimensions) {\n      params.dimensions = this.dimensions;\n    }\n    if (this.encodingFormat) {\n      params.encoding_format = this.encodingFormat;\n    }\n    const { data } = await this.embeddingWithRetry(params);\n    return data[0].embedding as TOutput;\n  }\n\n  /**\n   * Private method to make a request to the OpenAI API to generate\n   * embeddings. Handles the retry logic and returns the response from the\n   * API.\n   * @param request Request to send to the OpenAI API.\n   * @returns Promise that resolves to the response from the API.\n   */\n  protected async embeddingWithRetry(\n    request: OpenAIClient.EmbeddingCreateParams\n  ) {\n    if (!this.client) {\n      const openAIEndpointConfig: OpenAIEndpointConfig = {\n        baseURL: this.clientConfig.baseURL,\n      };\n\n      const endpoint = getEndpoint(openAIEndpointConfig);\n\n      const params = {\n        ...this.clientConfig,\n        baseURL: endpoint,\n        timeout: this.timeout,\n        maxRetries: 0,\n      };\n\n      if (!params.baseURL) {\n        delete params.baseURL;\n      }\n\n      this.client = new OpenAIClient(params);\n    }\n    const requestOptions = {};\n\n    return this.caller.call(async () => {\n      try {\n        const res = await this.client.embeddings.create(\n          request,\n          requestOptions\n        );\n        return res;\n      } catch (e) {\n        const error = wrapOpenAIClientError(e);\n        throw error;\n      }\n    });\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;AA0EA,IAAa,mBAAb,cACUA,uCAEV;CACE,QAAQ;;CAGR;CAEA,YAAY;CAGZ,gBAAgB;;;;;CAMhB;CAEA;CAEA;CAEA;CAEA,AAAU;CAEV,AAAU;CAEV,YACEC,QAWA;EACA,MAAM,qBAAqB;GAAE,gBAAgB;GAAG,GAAG;EAAQ;EAE3D,MAAM,mBAAmB;EAEzB,MAAM,SACJ,oBAAoB,UACpB,oBAAoB,uEACG,iBAAiB;EAE1C,KAAK,eACH,oBAAoB,eAAe,uEACZ,sBAAsB;EAE/C,KAAK,QACH,oBAAoB,SAAS,oBAAoB,aAAa,KAAK;EACrE,KAAK,YAAY,KAAK;EACtB,KAAK,YAAY,oBAAoB,aAAa,KAAK;EACvD,KAAK,gBACH,oBAAoB,iBAAiB,KAAK;EAC5C,KAAK,UAAU,oBAAoB;EACnC,KAAK,aAAa,oBAAoB;EACtC,KAAK,iBAAiB,oBAAoB;EAE1C,KAAK,eAAe;GAClB;GACA,cAAc,KAAK;GACnB,yBAAyB;GACzB,GAAG,QAAQ;EACZ;CACF;;;;;;;;CASD,MAAM,eAAeC,OAAqC;EACxD,MAAM,6DACJ,KAAK,gBAAgB,MAAM,IAAI,CAAC,MAAM,EAAE,QAAQ,OAAO,IAAI,CAAC,GAAG,OAC/D,KAAK,UACN;EAED,MAAM,gBAAgB,QAAQ,IAAI,CAAC,UAAU;GAC3C,MAAMC,SAA6C;IACjD,OAAO,KAAK;IACZ,OAAO;GACR;AACD,OAAI,KAAK,YACP,OAAO,aAAa,KAAK;AAE3B,OAAI,KAAK,gBACP,OAAO,kBAAkB,KAAK;AAEhC,UAAO,KAAK,mBAAmB,OAAO;EACvC,EAAC;EACF,MAAM,iBAAiB,MAAM,QAAQ,IAAI,cAAc;EAEvD,MAAMC,aAAwB,CAAE;AAChC,OAAK,IAAI,IAAI,GAAG,IAAI,eAAe,QAAQ,KAAK,GAAG;GACjD,MAAM,QAAQ,QAAQ;GACtB,MAAM,EAAE,MAAM,eAAe,GAAG,eAAe;AAC/C,QAAK,IAAI,IAAI,GAAG,IAAI,MAAM,QAAQ,KAAK,GACrC,WAAW,KAAK,cAAc,GAAG,UAAqB;EAEzD;AACD,SAAO;CACR;;;;;;;CAQD,MAAM,WAAWC,MAAgC;EAC/C,MAAMF,SAA6C;GACjD,OAAO,KAAK;GACZ,OAAO,KAAK,gBAAgB,KAAK,QAAQ,OAAO,IAAI,GAAG;EACxD;AACD,MAAI,KAAK,YACP,OAAO,aAAa,KAAK;AAE3B,MAAI,KAAK,gBACP,OAAO,kBAAkB,KAAK;EAEhC,MAAM,EAAE,MAAM,GAAG,MAAM,KAAK,mBAAmB,OAAO;AACtD,SAAO,KAAK,GAAG;CAChB;;;;;;;;CASD,MAAgB,mBACdG,SACA;AACA,MAAI,CAAC,KAAK,QAAQ;GAChB,MAAMC,uBAA6C,EACjD,SAAS,KAAK,aAAa,QAC5B;GAED,MAAM,WAAWC,0BAAY,qBAAqB;GAElD,MAAM,SAAS;IACb,GAAG,KAAK;IACR,SAAS;IACT,SAAS,KAAK;IACd,YAAY;GACb;AAED,OAAI,CAAC,OAAO,SACV,OAAO,OAAO;GAGhB,KAAK,SAAS,IAAIC,cAAa;EAChC;EACD,MAAM,iBAAiB,CAAE;AAEzB,SAAO,KAAK,OAAO,KAAK,YAAY;AAClC,OAAI;IACF,MAAM,MAAM,MAAM,KAAK,OAAO,WAAW,OACvC,SACA,eACD;AACD,WAAO;GACR,SAAQ,GAAG;IACV,MAAM,QAAQC,qCAAsB,EAAE;AACtC,UAAM;GACP;EACF,EAAC;CACH;AACF"}

package/dist/embeddings.d.cts

@@ -0,0 +1,120 @@
+import { ClientOptions, OpenAI as OpenAI$1 } from "openai";
+import { Embeddings, EmbeddingsParams } from "@langchain/core/embeddings";
+
+//#region src/embeddings.d.ts
+
+/**
+ * @see https://platform.openai.com/docs/guides/embeddings#embedding-models
+ */
+type OpenAIEmbeddingModelId = OpenAI$1.EmbeddingModel | (string & NonNullable<unknown>);
+/**
+ * Interface for OpenAIEmbeddings parameters. Extends EmbeddingsParams and
+ * defines additional parameters specific to the OpenAIEmbeddings class.
+ */
+interface OpenAIEmbeddingsParams extends EmbeddingsParams {
+  /**
+   * Model name to use
+   * Alias for `model`
+   * @deprecated Use "model" instead.
+   */
+  modelName: OpenAIEmbeddingModelId;
+  /** Model name to use */
+  model: OpenAIEmbeddingModelId;
+  /**
+   * The number of dimensions the resulting output embeddings should have.
+   * Only supported in `text-embedding-3` and later models.
+   */
+  dimensions?: number;
+  /**
+   * Timeout to use when making requests to OpenAI.
+   */
+  timeout?: number;
+  /**
+   * The maximum number of documents to embed in a single request. This is
+   * limited by the OpenAI API to a maximum of 2048.
+   */
+  batchSize?: number;
+  /**
+   * Whether to strip new lines from the input text. This is recommended by
+   * OpenAI for older models, but may not be suitable for all use cases.
+   * See: https://github.com/openai/openai-python/issues/418#issuecomment-1525939500
+   */
+  stripNewLines?: boolean;
+  /**
+   * The format to return the embeddings in. Can be either 'float' or 'base64'.
+   */
+  encodingFormat?: "float" | "base64";
+}
+/**
+ * Class for generating embeddings using the OpenAI API.
+ *
+ * To use with Azure, import the `AzureOpenAIEmbeddings` class.
+ *
+ * @example
+ * ```typescript
+ * // Embed a query using OpenAIEmbeddings to generate embeddings for a given text
+ * const model = new OpenAIEmbeddings();
+ * const res = await model.embedQuery(
+ *   "What would be a good company name for a company that makes colorful socks?",
+ * );
+ * console.log({ res });
+ *
+ * ```
+ */
+declare class OpenAIEmbeddings<TOutput = number[]> extends Embeddings<TOutput> implements Partial<OpenAIEmbeddingsParams> {
+  model: string;
+  /** @deprecated Use "model" instead */
+  modelName: string;
+  batchSize: number;
+  // TODO: Update to `false` on next minor release (see: https://github.com/langchain-ai/langchainjs/pull/3612)
+  stripNewLines: boolean;
+  /**
+   * The number of dimensions the resulting output embeddings should have.
+   * Only supported in `text-embedding-3` and later models.
+   */
+  dimensions?: number;
+  timeout?: number;
+  organization?: string;
+  encodingFormat?: "float" | "base64";
+  protected client: OpenAI$1;
+  protected clientConfig: ClientOptions;
+  constructor(fields?: Partial<OpenAIEmbeddingsParams> & {
+    verbose?: boolean;
+    /**
+     * The OpenAI API key to use.
+     * Alias for `apiKey`.
+     */
+    openAIApiKey?: string;
+    /** The OpenAI API key to use. */
+    apiKey?: string;
+    configuration?: ClientOptions;
+  });
+  /**
+   * Method to generate embeddings for an array of documents. Splits the
+   * documents into batches and makes requests to the OpenAI API to generate
+   * embeddings.
+   * @param texts Array of documents to generate embeddings for.
+   * @returns Promise that resolves to a 2D array of embeddings for each document.
+   */
+  embedDocuments(texts: string[]): Promise<TOutput[]>;
+  /**
+   * Method to generate an embedding for a single document. Calls the
+   * embeddingWithRetry method with the document as the input.
+   * @param text Document to generate an embedding for.
+   * @returns Promise that resolves to an embedding for the document.
+   */
+  embedQuery(text: string): Promise<TOutput>;
+  /**
+   * Private method to make a request to the OpenAI API to generate
+   * embeddings. Handles the retry logic and returns the response from the
+   * API.
+   * @param request Request to send to the OpenAI API.
+   * @returns Promise that resolves to the response from the API.
+   */
+  protected embeddingWithRetry(request: OpenAI$1.EmbeddingCreateParams): Promise<OpenAI$1.CreateEmbeddingResponse & {
+    _request_id?: string | null | undefined;
+  }>;
+}
+//#endregion
+export { OpenAIEmbeddingModelId, OpenAIEmbeddings, OpenAIEmbeddingsParams };
+//# sourceMappingURL=embeddings.d.cts.map

package/dist/embeddings.d.cts.map

@@ -0,0 +1 @@
+{"version":3,"file":"embeddings.d.cts","names":["ClientOptions","OpenAI","OpenAIClient","Embeddings","EmbeddingsParams","OpenAIEmbeddingModelId","EmbeddingModel","NonNullable","OpenAIEmbeddingsParams","OpenAIEmbeddings","TOutput","Partial","Promise","EmbeddingCreateParams","CreateEmbeddingResponse"],"sources":["../src/embeddings.d.ts"],"sourcesContent":["import { type ClientOptions, OpenAI as OpenAIClient } from \"openai\";\nimport { Embeddings, type EmbeddingsParams } from \"@langchain/core/embeddings\";\n/**\n * @see https://platform.openai.com/docs/guides/embeddings#embedding-models\n */\nexport type OpenAIEmbeddingModelId = OpenAIClient.EmbeddingModel | (string & NonNullable<unknown>);\n/**\n * Interface for OpenAIEmbeddings parameters. Extends EmbeddingsParams and\n * defines additional parameters specific to the OpenAIEmbeddings class.\n */\nexport interface OpenAIEmbeddingsParams extends EmbeddingsParams {\n    /**\n     * Model name to use\n     * Alias for `model`\n     * @deprecated Use \"model\" instead.\n     */\n    modelName: OpenAIEmbeddingModelId;\n    /** Model name to use */\n    model: OpenAIEmbeddingModelId;\n    /**\n     * The number of dimensions the resulting output embeddings should have.\n     * Only supported in `text-embedding-3` and later models.\n     */\n    dimensions?: number;\n    /**\n     * Timeout to use when making requests to OpenAI.\n     */\n    timeout?: number;\n    /**\n     * The maximum number of documents to embed in a single request. This is\n     * limited by the OpenAI API to a maximum of 2048.\n     */\n    batchSize?: number;\n    /**\n     * Whether to strip new lines from the input text. This is recommended by\n     * OpenAI for older models, but may not be suitable for all use cases.\n     * See: https://github.com/openai/openai-python/issues/418#issuecomment-1525939500\n     */\n    stripNewLines?: boolean;\n    /**\n     * The format to return the embeddings in. Can be either 'float' or 'base64'.\n     */\n    encodingFormat?: \"float\" | \"base64\";\n}\n/**\n * Class for generating embeddings using the OpenAI API.\n *\n * To use with Azure, import the `AzureOpenAIEmbeddings` class.\n *\n * @example\n * ```typescript\n * // Embed a query using OpenAIEmbeddings to generate embeddings for a given text\n * const model = new OpenAIEmbeddings();\n * const res = await model.embedQuery(\n *   \"What would be a good company name for a company that makes colorful socks?\",\n * );\n * console.log({ res });\n *\n * ```\n */\nexport declare class OpenAIEmbeddings<TOutput = number[]> extends Embeddings<TOutput> implements Partial<OpenAIEmbeddingsParams> {\n    model: string;\n    /** @deprecated Use \"model\" instead */\n    modelName: string;\n    batchSize: number;\n    // TODO: Update to `false` on next minor release (see: https://github.com/langchain-ai/langchainjs/pull/3612)\n    stripNewLines: boolean;\n    /**\n     * The number of dimensions the resulting output embeddings should have.\n     * Only supported in `text-embedding-3` and later models.\n     */\n    dimensions?: number;\n    timeout?: number;\n    organization?: string;\n    encodingFormat?: \"float\" | \"base64\";\n    protected client: OpenAIClient;\n    protected clientConfig: ClientOptions;\n    constructor(fields?: Partial<OpenAIEmbeddingsParams> & {\n        verbose?: boolean;\n        /**\n         * The OpenAI API key to use.\n         * Alias for `apiKey`.\n         */\n        openAIApiKey?: string;\n        /** The OpenAI API key to use. */\n        apiKey?: string;\n        configuration?: ClientOptions;\n    });\n    /**\n     * Method to generate embeddings for an array of documents. Splits the\n     * documents into batches and makes requests to the OpenAI API to generate\n     * embeddings.\n     * @param texts Array of documents to generate embeddings for.\n     * @returns Promise that resolves to a 2D array of embeddings for each document.\n     */\n    embedDocuments(texts: string[]): Promise<TOutput[]>;\n    /**\n     * Method to generate an embedding for a single document. Calls the\n     * embeddingWithRetry method with the document as the input.\n     * @param text Document to generate an embedding for.\n     * @returns Promise that resolves to an embedding for the document.\n     */\n    embedQuery(text: string): Promise<TOutput>;\n    /**\n     * Private method to make a request to the OpenAI API to generate\n     * embeddings. Handles the retry logic and returns the response from the\n     * API.\n     * @param request Request to send to the OpenAI API.\n     * @returns Promise that resolves to the response from the API.\n     */\n    protected embeddingWithRetry(request: OpenAIClient.EmbeddingCreateParams): Promise<OpenAIClient.CreateEmbeddingResponse & {\n        _request_id?: string | null | undefined;\n    }>;\n}\n"],"mappings":";;;;;;;AAKA;AAAkC,KAAtBK,sBAAAA,GAAyBH,QAAAA,CAAaI,cAAhB,GAAA,CAAA,MAAA,GAA2CC,WAA3C,CAAA,OAAA,CAAA,CAAA;;;AAAsD;AAKxF;AAAuC,UAAtBC,sBAAAA,SAA+BJ,gBAAT,CAAA;EAAA;;;AAAyB;AAkDhE;EAAqC,SAAA,EA5CtBC,sBA4CsB;EAAA;EAA+C,KAAqBG,EA1C9FH,sBA0C8FG;EAAsB;;;;EAiB/F,UASRR,CAAAA,EAAAA,MAAAA;EAAa;;;EAgBQ,OAAfY,CAAAA,EAAAA,MAAAA;EAAO;;;;EA1CuC,SAAqBD,CAAAA,EAAAA,MAAAA;EAAO;;;;;;;;;;;;;;;;;;;;;;;;;;;cAAnFF,6CAA6CN,WAAWO,oBAAoBC,QAAQH;;;;;;;;;;;;;;;oBAenFN;0BACMF;uBACHW,QAAQH;;;;;;;;;oBASTR;;;;;;;;;mCASaY,QAAQF;;;;;;;4BAOfE,QAAQF;;;;;;;;wCAQIR,QAAAA,CAAaW,wBAAwBD,QAAQV,QAAAA,CAAaY"}