langchain 0.0.131 → 0.0.132

package/dist/tools/sql.js

@@ -2,6 +2,12 @@ import { Tool } from "./base.js";
 import { OpenAI } from "../llms/openai.js";
 import { LLMChain } from "../chains/llm_chain.js";
 import { PromptTemplate } from "../prompts/prompt.js";
+/**
+ * A tool for executing SQL queries. It takes a SQL database as a
+ * parameter and assigns it to the `db` property. The `_call` method is
+ * used to run the SQL query and return the result. If the query is
+ * incorrect, an error message is returned.
+ */
 export class QuerySqlTool extends Tool {
     static lc_name() {
         return "QuerySqlTool";
@@ -40,6 +46,13 @@ export class QuerySqlTool extends Tool {
         }
     }
 }
+/**
+ * A tool for retrieving information about SQL tables. It takes a SQL
+ * database as a parameter and assigns it to the `db` property. The
+ * `_call` method is used to retrieve the schema and sample rows for the
+ * specified tables. If the tables do not exist, an error message is
+ * returned.
+ */
 export class InfoSqlTool extends Tool {
     static lc_name() {
         return "InfoSqlTool";
@@ -80,6 +93,12 @@ export class InfoSqlTool extends Tool {
         }
     }
 }
+/**
+ * A tool for listing all tables in a SQL database. It takes a SQL
+ * database as a parameter and assigns it to the `db` property. The
+ * `_call` method is used to return a comma-separated list of all tables
+ * in the database.
+ */
 export class ListTablesSqlTool extends Tool {
     static lc_name() {
         return "ListTablesSqlTool";
@@ -117,6 +136,12 @@ export class ListTablesSqlTool extends Tool {
         }
     }
 }
+/**
+ * A tool for checking SQL queries for common mistakes. It takes a
+ * LLMChain or QueryCheckerToolArgs as a parameter. The `_call` method is
+ * used to check the input query for common mistakes and returns a
+ * prediction.
+ */
 export class QueryCheckerTool extends Tool {
     static lc_name() {
         return "QueryCheckerTool";

package/dist/tools/vectorstore.cjs

@@ -3,6 +3,11 @@ Object.defineProperty(exports, "__esModule", { value: true });
 exports.VectorStoreQATool = void 0;
 const vector_db_qa_js_1 = require("../chains/vector_db_qa.cjs");
 const base_js_1 = require("./base.cjs");
+/**
+ * A tool for the VectorDBQA chain to interact with a Vector Store. It is
+ * used to answer questions about a specific topic. The input to this tool
+ * should be a fully formed question.
+ */
 class VectorStoreQATool extends base_js_1.Tool {
     static lc_name() {
         return "VectorStoreQATool";
@@ -45,6 +50,12 @@ class VectorStoreQATool extends base_js_1.Tool {
         this.llm = fields.llm;
         this.chain = vector_db_qa_js_1.VectorDBQAChain.fromLLM(this.llm, this.vectorStore);
     }
+    /**
+     * Returns a string that describes what the tool does.
+     * @param name The name of the tool.
+     * @param description A description of what the tool does.
+     * @returns A string that describes what the tool does.
+     */
     static getDescription(name, description) {
         return `Useful for when you need to answer questions about ${name}. Whenever you need information about ${description} you should ALWAYS use this. Input should be a fully formed question.`;
     }

package/dist/tools/vectorstore.d.ts

@@ -2,10 +2,18 @@ import { VectorStore } from "../vectorstores/base.js";
 import { BaseLanguageModel } from "../base_language/index.js";
 import { VectorDBQAChain } from "../chains/vector_db_qa.js";
 import { Tool } from "./base.js";
+/**
+ * Interface for tools that interact with a Vector Store.
+ */
 interface VectorStoreTool {
     vectorStore: VectorStore;
     llm: BaseLanguageModel;
 }
+/**
+ * A tool for the VectorDBQA chain to interact with a Vector Store. It is
+ * used to answer questions about a specific topic. The input to this tool
+ * should be a fully formed question.
+ */
 export declare class VectorStoreQATool extends Tool implements VectorStoreTool {
     static lc_name(): string;
     vectorStore: VectorStore;
@@ -14,6 +22,12 @@ export declare class VectorStoreQATool extends Tool implements VectorStoreTool {
     description: string;
     chain: VectorDBQAChain;
     constructor(name: string, description: string, fields: VectorStoreTool);
+    /**
+     * Returns a string that describes what the tool does.
+     * @param name The name of the tool.
+     * @param description A description of what the tool does.
+     * @returns A string that describes what the tool does.
+     */
     static getDescription(name: string, description: string): string;
     /** @ignore */
     _call(input: string): Promise<string>;

package/dist/tools/vectorstore.js

@@ -1,5 +1,10 @@
 import { VectorDBQAChain } from "../chains/vector_db_qa.js";
 import { Tool } from "./base.js";
+/**
+ * A tool for the VectorDBQA chain to interact with a Vector Store. It is
+ * used to answer questions about a specific topic. The input to this tool
+ * should be a fully formed question.
+ */
 export class VectorStoreQATool extends Tool {
     static lc_name() {
         return "VectorStoreQATool";
@@ -42,6 +47,12 @@ export class VectorStoreQATool extends Tool {
         this.llm = fields.llm;
         this.chain = VectorDBQAChain.fromLLM(this.llm, this.vectorStore);
     }
+    /**
+     * Returns a string that describes what the tool does.
+     * @param name The name of the tool.
+     * @param description A description of what the tool does.
+     * @returns A string that describes what the tool does.
+     */
     static getDescription(name, description) {
         return `Useful for when you need to answer questions about ${name}. Whenever you need information about ${description} you should ALWAYS use this. Input should be a fully formed question.`;
     }

package/dist/tools/webbrowser.cjs

@@ -133,6 +133,12 @@ const DEFAULT_HEADERS = {
     "Upgrade-Insecure-Requests": "1",
     "User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/111.0",
 };
+/**
+ * A class designed to interact with web pages, either to extract
+ * information from them or to summarize their content. It uses the axios
+ * library to send HTTP requests and the cheerio library to parse the
+ * returned HTML.
+ */
 class WebBrowser extends base_js_1.Tool {
     static lc_name() {
         return "WebBrowser";

package/dist/tools/webbrowser.d.ts

@@ -7,6 +7,12 @@ import { Embeddings } from "../embeddings/base.js";
 export declare const parseInputs: (inputs: string) => [string, string];
 export declare const getText: (html: string, baseUrl: string, summary: boolean) => string;
 type Headers = Record<string, any>;
+/**
+ * Defines the arguments that can be passed to the WebBrowser constructor.
+ * It extends the ToolParams interface and includes properties for a
+ * language model, embeddings, HTTP headers, an Axios configuration, a
+ * callback manager, and a text splitter.
+ */
 export interface WebBrowserArgs extends ToolParams {
     model: BaseLanguageModel;
     embeddings: Embeddings;
@@ -16,6 +22,12 @@ export interface WebBrowserArgs extends ToolParams {
     callbackManager?: CallbackManager;
     textSplitter?: TextSplitter;
 }
+/**
+ * A class designed to interact with web pages, either to extract
+ * information from them or to summarize their content. It uses the axios
+ * library to send HTTP requests and the cheerio library to parse the
+ * returned HTML.
+ */
 export declare class WebBrowser extends Tool {
     static lc_name(): string;
     get lc_namespace(): string[];

package/dist/tools/webbrowser.js

@@ -102,6 +102,12 @@ const DEFAULT_HEADERS = {
     "Upgrade-Insecure-Requests": "1",
     "User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/111.0",
 };
+/**
+ * A class designed to interact with web pages, either to extract
+ * information from them or to summarize their content. It uses the axios
+ * library to send HTTP requests and the cheerio library to parse the
+ * returned HTML.
+ */
 export class WebBrowser extends Tool {
     static lc_name() {
         return "WebBrowser";

package/dist/tools/wikipedia_query_run.cjs

@@ -2,6 +2,10 @@
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.WikipediaQueryRun = void 0;
 const base_js_1 = require("./base.cjs");
+/**
+ * Class for interacting with and fetching data from the Wikipedia API. It
+ * extends the Tool class.
+ */
 class WikipediaQueryRun extends base_js_1.Tool {
     static lc_name() {
         return "WikipediaQueryRun";
@@ -61,6 +65,13 @@ class WikipediaQueryRun extends base_js_1.Tool {
             return summaries.join("\n\n").slice(0, this.maxDocContentLength);
         }
     }
+    /**
+     * Fetches the content of a specific Wikipedia page. It returns the
+     * extracted content as a string.
+     * @param page The specific Wikipedia page to fetch its content.
+     * @param redirect A boolean value to indicate whether to redirect or not.
+     * @returns The extracted content of the specific Wikipedia page as a string.
+     */
     async content(page, redirect = true) {
         try {
             const result = await this._fetchPage(page, redirect);
@@ -70,6 +81,11 @@ class WikipediaQueryRun extends base_js_1.Tool {
             throw new Error(`Failed to fetch content for page "${page}": ${error}`);
         }
     }
+    /**
+     * Builds a URL for the Wikipedia API using the provided parameters.
+     * @param parameters The parameters to be used in building the URL.
+     * @returns A string representing the built URL.
+     */
     buildUrl(parameters) {
         const nonUndefinedParams = Object.entries(parameters)
             .filter(([_, value]) => value !== undefined)

package/dist/tools/wikipedia_query_run.d.ts

@@ -1,10 +1,22 @@
 import { Tool } from "./base.js";
+/**
+ * Interface for the parameters that can be passed to the
+ * WikipediaQueryRun constructor.
+ */
 export interface WikipediaQueryRunParams {
     topKResults?: number;
     maxDocContentLength?: number;
     baseUrl?: string;
 }
+/**
+ * Type alias for URL parameters. Represents a record where keys are
+ * strings and values can be string, number, boolean, undefined, or null.
+ */
 type UrlParameters = Record<string, string | number | boolean | undefined | null>;
+/**
+ * Class for interacting with and fetching data from the Wikipedia API. It
+ * extends the Tool class.
+ */
 export declare class WikipediaQueryRun extends Tool {
     static lc_name(): string;
     name: string;
@@ -14,7 +26,19 @@ export declare class WikipediaQueryRun extends Tool {
     protected baseUrl: string;
     constructor(params?: WikipediaQueryRunParams);
     _call(query: string): Promise<string>;
+    /**
+     * Fetches the content of a specific Wikipedia page. It returns the
+     * extracted content as a string.
+     * @param page The specific Wikipedia page to fetch its content.
+     * @param redirect A boolean value to indicate whether to redirect or not.
+     * @returns The extracted content of the specific Wikipedia page as a string.
+     */
     content(page: string, redirect?: boolean): Promise<string>;
+    /**
+     * Builds a URL for the Wikipedia API using the provided parameters.
+     * @param parameters The parameters to be used in building the URL.
+     * @returns A string representing the built URL.
+     */
     protected buildUrl<P extends UrlParameters>(parameters: P): string;
     private _fetchSearchResults;
     private _fetchPage;

package/dist/tools/wikipedia_query_run.js

@@ -1,4 +1,8 @@
 import { Tool } from "./base.js";
+/**
+ * Class for interacting with and fetching data from the Wikipedia API. It
+ * extends the Tool class.
+ */
 export class WikipediaQueryRun extends Tool {
     static lc_name() {
         return "WikipediaQueryRun";
@@ -58,6 +62,13 @@ export class WikipediaQueryRun extends Tool {
             return summaries.join("\n\n").slice(0, this.maxDocContentLength);
         }
     }
+    /**
+     * Fetches the content of a specific Wikipedia page. It returns the
+     * extracted content as a string.
+     * @param page The specific Wikipedia page to fetch its content.
+     * @param redirect A boolean value to indicate whether to redirect or not.
+     * @returns The extracted content of the specific Wikipedia page as a string.
+     */
     async content(page, redirect = true) {
         try {
             const result = await this._fetchPage(page, redirect);
@@ -67,6 +78,11 @@ export class WikipediaQueryRun extends Tool {
             throw new Error(`Failed to fetch content for page "${page}": ${error}`);
         }
     }
+    /**
+     * Builds a URL for the Wikipedia API using the provided parameters.
+     * @param parameters The parameters to be used in building the URL.
+     * @returns A string representing the built URL.
+     */
     buildUrl(parameters) {
         const nonUndefinedParams = Object.entries(parameters)
             .filter(([_, value]) => value !== undefined)

package/dist/tools/zapier.cjs

@@ -18,6 +18,13 @@ const zapierNLABaseDescription = "A wrapper around Zapier NLA actions. " +
     "If you get a none or null response, STOP EXECUTION, do not try to another tool! " +
     "This tool specifically used for: {zapier_description}, " +
     "and has params: {params}";
+/**
+ * A wrapper class for Zapier's Natural Language Actions (NLA). It
+ * provides an interface to interact with the 5k+ apps and 20k+ actions on
+ * Zapier's platform through a natural language API interface. This
+ * includes apps like Gmail, Salesforce, Trello, Slack, Asana, HubSpot,
+ * Google Sheets, Microsoft Teams, and many more.
+ */
 class ZapierNLAWrapper extends serializable_js_1.Serializable {
     get lc_secrets() {
         return {
@@ -179,6 +186,11 @@ class ZapierNLAWrapper extends serializable_js_1.Serializable {
     }
 }
 exports.ZapierNLAWrapper = ZapierNLAWrapper;
+/**
+ * A tool that uses the `ZapierNLAWrapper` to run a specific action. It
+ * takes in the `ZapierNLAWrapper` instance, an action ID, a description,
+ * a schema for the parameters, and optionally the parameters themselves.
+ */
 class ZapierNLARunAction extends base_js_1.Tool {
     static lc_name() {
         return "ZapierNLARunAction";

package/dist/tools/zapier.d.ts

@@ -14,6 +14,13 @@ export interface ZapierNLAWrapperParams extends AsyncCallerParams {
      */
     oauthAccessToken?: string;
 }
+/**
+ * A wrapper class for Zapier's Natural Language Actions (NLA). It
+ * provides an interface to interact with the 5k+ apps and 20k+ actions on
+ * Zapier's platform through a natural language API interface. This
+ * includes apps like Gmail, Salesforce, Trello, Slack, Asana, HubSpot,
+ * Google Sheets, Microsoft Teams, and many more.
+ */
 export declare class ZapierNLAWrapper extends Serializable {
     lc_namespace: string[];
     get lc_secrets(): {
@@ -67,6 +74,11 @@ export declare class ZapierNLAWrapper extends Serializable {
      */
     listActionsAsString(): Promise<string>;
 }
+/**
+ * A tool that uses the `ZapierNLAWrapper` to run a specific action. It
+ * takes in the `ZapierNLAWrapper` instance, an action ID, a description,
+ * a schema for the parameters, and optionally the parameters themselves.
+ */
 export declare class ZapierNLARunAction extends Tool {
     static lc_name(): string;
     apiWrapper: ZapierNLAWrapper;

package/dist/tools/zapier.js

@@ -15,6 +15,13 @@ const zapierNLABaseDescription = "A wrapper around Zapier NLA actions. " +
     "If you get a none or null response, STOP EXECUTION, do not try to another tool! " +
     "This tool specifically used for: {zapier_description}, " +
     "and has params: {params}";
+/**
+ * A wrapper class for Zapier's Natural Language Actions (NLA). It
+ * provides an interface to interact with the 5k+ apps and 20k+ actions on
+ * Zapier's platform through a natural language API interface. This
+ * includes apps like Gmail, Salesforce, Trello, Slack, Asana, HubSpot,
+ * Google Sheets, Microsoft Teams, and many more.
+ */
 export class ZapierNLAWrapper extends Serializable {
     get lc_secrets() {
         return {
@@ -175,6 +182,11 @@ export class ZapierNLAWrapper extends Serializable {
         return JSON.stringify(result);
     }
 }
+/**
+ * A tool that uses the `ZapierNLAWrapper` to run a specific action. It
+ * takes in the `ZapierNLAWrapper` instance, an action ID, a description,
+ * a schema for the parameters, and optionally the parameters themselves.
+ */
 export class ZapierNLARunAction extends Tool {
     static lc_name() {
         return "ZapierNLARunAction";

package/dist/vectorstores/analyticdb.cjs

@@ -36,6 +36,12 @@ const base_js_1 = require("./base.cjs");
 const document_js_1 = require("../document.cjs");
 const _LANGCHAIN_DEFAULT_EMBEDDING_DIM = 1536;
 const _LANGCHAIN_DEFAULT_COLLECTION_NAME = "langchain_document";
+/**
+ * Class that provides methods for creating and managing a collection of
+ * documents in an AnalyticDB, adding documents or vectors to the
+ * collection, performing similarity search on vectors, and creating an
+ * instance of `AnalyticDBVectorStore` from texts or documents.
+ */
 class AnalyticDBVectorStore extends base_js_1.VectorStore {
     _vectorstoreType() {
         return "analyticdb";
@@ -85,9 +91,20 @@ class AnalyticDBVectorStore extends base_js_1.VectorStore {
             args.collectionName || _LANGCHAIN_DEFAULT_COLLECTION_NAME;
         this.preDeleteCollection = args.preDeleteCollection || false;
     }
+    /**
+     * Closes all the clients in the pool and terminates the pool.
+     * @returns Promise that resolves when all clients are closed and the pool is terminated.
+     */
     async end() {
         return this.pool.end();
     }
+    /**
+     * Creates a new table in the database if it does not already exist. The
+     * table is created with columns for id, embedding, document, and
+     * metadata. An index is also created on the embedding column if it does
+     * not already exist.
+     * @returns Promise that resolves when the table and index are created.
+     */
     async createTableIfNotExists() {
         const client = await this.pool.connect();
         try {
@@ -131,10 +148,20 @@ class AnalyticDBVectorStore extends base_js_1.VectorStore {
             client.release();
         }
     }
+    /**
+     * Deletes the collection from the database if it exists.
+     * @returns Promise that resolves when the collection is deleted.
+     */
     async deleteCollection() {
         const dropStatement = `DROP TABLE IF EXISTS ${this.collectionName};`;
         await this.pool.query(dropStatement);
     }
+    /**
+     * Creates a new collection in the database. If `preDeleteCollection` is
+     * true, any existing collection with the same name is deleted before the
+     * new collection is created.
+     * @returns Promise that resolves when the collection is created.
+     */
     async createCollection() {
         if (this.preDeleteCollection) {
             await this.deleteCollection();
@@ -142,10 +169,24 @@ class AnalyticDBVectorStore extends base_js_1.VectorStore {
         await this.createTableIfNotExists();
         this.isCreateCollection = true;
     }
+    /**
+     * Adds an array of documents to the collection. The documents are first
+     * converted to vectors using the `embedDocuments` method of the
+     * `embeddings` instance.
+     * @param documents Array of Document instances to be added to the collection.
+     * @returns Promise that resolves when the documents are added.
+     */
     async addDocuments(documents) {
         const texts = documents.map(({ pageContent }) => pageContent);
         return this.addVectors(await this.embeddings.embedDocuments(texts), documents);
     }
+    /**
+     * Adds an array of vectors and corresponding documents to the collection.
+     * The vectors and documents are batch inserted into the database.
+     * @param vectors Array of vectors to be added to the collection.
+     * @param documents Array of Document instances corresponding to the vectors.
+     * @returns Promise that resolves when the vectors and documents are added.
+     */
     async addVectors(vectors, documents) {
         if (vectors.length === 0) {
             return;
@@ -212,6 +253,16 @@ class AnalyticDBVectorStore extends base_js_1.VectorStore {
             client.release();
         }
     }
+    /**
+     * Performs a similarity search on the vectors in the collection. The
+     * search is performed using the given query vector and returns the top k
+     * most similar vectors along with their corresponding documents and
+     * similarity scores.
+     * @param query Query vector for the similarity search.
+     * @param k Number of top similar vectors to return.
+     * @param filter Optional. Filter to apply on the metadata of the documents.
+     * @returns Promise that resolves to an array of tuples, each containing a Document instance and its similarity score.
+     */
     async similaritySearchVectorWithScore(query, k, filter) {
         if (!this.isCreateCollection) {
             await this.createCollection();
@@ -241,6 +292,16 @@ class AnalyticDBVectorStore extends base_js_1.VectorStore {
         ]);
         return result;
     }
+    /**
+     * Creates an instance of `AnalyticDBVectorStore` from an array of texts
+     * and corresponding metadata. The texts are first converted to Document
+     * instances before being added to the collection.
+     * @param texts Array of texts to be added to the collection.
+     * @param metadatas Array or object of metadata corresponding to the texts.
+     * @param embeddings Embeddings instance used to convert the texts to vectors.
+     * @param dbConfig Configuration for the AnalyticDB.
+     * @returns Promise that resolves to an instance of `AnalyticDBVectorStore`.
+     */
     static async fromTexts(texts, metadatas, embeddings, dbConfig) {
         const docs = [];
         for (let i = 0; i < texts.length; i += 1) {
@@ -253,11 +314,26 @@ class AnalyticDBVectorStore extends base_js_1.VectorStore {
         }
         return AnalyticDBVectorStore.fromDocuments(docs, embeddings, dbConfig);
     }
+    /**
+     * Creates an instance of `AnalyticDBVectorStore` from an array of
+     * Document instances. The documents are added to the collection.
+     * @param docs Array of Document instances to be added to the collection.
+     * @param embeddings Embeddings instance used to convert the documents to vectors.
+     * @param dbConfig Configuration for the AnalyticDB.
+     * @returns Promise that resolves to an instance of `AnalyticDBVectorStore`.
+     */
     static async fromDocuments(docs, embeddings, dbConfig) {
         const instance = new this(embeddings, dbConfig);
         await instance.addDocuments(docs);
         return instance;
     }
+    /**
+     * Creates an instance of `AnalyticDBVectorStore` from an existing index
+     * in the database. A new collection is created in the database.
+     * @param embeddings Embeddings instance used to convert the documents to vectors.
+     * @param dbConfig Configuration for the AnalyticDB.
+     * @returns Promise that resolves to an instance of `AnalyticDBVectorStore`.
+     */
     static async fromExistingIndex(embeddings, dbConfig) {
         const instance = new this(embeddings, dbConfig);
         await instance.createCollection();

package/dist/vectorstores/analyticdb.d.ts

@@ -2,12 +2,22 @@ import { PoolConfig } from "pg";
 import { VectorStore } from "./base.js";
 import { Embeddings } from "../embeddings/base.js";
 import { Document } from "../document.js";
+/**
+ * Interface defining the arguments required to create an instance of
+ * `AnalyticDBVectorStore`.
+ */
 export interface AnalyticDBArgs {
     connectionOptions: PoolConfig;
     embeddingDimension?: number;
     collectionName?: string;
     preDeleteCollection?: boolean;
 }
+/**
+ * Class that provides methods for creating and managing a collection of
+ * documents in an AnalyticDB, adding documents or vectors to the
+ * collection, performing similarity search on vectors, and creating an
+ * instance of `AnalyticDBVectorStore` from texts or documents.
+ */
 export declare class AnalyticDBVectorStore extends VectorStore {
     FilterType: Record<string, any>;
     private pool;
@@ -17,14 +27,84 @@ export declare class AnalyticDBVectorStore extends VectorStore {
     private isCreateCollection;
     _vectorstoreType(): string;
     constructor(embeddings: Embeddings, args: AnalyticDBArgs);
+    /**
+     * Closes all the clients in the pool and terminates the pool.
+     * @returns Promise that resolves when all clients are closed and the pool is terminated.
+     */
     end(): Promise<void>;
+    /**
+     * Creates a new table in the database if it does not already exist. The
+     * table is created with columns for id, embedding, document, and
+     * metadata. An index is also created on the embedding column if it does
+     * not already exist.
+     * @returns Promise that resolves when the table and index are created.
+     */
     createTableIfNotExists(): Promise<void>;
+    /**
+     * Deletes the collection from the database if it exists.
+     * @returns Promise that resolves when the collection is deleted.
+     */
     deleteCollection(): Promise<void>;
+    /**
+     * Creates a new collection in the database. If `preDeleteCollection` is
+     * true, any existing collection with the same name is deleted before the
+     * new collection is created.
+     * @returns Promise that resolves when the collection is created.
+     */
     createCollection(): Promise<void>;
+    /**
+     * Adds an array of documents to the collection. The documents are first
+     * converted to vectors using the `embedDocuments` method of the
+     * `embeddings` instance.
+     * @param documents Array of Document instances to be added to the collection.
+     * @returns Promise that resolves when the documents are added.
+     */
     addDocuments(documents: Document[]): Promise<void>;
+    /**
+     * Adds an array of vectors and corresponding documents to the collection.
+     * The vectors and documents are batch inserted into the database.
+     * @param vectors Array of vectors to be added to the collection.
+     * @param documents Array of Document instances corresponding to the vectors.
+     * @returns Promise that resolves when the vectors and documents are added.
+     */
     addVectors(vectors: number[][], documents: Document[]): Promise<void>;
+    /**
+     * Performs a similarity search on the vectors in the collection. The
+     * search is performed using the given query vector and returns the top k
+     * most similar vectors along with their corresponding documents and
+     * similarity scores.
+     * @param query Query vector for the similarity search.
+     * @param k Number of top similar vectors to return.
+     * @param filter Optional. Filter to apply on the metadata of the documents.
+     * @returns Promise that resolves to an array of tuples, each containing a Document instance and its similarity score.
+     */
     similaritySearchVectorWithScore(query: number[], k: number, filter?: this["FilterType"]): Promise<[Document, number][]>;
+    /**
+     * Creates an instance of `AnalyticDBVectorStore` from an array of texts
+     * and corresponding metadata. The texts are first converted to Document
+     * instances before being added to the collection.
+     * @param texts Array of texts to be added to the collection.
+     * @param metadatas Array or object of metadata corresponding to the texts.
+     * @param embeddings Embeddings instance used to convert the texts to vectors.
+     * @param dbConfig Configuration for the AnalyticDB.
+     * @returns Promise that resolves to an instance of `AnalyticDBVectorStore`.
+     */
     static fromTexts(texts: string[], metadatas: object[] | object, embeddings: Embeddings, dbConfig: AnalyticDBArgs): Promise<AnalyticDBVectorStore>;
+    /**
+     * Creates an instance of `AnalyticDBVectorStore` from an array of
+     * Document instances. The documents are added to the collection.
+     * @param docs Array of Document instances to be added to the collection.
+     * @param embeddings Embeddings instance used to convert the documents to vectors.
+     * @param dbConfig Configuration for the AnalyticDB.
+     * @returns Promise that resolves to an instance of `AnalyticDBVectorStore`.
+     */
     static fromDocuments(docs: Document[], embeddings: Embeddings, dbConfig: AnalyticDBArgs): Promise<AnalyticDBVectorStore>;
+    /**
+     * Creates an instance of `AnalyticDBVectorStore` from an existing index
+     * in the database. A new collection is created in the database.
+     * @param embeddings Embeddings instance used to convert the documents to vectors.
+     * @param dbConfig Configuration for the AnalyticDB.
+     * @returns Promise that resolves to an instance of `AnalyticDBVectorStore`.
+     */
     static fromExistingIndex(embeddings: Embeddings, dbConfig: AnalyticDBArgs): Promise<AnalyticDBVectorStore>;
 }