langchain 0.0.131 → 0.0.132

package/dist/vectorstores/vectara.cjs

@@ -5,6 +5,10 @@ const document_js_1 = require("../document.cjs");
 const fake_js_1 = require("../embeddings/fake.cjs");
 const env_js_1 = require("../util/env.cjs");
 const base_js_1 = require("./base.cjs");
+/**
+ * Class for interacting with the Vectara API. Extends the VectorStore
+ * class.
+ */
 class VectaraStore extends base_js_1.VectorStore {
     get lc_secrets() {
         return {
@@ -80,6 +84,10 @@ class VectaraStore extends base_js_1.VectorStore {
         this.customerId = customerId;
         this.verbose = args.verbose ?? false;
     }
+    /**
+     * Returns a header for Vectara API calls.
+     * @returns A Promise that resolves to a VectaraCallHeader object.
+     */
     async getJsonHeader() {
         return {
             headers: {
@@ -89,9 +97,21 @@ class VectaraStore extends base_js_1.VectorStore {
             },
         };
     }
+    /**
+     * Throws an error, as this method is not implemented. Use addDocuments
+     * instead.
+     * @param _vectors Not used.
+     * @param _documents Not used.
+     * @returns Does not return a value.
+     */
     async addVectors(_vectors, _documents) {
         throw new Error("Method not implemented. Please call addDocuments instead.");
     }
+    /**
+     * Adds documents to the Vectara store.
+     * @param documents An array of Document objects to add to the Vectara store.
+     * @returns A Promise that resolves when the documents have been added.
+     */
     async addDocuments(documents) {
         const headers = await this.getJsonHeader();
         let countAdded = 0;
@@ -143,6 +163,47 @@ class VectaraStore extends base_js_1.VectorStore {
             console.log(`Added ${countAdded} documents to Vectara`);
         }
     }
+    async addFiles(filePaths, metadata = undefined) {
+        let numDocs = 0;
+        for (const [index, fileBlob] of filePaths.entries()) {
+            const md = metadata ? metadata[index] : {};
+            const data = new FormData();
+            data.append("file", fileBlob, `file_${index}`);
+            data.append("doc-metadata", JSON.stringify(md));
+            try {
+                const response = await fetch(`https://api.vectara.io/v1/upload?c=${this.customerId}&o=${this.corpusId}`, {
+                    method: "POST",
+                    headers: {
+                        "x-api-key": this.apiKey,
+                    },
+                    body: data,
+                });
+                const result = await response.json();
+                const { status } = response;
+                if (status !== 200 && status !== 409) {
+                    throw new Error(`Vectara API returned status code ${status}: ${result}`);
+                }
+                else {
+                    numDocs += 1;
+                }
+            }
+            catch (err) {
+                console.error(`Failed to upload file at index ${index}:`, err);
+            }
+        }
+        if (this.verbose) {
+            console.log(`Uploaded ${filePaths.length} files to Vectara`);
+        }
+        return numDocs;
+    }
+    /**
+     * Performs a similarity search and returns documents along with their
+     * scores.
+     * @param query The query string for the similarity search.
+     * @param k Optional. The number of results to return. Default is 10.
+     * @param filter Optional. A VectaraFilter object to refine the search results.
+     * @returns A Promise that resolves to an array of tuples, each containing a Document and its score.
+     */
     async similaritySearchWithScore(query, k = 10, filter = undefined) {
         const headers = await this.getJsonHeader();
         const data = {
@@ -179,6 +240,19 @@ class VectaraStore extends base_js_1.VectorStore {
         }
         const result = await response.json();
         const responses = result.responseSet[0].response;
+        const documents = result.responseSet[0].document;
+        for (let i = 0; i < responses.length; i += 1) {
+            const responseMetadata = responses[i].metadata;
+            const documentMetadata = documents[responses[i].documentIndex].metadata;
+            const combinedMetadata = {};
+            responseMetadata.forEach((item) => {
+                combinedMetadata[item.name] = item.value;
+            });
+            documentMetadata.forEach((item) => {
+                combinedMetadata[item.name] = item.value;
+            });
+            responses[i].metadata = Object.entries(combinedMetadata).map(([name, value]) => ({ name, value }));
+        }
         const documentsAndScores = responses.map((response) => [
             new document_js_1.Document({
                 pageContent: response.text,
@@ -188,13 +262,36 @@ class VectaraStore extends base_js_1.VectorStore {
         ]);
         return documentsAndScores;
     }
+    /**
+     * Performs a similarity search and returns documents.
+     * @param query The query string for the similarity search.
+     * @param k Optional. The number of results to return. Default is 10.
+     * @param filter Optional. A VectaraFilter object to refine the search results.
+     * @returns A Promise that resolves to an array of Document objects.
+     */
     async similaritySearch(query, k = 10, filter = undefined) {
         const resultWithScore = await this.similaritySearchWithScore(query, k, filter);
         return resultWithScore.map((result) => result[0]);
     }
+    /**
+     * Throws an error, as this method is not implemented. Use
+     * similaritySearch or similaritySearchWithScore instead.
+     * @param _query Not used.
+     * @param _k Not used.
+     * @param _filter Not used.
+     * @returns Does not return a value.
+     */
     async similaritySearchVectorWithScore(_query, _k, _filter) {
         throw new Error("Method not implemented. Please call similaritySearch or similaritySearchWithScore instead.");
     }
+    /**
+     * Creates a VectaraStore instance from texts.
+     * @param texts An array of text strings.
+     * @param metadatas Metadata for the texts. Can be a single object or an array of objects.
+     * @param _embeddings Not used.
+     * @param args A VectaraLibArgs object for initializing the VectaraStore instance.
+     * @returns A Promise that resolves to a VectaraStore instance.
+     */
     static fromTexts(texts, metadatas, _embeddings, args) {
         const docs = [];
         for (let i = 0; i < texts.length; i += 1) {
@@ -207,6 +304,13 @@ class VectaraStore extends base_js_1.VectorStore {
         }
         return VectaraStore.fromDocuments(docs, new fake_js_1.FakeEmbeddings(), args);
     }
+    /**
+     * Creates a VectaraStore instance from documents.
+     * @param docs An array of Document objects.
+     * @param _embeddings Not used.
+     * @param args A VectaraLibArgs object for initializing the VectaraStore instance.
+     * @returns A Promise that resolves to a VectaraStore instance.
+     */
     static async fromDocuments(docs, _embeddings, args) {
         const instance = new this(args);
         await instance.addDocuments(docs);

package/dist/vectorstores/vectara.d.ts

@@ -1,12 +1,19 @@
 import { Document } from "../document.js";
 import { Embeddings } from "../embeddings/base.js";
 import { VectorStore } from "./base.js";
+/**
+ * Interface for the arguments required to initialize a VectaraStore
+ * instance.
+ */
 export interface VectaraLibArgs {
     customerId: number;
     corpusId: number;
     apiKey: string;
     verbose?: boolean;
 }
+/**
+ * Interface for the headers required for Vectara API calls.
+ */
 interface VectaraCallHeader {
     headers: {
         "x-api-key": string;
@@ -14,15 +21,25 @@ interface VectaraCallHeader {
         "customer-id": string;
     };
 }
+/**
+ * Interface for the filter options used in Vectara API calls.
+ */
 export interface VectaraFilter {
     filter?: string;
     lambda?: number;
     contextConfig?: VectaraContextConfig;
 }
+/**
+ * Interface for the context configuration used in Vectara API calls.
+ */
 export interface VectaraContextConfig {
     sentencesBefore?: number;
     sentencesAfter?: number;
 }
+/**
+ * Class for interacting with the Vectara API. Extends the VectorStore
+ * class.
+ */
 export declare class VectaraStore extends VectorStore {
     get lc_secrets(): {
         [key: string]: string;
@@ -39,13 +56,68 @@ export declare class VectaraStore extends VectorStore {
     private vectaraApiTimeoutSeconds;
     _vectorstoreType(): string;
     constructor(args: VectaraLibArgs);
+    /**
+     * Returns a header for Vectara API calls.
+     * @returns A Promise that resolves to a VectaraCallHeader object.
+     */
     getJsonHeader(): Promise<VectaraCallHeader>;
+    /**
+     * Throws an error, as this method is not implemented. Use addDocuments
+     * instead.
+     * @param _vectors Not used.
+     * @param _documents Not used.
+     * @returns Does not return a value.
+     */
     addVectors(_vectors: number[][], _documents: Document[]): Promise<void>;
+    /**
+     * Adds documents to the Vectara store.
+     * @param documents An array of Document objects to add to the Vectara store.
+     * @returns A Promise that resolves when the documents have been added.
+     */
     addDocuments(documents: Document[]): Promise<void>;
+    addFiles(filePaths: Blob[], metadata?: Record<string, unknown> | undefined): Promise<number>;
+    /**
+     * Performs a similarity search and returns documents along with their
+     * scores.
+     * @param query The query string for the similarity search.
+     * @param k Optional. The number of results to return. Default is 10.
+     * @param filter Optional. A VectaraFilter object to refine the search results.
+     * @returns A Promise that resolves to an array of tuples, each containing a Document and its score.
+     */
     similaritySearchWithScore(query: string, k?: number, filter?: VectaraFilter | undefined): Promise<[Document, number][]>;
+    /**
+     * Performs a similarity search and returns documents.
+     * @param query The query string for the similarity search.
+     * @param k Optional. The number of results to return. Default is 10.
+     * @param filter Optional. A VectaraFilter object to refine the search results.
+     * @returns A Promise that resolves to an array of Document objects.
+     */
     similaritySearch(query: string, k?: number, filter?: VectaraFilter | undefined): Promise<Document[]>;
+    /**
+     * Throws an error, as this method is not implemented. Use
+     * similaritySearch or similaritySearchWithScore instead.
+     * @param _query Not used.
+     * @param _k Not used.
+     * @param _filter Not used.
+     * @returns Does not return a value.
+     */
     similaritySearchVectorWithScore(_query: number[], _k: number, _filter?: VectaraFilter | undefined): Promise<[Document, number][]>;
+    /**
+     * Creates a VectaraStore instance from texts.
+     * @param texts An array of text strings.
+     * @param metadatas Metadata for the texts. Can be a single object or an array of objects.
+     * @param _embeddings Not used.
+     * @param args A VectaraLibArgs object for initializing the VectaraStore instance.
+     * @returns A Promise that resolves to a VectaraStore instance.
+     */
     static fromTexts(texts: string[], metadatas: object | object[], _embeddings: Embeddings, args: VectaraLibArgs): Promise<VectaraStore>;
+    /**
+     * Creates a VectaraStore instance from documents.
+     * @param docs An array of Document objects.
+     * @param _embeddings Not used.
+     * @param args A VectaraLibArgs object for initializing the VectaraStore instance.
+     * @returns A Promise that resolves to a VectaraStore instance.
+     */
     static fromDocuments(docs: Document[], _embeddings: Embeddings, args: VectaraLibArgs): Promise<VectaraStore>;
 }
 export {};

package/dist/vectorstores/vectara.js

@@ -2,6 +2,10 @@ import { Document } from "../document.js";
 import { FakeEmbeddings } from "../embeddings/fake.js";
 import { getEnvironmentVariable } from "../util/env.js";
 import { VectorStore } from "./base.js";
+/**
+ * Class for interacting with the Vectara API. Extends the VectorStore
+ * class.
+ */
 export class VectaraStore extends VectorStore {
     get lc_secrets() {
         return {
@@ -77,6 +81,10 @@ export class VectaraStore extends VectorStore {
         this.customerId = customerId;
         this.verbose = args.verbose ?? false;
     }
+    /**
+     * Returns a header for Vectara API calls.
+     * @returns A Promise that resolves to a VectaraCallHeader object.
+     */
     async getJsonHeader() {
         return {
             headers: {
@@ -86,9 +94,21 @@ export class VectaraStore extends VectorStore {
             },
         };
     }
+    /**
+     * Throws an error, as this method is not implemented. Use addDocuments
+     * instead.
+     * @param _vectors Not used.
+     * @param _documents Not used.
+     * @returns Does not return a value.
+     */
     async addVectors(_vectors, _documents) {
         throw new Error("Method not implemented. Please call addDocuments instead.");
     }
+    /**
+     * Adds documents to the Vectara store.
+     * @param documents An array of Document objects to add to the Vectara store.
+     * @returns A Promise that resolves when the documents have been added.
+     */
     async addDocuments(documents) {
         const headers = await this.getJsonHeader();
         let countAdded = 0;
@@ -140,6 +160,47 @@ export class VectaraStore extends VectorStore {
             console.log(`Added ${countAdded} documents to Vectara`);
         }
     }
+    async addFiles(filePaths, metadata = undefined) {
+        let numDocs = 0;
+        for (const [index, fileBlob] of filePaths.entries()) {
+            const md = metadata ? metadata[index] : {};
+            const data = new FormData();
+            data.append("file", fileBlob, `file_${index}`);
+            data.append("doc-metadata", JSON.stringify(md));
+            try {
+                const response = await fetch(`https://api.vectara.io/v1/upload?c=${this.customerId}&o=${this.corpusId}`, {
+                    method: "POST",
+                    headers: {
+                        "x-api-key": this.apiKey,
+                    },
+                    body: data,
+                });
+                const result = await response.json();
+                const { status } = response;
+                if (status !== 200 && status !== 409) {
+                    throw new Error(`Vectara API returned status code ${status}: ${result}`);
+                }
+                else {
+                    numDocs += 1;
+                }
+            }
+            catch (err) {
+                console.error(`Failed to upload file at index ${index}:`, err);
+            }
+        }
+        if (this.verbose) {
+            console.log(`Uploaded ${filePaths.length} files to Vectara`);
+        }
+        return numDocs;
+    }
+    /**
+     * Performs a similarity search and returns documents along with their
+     * scores.
+     * @param query The query string for the similarity search.
+     * @param k Optional. The number of results to return. Default is 10.
+     * @param filter Optional. A VectaraFilter object to refine the search results.
+     * @returns A Promise that resolves to an array of tuples, each containing a Document and its score.
+     */
     async similaritySearchWithScore(query, k = 10, filter = undefined) {
         const headers = await this.getJsonHeader();
         const data = {
@@ -176,6 +237,19 @@ export class VectaraStore extends VectorStore {
         }
         const result = await response.json();
         const responses = result.responseSet[0].response;
+        const documents = result.responseSet[0].document;
+        for (let i = 0; i < responses.length; i += 1) {
+            const responseMetadata = responses[i].metadata;
+            const documentMetadata = documents[responses[i].documentIndex].metadata;
+            const combinedMetadata = {};
+            responseMetadata.forEach((item) => {
+                combinedMetadata[item.name] = item.value;
+            });
+            documentMetadata.forEach((item) => {
+                combinedMetadata[item.name] = item.value;
+            });
+            responses[i].metadata = Object.entries(combinedMetadata).map(([name, value]) => ({ name, value }));
+        }
         const documentsAndScores = responses.map((response) => [
             new Document({
                 pageContent: response.text,
@@ -185,13 +259,36 @@ export class VectaraStore extends VectorStore {
         ]);
         return documentsAndScores;
     }
+    /**
+     * Performs a similarity search and returns documents.
+     * @param query The query string for the similarity search.
+     * @param k Optional. The number of results to return. Default is 10.
+     * @param filter Optional. A VectaraFilter object to refine the search results.
+     * @returns A Promise that resolves to an array of Document objects.
+     */
     async similaritySearch(query, k = 10, filter = undefined) {
         const resultWithScore = await this.similaritySearchWithScore(query, k, filter);
         return resultWithScore.map((result) => result[0]);
     }
+    /**
+     * Throws an error, as this method is not implemented. Use
+     * similaritySearch or similaritySearchWithScore instead.
+     * @param _query Not used.
+     * @param _k Not used.
+     * @param _filter Not used.
+     * @returns Does not return a value.
+     */
     async similaritySearchVectorWithScore(_query, _k, _filter) {
         throw new Error("Method not implemented. Please call similaritySearch or similaritySearchWithScore instead.");
     }
+    /**
+     * Creates a VectaraStore instance from texts.
+     * @param texts An array of text strings.
+     * @param metadatas Metadata for the texts. Can be a single object or an array of objects.
+     * @param _embeddings Not used.
+     * @param args A VectaraLibArgs object for initializing the VectaraStore instance.
+     * @returns A Promise that resolves to a VectaraStore instance.
+     */
     static fromTexts(texts, metadatas, _embeddings, args) {
         const docs = [];
         for (let i = 0; i < texts.length; i += 1) {
@@ -204,6 +301,13 @@ export class VectaraStore extends VectorStore {
         }
         return VectaraStore.fromDocuments(docs, new FakeEmbeddings(), args);
     }
+    /**
+     * Creates a VectaraStore instance from documents.
+     * @param docs An array of Document objects.
+     * @param _embeddings Not used.
+     * @param args A VectaraLibArgs object for initializing the VectaraStore instance.
+     * @returns A Promise that resolves to a VectaraStore instance.
+     */
     static async fromDocuments(docs, _embeddings, args) {
         const instance = new this(args);
         await instance.addDocuments(docs);

package/dist/vectorstores/weaviate.cjs

@@ -64,6 +64,11 @@ obj) => {
     return flattenedObject;
 };
 exports.flattenObjectForWeaviate = flattenObjectForWeaviate;
+/**
+ * Class that extends the `VectorStore` base class. It provides methods to
+ * interact with a Weaviate index, including adding vectors and documents,
+ * deleting data, and performing similarity searches.
+ */
 class WeaviateStore extends base_js_1.VectorStore {
     _vectorstoreType() {
         return "weaviate";
@@ -128,6 +133,14 @@ class WeaviateStore extends base_js_1.VectorStore {
             ];
         }
     }
+    /**
+     * Method to add vectors and corresponding documents to the Weaviate
+     * index.
+     * @param vectors Array of vectors to be added.
+     * @param documents Array of documents corresponding to the vectors.
+     * @param options Optional parameter that can include specific IDs for the documents.
+     * @returns An array of document IDs.
+     */
     async addVectors(vectors, documents, options) {
         const documentIds = options?.ids ?? documents.map((_) => uuid.v4());
         const batch = documents.map((document, index) => {
@@ -156,9 +169,23 @@ class WeaviateStore extends base_js_1.VectorStore {
         }
         return documentIds;
     }
+    /**
+     * Method to add documents to the Weaviate index. It first generates
+     * vectors for the documents using the embeddings, then adds the vectors
+     * and documents to the index.
+     * @param documents Array of documents to be added.
+     * @param options Optional parameter that can include specific IDs for the documents.
+     * @returns An array of document IDs.
+     */
     async addDocuments(documents, options) {
         return this.addVectors(await this.embeddings.embedDocuments(documents.map((d) => d.pageContent)), documents, options);
     }
+    /**
+     * Method to delete data from the Weaviate index. It can delete data based
+     * on specific IDs or a filter.
+     * @param params Object that includes either an array of IDs or a filter for the data to be deleted.
+     * @returns Promise that resolves when the deletion is complete.
+     */
     async delete(params) {
         const { ids, filter } = params;
         if (ids && ids.length > 0) {
@@ -187,6 +214,15 @@ class WeaviateStore extends base_js_1.VectorStore {
             throw new Error(`This method requires either "ids" or "filter" to be set in the input object`);
         }
     }
+    /**
+     * Method to perform a similarity search on the stored vectors in the
+     * Weaviate index. It returns the top k most similar documents and their
+     * similarity scores.
+     * @param query The query vector.
+     * @param k The number of most similar documents to return.
+     * @param filter Optional filter to apply to the search.
+     * @returns An array of tuples, where each tuple contains a document and its similarity score.
+     */
     async similaritySearchVectorWithScore(query, k, filter) {
         try {
             let builder = await this.client.graphql
@@ -222,6 +258,16 @@ class WeaviateStore extends base_js_1.VectorStore {
             throw Error(`'Error in similaritySearch' ${e}`);
         }
     }
+    /**
+     * Static method to create a new `WeaviateStore` instance from a list of
+     * texts. It first creates documents from the texts and metadata, then
+     * adds the documents to the Weaviate index.
+     * @param texts Array of texts.
+     * @param metadatas Metadata for the texts. Can be a single object or an array of objects.
+     * @param embeddings Embeddings to be used for the texts.
+     * @param args Arguments required to create a new `WeaviateStore` instance.
+     * @returns A new `WeaviateStore` instance.
+     */
     static fromTexts(texts, metadatas, embeddings, args) {
         const docs = [];
         for (let i = 0; i < texts.length; i += 1) {
@@ -234,11 +280,26 @@ class WeaviateStore extends base_js_1.VectorStore {
         }
         return WeaviateStore.fromDocuments(docs, embeddings, args);
     }
+    /**
+     * Static method to create a new `WeaviateStore` instance from a list of
+     * documents. It adds the documents to the Weaviate index.
+     * @param docs Array of documents.
+     * @param embeddings Embeddings to be used for the documents.
+     * @param args Arguments required to create a new `WeaviateStore` instance.
+     * @returns A new `WeaviateStore` instance.
+     */
     static async fromDocuments(docs, embeddings, args) {
         const instance = new this(embeddings, args);
         await instance.addDocuments(docs);
         return instance;
     }
+    /**
+     * Static method to create a new `WeaviateStore` instance from an existing
+     * Weaviate index.
+     * @param embeddings Embeddings to be used for the Weaviate index.
+     * @param args Arguments required to create a new `WeaviateStore` instance.
+     * @returns A new `WeaviateStore` instance.
+     */
     static async fromExistingIndex(embeddings, args) {
         return new this(embeddings, args);
     }

package/dist/vectorstores/weaviate.d.ts

@@ -3,6 +3,11 @@ import { VectorStore } from "./base.js";
 import { Embeddings } from "../embeddings/base.js";
 import { Document } from "../document.js";
 export declare const flattenObjectForWeaviate: (obj: Record<string, any>) => Record<string, any>;
+/**
+ * Interface that defines the arguments required to create a new instance
+ * of the `WeaviateStore` class. It includes the Weaviate client, the name
+ * of the class in Weaviate, and optional keys for text and metadata.
+ */
 export interface WeaviateLibArgs {
     client: WeaviateClient;
     /**
@@ -13,10 +18,19 @@ export interface WeaviateLibArgs {
     metadataKeys?: string[];
     tenant?: string;
 }
+/**
+ * Interface that defines a filter for querying data from Weaviate. It
+ * includes a distance and a `WhereFilter`.
+ */
 export interface WeaviateFilter {
     distance?: number;
     where: WhereFilter;
 }
+/**
+ * Class that extends the `VectorStore` base class. It provides methods to
+ * interact with a Weaviate index, including adding vectors and documents,
+ * deleting data, and performing similarity searches.
+ */
 export declare class WeaviateStore extends VectorStore {
     embeddings: Embeddings;
     FilterType: WeaviateFilter;
@@ -27,18 +41,74 @@ export declare class WeaviateStore extends VectorStore {
     private tenant?;
     _vectorstoreType(): string;
     constructor(embeddings: Embeddings, args: WeaviateLibArgs);
+    /**
+     * Method to add vectors and corresponding documents to the Weaviate
+     * index.
+     * @param vectors Array of vectors to be added.
+     * @param documents Array of documents corresponding to the vectors.
+     * @param options Optional parameter that can include specific IDs for the documents.
+     * @returns An array of document IDs.
+     */
     addVectors(vectors: number[][], documents: Document[], options?: {
         ids?: string[];
     }): Promise<string[]>;
+    /**
+     * Method to add documents to the Weaviate index. It first generates
+     * vectors for the documents using the embeddings, then adds the vectors
+     * and documents to the index.
+     * @param documents Array of documents to be added.
+     * @param options Optional parameter that can include specific IDs for the documents.
+     * @returns An array of document IDs.
+     */
     addDocuments(documents: Document[], options?: {
         ids?: string[];
     }): Promise<string[]>;
+    /**
+     * Method to delete data from the Weaviate index. It can delete data based
+     * on specific IDs or a filter.
+     * @param params Object that includes either an array of IDs or a filter for the data to be deleted.
+     * @returns Promise that resolves when the deletion is complete.
+     */
     delete(params: {
         ids?: string[];
         filter?: WeaviateFilter;
     }): Promise<void>;
+    /**
+     * Method to perform a similarity search on the stored vectors in the
+     * Weaviate index. It returns the top k most similar documents and their
+     * similarity scores.
+     * @param query The query vector.
+     * @param k The number of most similar documents to return.
+     * @param filter Optional filter to apply to the search.
+     * @returns An array of tuples, where each tuple contains a document and its similarity score.
+     */
     similaritySearchVectorWithScore(query: number[], k: number, filter?: WeaviateFilter): Promise<[Document, number][]>;
+    /**
+     * Static method to create a new `WeaviateStore` instance from a list of
+     * texts. It first creates documents from the texts and metadata, then
+     * adds the documents to the Weaviate index.
+     * @param texts Array of texts.
+     * @param metadatas Metadata for the texts. Can be a single object or an array of objects.
+     * @param embeddings Embeddings to be used for the texts.
+     * @param args Arguments required to create a new `WeaviateStore` instance.
+     * @returns A new `WeaviateStore` instance.
+     */
     static fromTexts(texts: string[], metadatas: object | object[], embeddings: Embeddings, args: WeaviateLibArgs): Promise<WeaviateStore>;
+    /**
+     * Static method to create a new `WeaviateStore` instance from a list of
+     * documents. It adds the documents to the Weaviate index.
+     * @param docs Array of documents.
+     * @param embeddings Embeddings to be used for the documents.
+     * @param args Arguments required to create a new `WeaviateStore` instance.
+     * @returns A new `WeaviateStore` instance.
+     */
     static fromDocuments(docs: Document[], embeddings: Embeddings, args: WeaviateLibArgs): Promise<WeaviateStore>;
+    /**
+     * Static method to create a new `WeaviateStore` instance from an existing
+     * Weaviate index.
+     * @param embeddings Embeddings to be used for the Weaviate index.
+     * @param args Arguments required to create a new `WeaviateStore` instance.
+     * @returns A new `WeaviateStore` instance.
+     */
     static fromExistingIndex(embeddings: Embeddings, args: WeaviateLibArgs): Promise<WeaviateStore>;
 }