langchain 0.0.130 → 0.0.132

package/dist/embeddings/fake.cjs

@@ -2,18 +2,39 @@
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.SyntheticEmbeddings = exports.FakeEmbeddings = void 0;
 const base_js_1 = require("./base.cjs");
+/**
+ * A class that provides fake embeddings by overriding the embedDocuments
+ * and embedQuery methods to return fixed values.
+ */
 class FakeEmbeddings extends base_js_1.Embeddings {
     constructor(params) {
         super(params ?? {});
     }
+    /**
+     * Generates fixed embeddings for a list of documents.
+     * @param documents List of documents to generate embeddings for.
+     * @returns A promise that resolves with a list of fixed embeddings for each document.
+     */
     embedDocuments(documents) {
         return Promise.resolve(documents.map(() => [0.1, 0.2, 0.3, 0.4]));
     }
+    /**
+     * Generates a fixed embedding for a query.
+     * @param _ The query to generate an embedding for.
+     * @returns A promise that resolves with a fixed embedding for the query.
+     */
     embedQuery(_) {
         return Promise.resolve([0.1, 0.2, 0.3, 0.4]);
     }
 }
 exports.FakeEmbeddings = FakeEmbeddings;
+/**
+ * A class that provides synthetic embeddings by overriding the
+ * embedDocuments and embedQuery methods to generate embeddings based on
+ * the input documents. The embeddings are generated by converting each
+ * document into chunks, calculating a numerical value for each chunk, and
+ * returning an array of these values as the embedding.
+ */
 class SyntheticEmbeddings extends base_js_1.Embeddings {
     constructor(params) {
         super(params ?? {});
@@ -25,9 +46,21 @@ class SyntheticEmbeddings extends base_js_1.Embeddings {
         });
         this.vectorSize = params?.vectorSize ?? 4;
     }
+    /**
+     * Generates synthetic embeddings for a list of documents.
+     * @param documents List of documents to generate embeddings for.
+     * @returns A promise that resolves with a list of synthetic embeddings for each document.
+     */
     async embedDocuments(documents) {
         return Promise.all(documents.map((doc) => this.embedQuery(doc)));
     }
+    /**
+     * Generates a synthetic embedding for a document. The document is
+     * converted into chunks, a numerical value is calculated for each chunk,
+     * and an array of these values is returned as the embedding.
+     * @param document The document to generate an embedding for.
+     * @returns A promise that resolves with a synthetic embedding for the document.
+     */
     async embedQuery(document) {
         let doc = document;
         // Only use the letters (and space) from the document, and make them lower case

package/dist/embeddings/fake.d.ts

@@ -1,16 +1,53 @@
 import { Embeddings, EmbeddingsParams } from "./base.js";
+/**
+ * A class that provides fake embeddings by overriding the embedDocuments
+ * and embedQuery methods to return fixed values.
+ */
 export declare class FakeEmbeddings extends Embeddings {
     constructor(params?: EmbeddingsParams);
+    /**
+     * Generates fixed embeddings for a list of documents.
+     * @param documents List of documents to generate embeddings for.
+     * @returns A promise that resolves with a list of fixed embeddings for each document.
+     */
     embedDocuments(documents: string[]): Promise<number[][]>;
+    /**
+     * Generates a fixed embedding for a query.
+     * @param _ The query to generate an embedding for.
+     * @returns A promise that resolves with a fixed embedding for the query.
+     */
     embedQuery(_: string): Promise<number[]>;
 }
+/**
+ * An interface that defines additional parameters specific to the
+ * SyntheticEmbeddings class.
+ */
 interface SyntheticEmbeddingsParams extends EmbeddingsParams {
     vectorSize: number;
 }
+/**
+ * A class that provides synthetic embeddings by overriding the
+ * embedDocuments and embedQuery methods to generate embeddings based on
+ * the input documents. The embeddings are generated by converting each
+ * document into chunks, calculating a numerical value for each chunk, and
+ * returning an array of these values as the embedding.
+ */
 export declare class SyntheticEmbeddings extends Embeddings implements SyntheticEmbeddingsParams {
     vectorSize: number;
     constructor(params?: SyntheticEmbeddingsParams);
+    /**
+     * Generates synthetic embeddings for a list of documents.
+     * @param documents List of documents to generate embeddings for.
+     * @returns A promise that resolves with a list of synthetic embeddings for each document.
+     */
     embedDocuments(documents: string[]): Promise<number[][]>;
+    /**
+     * Generates a synthetic embedding for a document. The document is
+     * converted into chunks, a numerical value is calculated for each chunk,
+     * and an array of these values is returned as the embedding.
+     * @param document The document to generate an embedding for.
+     * @returns A promise that resolves with a synthetic embedding for the document.
+     */
     embedQuery(document: string): Promise<number[]>;
 }
 export {};

package/dist/embeddings/fake.js

@@ -1,15 +1,36 @@
 import { Embeddings } from "./base.js";
+/**
+ * A class that provides fake embeddings by overriding the embedDocuments
+ * and embedQuery methods to return fixed values.
+ */
 export class FakeEmbeddings extends Embeddings {
     constructor(params) {
         super(params ?? {});
     }
+    /**
+     * Generates fixed embeddings for a list of documents.
+     * @param documents List of documents to generate embeddings for.
+     * @returns A promise that resolves with a list of fixed embeddings for each document.
+     */
     embedDocuments(documents) {
         return Promise.resolve(documents.map(() => [0.1, 0.2, 0.3, 0.4]));
     }
+    /**
+     * Generates a fixed embedding for a query.
+     * @param _ The query to generate an embedding for.
+     * @returns A promise that resolves with a fixed embedding for the query.
+     */
     embedQuery(_) {
         return Promise.resolve([0.1, 0.2, 0.3, 0.4]);
     }
 }
+/**
+ * A class that provides synthetic embeddings by overriding the
+ * embedDocuments and embedQuery methods to generate embeddings based on
+ * the input documents. The embeddings are generated by converting each
+ * document into chunks, calculating a numerical value for each chunk, and
+ * returning an array of these values as the embedding.
+ */
 export class SyntheticEmbeddings extends Embeddings {
     constructor(params) {
         super(params ?? {});
@@ -21,9 +42,21 @@ export class SyntheticEmbeddings extends Embeddings {
         });
         this.vectorSize = params?.vectorSize ?? 4;
     }
+    /**
+     * Generates synthetic embeddings for a list of documents.
+     * @param documents List of documents to generate embeddings for.
+     * @returns A promise that resolves with a list of synthetic embeddings for each document.
+     */
     async embedDocuments(documents) {
         return Promise.all(documents.map((doc) => this.embedQuery(doc)));
     }
+    /**
+     * Generates a synthetic embedding for a document. The document is
+     * converted into chunks, a numerical value is calculated for each chunk,
+     * and an array of these values is returned as the embedding.
+     * @param document The document to generate an embedding for.
+     * @returns A promise that resolves with a synthetic embedding for the document.
+     */
     async embedQuery(document) {
         let doc = document;
         // Only use the letters (and space) from the document, and make them lower case

package/dist/embeddings/googlepalm.cjs

@@ -5,6 +5,10 @@ const generativelanguage_1 = require("@google-ai/generativelanguage");
 const google_auth_library_1 = require("google-auth-library");
 const base_js_1 = require("./base.cjs");
 const env_js_1 = require("../util/env.cjs");
+/**
+ * Class that extends the Embeddings class and provides methods for
+ * generating embeddings using the Google Palm API.
+ */
 class GooglePaLMEmbeddings extends base_js_1.Embeddings {
     constructor(fields) {
         super(fields ?? {});
@@ -45,9 +49,23 @@ class GooglePaLMEmbeddings extends base_js_1.Embeddings {
         });
         return res[0].embedding?.value ?? [];
     }
+    /**
+     * Method that takes a document as input and returns a promise that
+     * resolves to an embedding for the document. It calls the _embedText
+     * method with the document as the input.
+     * @param document Document for which to generate an embedding.
+     * @returns Promise that resolves to an embedding for the input document.
+     */
     embedQuery(document) {
         return this.caller.callWithOptions({}, this._embedText.bind(this), document);
     }
+    /**
+     * Method that takes an array of documents as input and returns a promise
+     * that resolves to a 2D array of embeddings for each document. It calls
+     * the _embedText method for each document in the array.
+     * @param documents Array of documents for which to generate embeddings.
+     * @returns Promise that resolves to a 2D array of embeddings for each input document.
+     */
     embedDocuments(documents) {
         return Promise.all(documents.map((document) => this._embedText(document)));
     }

package/dist/embeddings/googlepalm.d.ts

@@ -1,4 +1,8 @@
 import { Embeddings, EmbeddingsParams } from "./base.js";
+/**
+ * Interface that extends EmbeddingsParams and defines additional
+ * parameters specific to the GooglePaLMEmbeddings class.
+ */
 export interface GooglePaLMEmbeddingsParams extends EmbeddingsParams {
     /**
      * Model Name to use
@@ -11,12 +15,30 @@ export interface GooglePaLMEmbeddingsParams extends EmbeddingsParams {
      */
     apiKey?: string;
 }
+/**
+ * Class that extends the Embeddings class and provides methods for
+ * generating embeddings using the Google Palm API.
+ */
 export declare class GooglePaLMEmbeddings extends Embeddings implements GooglePaLMEmbeddingsParams {
     apiKey?: string;
     modelName: string;
     private client;
     constructor(fields?: GooglePaLMEmbeddingsParams);
     protected _embedText(text: string): Promise<number[]>;
+    /**
+     * Method that takes a document as input and returns a promise that
+     * resolves to an embedding for the document. It calls the _embedText
+     * method with the document as the input.
+     * @param document Document for which to generate an embedding.
+     * @returns Promise that resolves to an embedding for the input document.
+     */
     embedQuery(document: string): Promise<number[]>;
+    /**
+     * Method that takes an array of documents as input and returns a promise
+     * that resolves to a 2D array of embeddings for each document. It calls
+     * the _embedText method for each document in the array.
+     * @param documents Array of documents for which to generate embeddings.
+     * @returns Promise that resolves to a 2D array of embeddings for each input document.
+     */
     embedDocuments(documents: string[]): Promise<number[][]>;
 }

package/dist/embeddings/googlepalm.js

@@ -2,6 +2,10 @@ import { TextServiceClient } from "@google-ai/generativelanguage";
 import { GoogleAuth } from "google-auth-library";
 import { Embeddings } from "./base.js";
 import { getEnvironmentVariable } from "../util/env.js";
+/**
+ * Class that extends the Embeddings class and provides methods for
+ * generating embeddings using the Google Palm API.
+ */
 export class GooglePaLMEmbeddings extends Embeddings {
     constructor(fields) {
         super(fields ?? {});
@@ -42,9 +46,23 @@ export class GooglePaLMEmbeddings extends Embeddings {
         });
         return res[0].embedding?.value ?? [];
     }
+    /**
+     * Method that takes a document as input and returns a promise that
+     * resolves to an embedding for the document. It calls the _embedText
+     * method with the document as the input.
+     * @param document Document for which to generate an embedding.
+     * @returns Promise that resolves to an embedding for the input document.
+     */
     embedQuery(document) {
         return this.caller.callWithOptions({}, this._embedText.bind(this), document);
     }
+    /**
+     * Method that takes an array of documents as input and returns a promise
+     * that resolves to a 2D array of embeddings for each document. It calls
+     * the _embedText method for each document in the array.
+     * @param documents Array of documents for which to generate embeddings.
+     * @returns Promise that resolves to a 2D array of embeddings for each input document.
+     */
     embedDocuments(documents) {
         return Promise.all(documents.map((document) => this._embedText(document)));
     }

package/dist/embeddings/googlevertexai.cjs

@@ -36,6 +36,14 @@ class GoogleVertexAIEmbeddings extends base_js_1.Embeddings {
         this.model = fields?.model ?? this.model;
         this.connection = new googlevertexai_connection_js_1.GoogleVertexAIConnection({ ...fields, ...this }, this.caller);
     }
+    /**
+     * Takes an array of documents as input and returns a promise that
+     * resolves to a 2D array of embeddings for each document. It splits the
+     * documents into chunks and makes requests to the Google Vertex AI API to
+     * generate embeddings.
+     * @param documents An array of documents to be embedded.
+     * @returns A promise that resolves to a 2D array of embeddings for each document.
+     */
     async embedDocuments(documents) {
         const instanceChunks = (0, chunk_js_1.chunkArray)(documents.map((document) => ({
             content: document,
@@ -48,6 +56,13 @@ class GoogleVertexAIEmbeddings extends base_js_1.Embeddings {
             .flat() ?? [];
         return result;
     }
+    /**
+     * Takes a document as input and returns a promise that resolves to an
+     * embedding for the document. It calls the embedDocuments method with the
+     * document as the input.
+     * @param document A document to be embedded.
+     * @returns A promise that resolves to an embedding for the document.
+     */
     async embedQuery(document) {
         const data = await this.embedDocuments([document]);
         return data[0];

package/dist/embeddings/googlevertexai.d.ts

@@ -1,5 +1,10 @@
 import { Embeddings, EmbeddingsParams } from "./base.js";
 import { GoogleVertexAIConnectionParams } from "../types/googlevertexai-types.js";
+/**
+ * Defines the parameters required to initialize a
+ * GoogleVertexAIEmbeddings instance. It extends EmbeddingsParams and
+ * GoogleVertexAIConnectionParams.
+ */
 export interface GoogleVertexAIEmbeddingsParams extends EmbeddingsParams, GoogleVertexAIConnectionParams {
 }
 /**
@@ -20,6 +25,21 @@ export declare class GoogleVertexAIEmbeddings extends Embeddings implements Goog
     model: string;
     private connection;
     constructor(fields?: GoogleVertexAIEmbeddingsParams);
+    /**
+     * Takes an array of documents as input and returns a promise that
+     * resolves to a 2D array of embeddings for each document. It splits the
+     * documents into chunks and makes requests to the Google Vertex AI API to
+     * generate embeddings.
+     * @param documents An array of documents to be embedded.
+     * @returns A promise that resolves to a 2D array of embeddings for each document.
+     */
     embedDocuments(documents: string[]): Promise<number[][]>;
+    /**
+     * Takes a document as input and returns a promise that resolves to an
+     * embedding for the document. It calls the embedDocuments method with the
+     * document as the input.
+     * @param document A document to be embedded.
+     * @returns A promise that resolves to an embedding for the document.
+     */
     embedQuery(document: string): Promise<number[]>;
 }

package/dist/embeddings/googlevertexai.js

@@ -33,6 +33,14 @@ export class GoogleVertexAIEmbeddings extends Embeddings {
         this.model = fields?.model ?? this.model;
         this.connection = new GoogleVertexAIConnection({ ...fields, ...this }, this.caller);
     }
+    /**
+     * Takes an array of documents as input and returns a promise that
+     * resolves to a 2D array of embeddings for each document. It splits the
+     * documents into chunks and makes requests to the Google Vertex AI API to
+     * generate embeddings.
+     * @param documents An array of documents to be embedded.
+     * @returns A promise that resolves to a 2D array of embeddings for each document.
+     */
     async embedDocuments(documents) {
         const instanceChunks = chunkArray(documents.map((document) => ({
             content: document,
@@ -45,6 +53,13 @@ export class GoogleVertexAIEmbeddings extends Embeddings {
             .flat() ?? [];
         return result;
     }
+    /**
+     * Takes a document as input and returns a promise that resolves to an
+     * embedding for the document. It calls the embedDocuments method with the
+     * document as the input.
+     * @param document A document to be embedded.
+     * @returns A promise that resolves to an embedding for the document.
+     */
     async embedQuery(document) {
         const data = await this.embedDocuments([document]);
         return data[0];

package/dist/embeddings/hf.cjs

@@ -4,6 +4,11 @@ exports.HuggingFaceInferenceEmbeddings = void 0;
 const inference_1 = require("@huggingface/inference");
 const base_js_1 = require("./base.cjs");
 const env_js_1 = require("../util/env.cjs");
+/**
+ * Class that extends the Embeddings class and provides methods for
+ * generating embeddings using Hugging Face models through the
+ * HuggingFaceInference API.
+ */
 class HuggingFaceInferenceEmbeddings extends base_js_1.Embeddings {
     constructor(fields) {
         super(fields ?? {});
@@ -39,9 +44,24 @@ class HuggingFaceInferenceEmbeddings extends base_js_1.Embeddings {
             inputs: clean,
         }));
     }
+    /**
+     * Method that takes a document as input and returns a promise that
+     * resolves to an embedding for the document. It calls the _embed method
+     * with the document as the input and returns the first embedding in the
+     * resulting array.
+     * @param document Document to generate an embedding for.
+     * @returns Promise that resolves to an embedding for the document.
+     */
     embedQuery(document) {
         return this._embed([document]).then((embeddings) => embeddings[0]);
     }
+    /**
+     * Method that takes an array of documents as input and returns a promise
+     * that resolves to a 2D array of embeddings for each document. It calls
+     * the _embed method with the documents as the input.
+     * @param documents Array of documents to generate embeddings for.
+     * @returns Promise that resolves to a 2D array of embeddings for each document.
+     */
     embedDocuments(documents) {
         return this._embed(documents);
     }

package/dist/embeddings/hf.d.ts

@@ -1,15 +1,39 @@
 import { HfInference } from "@huggingface/inference";
 import { Embeddings, EmbeddingsParams } from "./base.js";
+/**
+ * Interface that extends EmbeddingsParams and defines additional
+ * parameters specific to the HuggingFaceInferenceEmbeddings class.
+ */
 export interface HuggingFaceInferenceEmbeddingsParams extends EmbeddingsParams {
     apiKey?: string;
     model?: string;
 }
+/**
+ * Class that extends the Embeddings class and provides methods for
+ * generating embeddings using Hugging Face models through the
+ * HuggingFaceInference API.
+ */
 export declare class HuggingFaceInferenceEmbeddings extends Embeddings implements HuggingFaceInferenceEmbeddingsParams {
     apiKey?: string;
     model: string;
     client: HfInference;
     constructor(fields?: HuggingFaceInferenceEmbeddingsParams);
     _embed(texts: string[]): Promise<number[][]>;
+    /**
+     * Method that takes a document as input and returns a promise that
+     * resolves to an embedding for the document. It calls the _embed method
+     * with the document as the input and returns the first embedding in the
+     * resulting array.
+     * @param document Document to generate an embedding for.
+     * @returns Promise that resolves to an embedding for the document.
+     */
     embedQuery(document: string): Promise<number[]>;
+    /**
+     * Method that takes an array of documents as input and returns a promise
+     * that resolves to a 2D array of embeddings for each document. It calls
+     * the _embed method with the documents as the input.
+     * @param documents Array of documents to generate embeddings for.
+     * @returns Promise that resolves to a 2D array of embeddings for each document.
+     */
     embedDocuments(documents: string[]): Promise<number[][]>;
 }

package/dist/embeddings/hf.js

@@ -1,6 +1,11 @@
 import { HfInference } from "@huggingface/inference";
 import { Embeddings } from "./base.js";
 import { getEnvironmentVariable } from "../util/env.js";
+/**
+ * Class that extends the Embeddings class and provides methods for
+ * generating embeddings using Hugging Face models through the
+ * HuggingFaceInference API.
+ */
 export class HuggingFaceInferenceEmbeddings extends Embeddings {
     constructor(fields) {
         super(fields ?? {});
@@ -36,9 +41,24 @@ export class HuggingFaceInferenceEmbeddings extends Embeddings {
             inputs: clean,
         }));
     }
+    /**
+     * Method that takes a document as input and returns a promise that
+     * resolves to an embedding for the document. It calls the _embed method
+     * with the document as the input and returns the first embedding in the
+     * resulting array.
+     * @param document Document to generate an embedding for.
+     * @returns Promise that resolves to an embedding for the document.
+     */
     embedQuery(document) {
         return this._embed([document]).then((embeddings) => embeddings[0]);
     }
+    /**
+     * Method that takes an array of documents as input and returns a promise
+     * that resolves to a 2D array of embeddings for each document. It calls
+     * the _embed method with the documents as the input.
+     * @param documents Array of documents to generate embeddings for.
+     * @returns Promise that resolves to a 2D array of embeddings for each document.
+     */
     embedDocuments(documents) {
         return this._embed(documents);
     }

package/dist/embeddings/openai.cjs

@@ -10,6 +10,11 @@ const axios_fetch_adapter_js_1 = __importDefault(require("../util/axios-fetch-ad
 const chunk_js_1 = require("../util/chunk.cjs");
 const base_js_1 = require("./base.cjs");
 const azure_js_1 = require("../util/azure.cjs");
+/**
+ * Class for generating embeddings using the OpenAI API. Extends the
+ * Embeddings class and implements OpenAIEmbeddingsParams and
+ * AzureOpenAIInput.
+ */
 class OpenAIEmbeddings extends base_js_1.Embeddings {
     constructor(fields, configuration) {
         const fieldsWithDefaults = { maxConcurrency: 2, ...fields };
@@ -124,6 +129,13 @@ class OpenAIEmbeddings extends base_js_1.Embeddings {
             ...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_js_1.chunkArray)(this.stripNewLines ? texts.map((t) => t.replace(/\n/g, " ")) : texts, this.batchSize);
         const batchRequests = batches.map((batch) => this.embeddingWithRetry({
@@ -141,6 +153,12 @@ class OpenAIEmbeddings extends base_js_1.Embeddings {
         }
         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 { data } = await this.embeddingWithRetry({
             model: this.modelName,
@@ -148,6 +166,13 @@ class OpenAIEmbeddings extends base_js_1.Embeddings {
         });
         return data.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 = {

package/dist/embeddings/openai.d.ts

@@ -1,6 +1,10 @@
 import { ConfigurationParameters } from "openai";
 import { AzureOpenAIInput } from "../types/openai-types.js";
 import { Embeddings, EmbeddingsParams } from "./base.js";
+/**
+ * Interface for OpenAIEmbeddings parameters. Extends EmbeddingsParams and
+ * defines additional parameters specific to the OpenAIEmbeddings class.
+ */
 export interface OpenAIEmbeddingsParams extends EmbeddingsParams {
     /** Model name to use */
     modelName: string;
@@ -19,6 +23,11 @@ export interface OpenAIEmbeddingsParams extends EmbeddingsParams {
      */
     stripNewLines?: boolean;
 }
+/**
+ * Class for generating embeddings using the OpenAI API. Extends the
+ * Embeddings class and implements OpenAIEmbeddingsParams and
+ * AzureOpenAIInput.
+ */
 export declare class OpenAIEmbeddings extends Embeddings implements OpenAIEmbeddingsParams, AzureOpenAIInput {
     modelName: string;
     batchSize: number;
@@ -35,7 +44,27 @@ export declare class OpenAIEmbeddings extends Embeddings implements OpenAIEmbedd
         verbose?: boolean;
         openAIApiKey?: string;
     }, configuration?: ConfigurationParameters);
+    /**
+     * 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<number[][]>;
+    /**
+     * 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<number[]>;
+    /**
+     * 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.
+     */
     private embeddingWithRetry;
 }

package/dist/embeddings/openai.js

@@ -4,6 +4,11 @@ import fetchAdapter from "../util/axios-fetch-adapter.js";
 import { chunkArray } from "../util/chunk.js";
 import { Embeddings } from "./base.js";
 import { getEndpoint } from "../util/azure.js";
+/**
+ * Class for generating embeddings using the OpenAI API. Extends the
+ * Embeddings class and implements OpenAIEmbeddingsParams and
+ * AzureOpenAIInput.
+ */
 export class OpenAIEmbeddings extends Embeddings {
     constructor(fields, configuration) {
         const fieldsWithDefaults = { maxConcurrency: 2, ...fields };
@@ -118,6 +123,13 @@ export class OpenAIEmbeddings extends Embeddings {
             ...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 = chunkArray(this.stripNewLines ? texts.map((t) => t.replace(/\n/g, " ")) : texts, this.batchSize);
         const batchRequests = batches.map((batch) => this.embeddingWithRetry({
@@ -135,6 +147,12 @@ export class OpenAIEmbeddings extends Embeddings {
         }
         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 { data } = await this.embeddingWithRetry({
             model: this.modelName,
@@ -142,6 +160,13 @@ export class OpenAIEmbeddings extends Embeddings {
         });
         return data.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 = {