langchain 0.0.202 → 0.0.204-rc.0

package/dist/document_loaders/fs/openai_whisper_audio.cjs

@@ -1,7 +1,7 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.OpenAIWhisperAudio = void 0;
-const openai_1 = require("openai");
+const openai_1 = require("@langchain/openai");
 const document_js_1 = require("../../document.cjs");
 const buffer_js_1 = require("./buffer.cjs");
 const MODEL_NAME = "whisper-1";
@@ -24,7 +24,7 @@ class OpenAIWhisperAudio extends buffer_js_1.BufferLoader {
             writable: true,
             value: void 0
         });
-        this.openAIClient = new openai_1.OpenAI(fields?.clientOptions);
+        this.openAIClient = new openai_1.OpenAIClient(fields?.clientOptions);
     }
     async parse(raw, metadata) {
         const fileName = metadata.source === "blob" ? metadata.blobType : metadata.source;

package/dist/document_loaders/fs/openai_whisper_audio.d.ts

@@ -1,5 +1,5 @@
 /// <reference types="node" resolution-mode="require"/>
-import { type ClientOptions } from "openai";
+import { type ClientOptions } from "@langchain/openai";
 import { Document } from "../../document.js";
 import { BufferLoader } from "./buffer.js";
 /**

package/dist/document_loaders/fs/openai_whisper_audio.js

@@ -1,4 +1,4 @@
-import { OpenAI as OpenAIClient, toFile } from "openai";
+import { OpenAIClient, toFile } from "@langchain/openai";
 import { Document } from "../../document.js";
 import { BufferLoader } from "./buffer.js";
 const MODEL_NAME = "whisper-1";

package/dist/document_loaders/fs/pdf.cjs

@@ -15,7 +15,7 @@ const document_js_2 = require("../../util/document.cjs");
  * ```
  */
 class PDFLoader extends buffer_js_1.BufferLoader {
-    constructor(filePathOrBlob, { splitPages = true, pdfjs = PDFLoaderImports, parsedItemSeparator = " ", } = {}) {
+    constructor(filePathOrBlob, { splitPages = true, pdfjs = PDFLoaderImports, parsedItemSeparator = "", } = {}) {
         super(filePathOrBlob);
         Object.defineProperty(this, "splitPages", {
             enumerable: true,

package/dist/document_loaders/fs/pdf.js

@@ -12,7 +12,7 @@ import { formatDocumentsAsString } from "../../util/document.js";
  * ```
  */
 export class PDFLoader extends BufferLoader {
-    constructor(filePathOrBlob, { splitPages = true, pdfjs = PDFLoaderImports, parsedItemSeparator = " ", } = {}) {
+    constructor(filePathOrBlob, { splitPages = true, pdfjs = PDFLoaderImports, parsedItemSeparator = "", } = {}) {
         super(filePathOrBlob);
         Object.defineProperty(this, "splitPages", {
             enumerable: true,

package/dist/document_loaders/web/pdf.cjs

@@ -14,7 +14,7 @@ const document_js_2 = require("../../util/document.cjs");
  * ```
  */
 class WebPDFLoader extends base_js_1.BaseDocumentLoader {
-    constructor(blob, { splitPages = true, pdfjs = PDFLoaderImports, parsedItemSeparator = " ", } = {}) {
+    constructor(blob, { splitPages = true, pdfjs = PDFLoaderImports, parsedItemSeparator = "", } = {}) {
         super();
         Object.defineProperty(this, "blob", {
             enumerable: true,

package/dist/document_loaders/web/pdf.js

@@ -11,7 +11,7 @@ import { formatDocumentsAsString } from "../../util/document.js";
  * ```
  */
 export class WebPDFLoader extends BaseDocumentLoader {
-    constructor(blob, { splitPages = true, pdfjs = PDFLoaderImports, parsedItemSeparator = " ", } = {}) {
+    constructor(blob, { splitPages = true, pdfjs = PDFLoaderImports, parsedItemSeparator = "", } = {}) {
         super();
         Object.defineProperty(this, "blob", {
             enumerable: true,

package/dist/document_transformers/html_to_text.cjs

@@ -1,49 +1,17 @@
 "use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.HtmlToTextTransformer = void 0;
-const html_to_text_1 = require("html-to-text");
-const document_js_1 = require("../document.cjs");
-const document_js_2 = require("../schema/document.cjs");
-/**
- * A transformer that converts HTML content to plain text.
- * @example
- * ```typescript
- * const loader = new CheerioWebBaseLoader("https://example.com/some-page");
- * const docs = await loader.load();
- *
- * const splitter = new RecursiveCharacterTextSplitter({
- *  maxCharacterCount: 1000,
- * });
- * const transformer = new HtmlToTextTransformer();
- *
- * // The sequence of text splitting followed by HTML to text transformation
- * const sequence = splitter.pipe(transformer);
- *
- * // Processing the loaded documents through the sequence
- * const newDocuments = await sequence.invoke(docs);
- *
- * console.log(newDocuments);
- * ```
- */
-class HtmlToTextTransformer extends document_js_2.MappingDocumentTransformer {
-    static lc_name() {
-        return "HtmlToTextTransformer";
-    }
-    constructor(options = {}) {
-        super(options);
-        Object.defineProperty(this, "options", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: options
-        });
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
     }
-    async _transformDocument(document) {
-        const extractedContent = (0, html_to_text_1.htmlToText)(document.pageContent, this.options);
-        return new document_js_1.Document({
-            pageContent: extractedContent,
-            metadata: { ...document.metadata },
-        });
-    }
-}
-exports.HtmlToTextTransformer = HtmlToTextTransformer;
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __exportStar = (this && this.__exportStar) || function(m, exports) {
+    for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports, p)) __createBinding(exports, m, p);
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+__exportStar(require("@langchain/community/document_transformers/html_to_text"), exports);

package/dist/document_transformers/html_to_text.d.ts

@@ -1,30 +1 @@
-import type { HtmlToTextOptions } from "html-to-text";
-import { Document } from "../document.js";
-import { MappingDocumentTransformer } from "../schema/document.js";
-/**
- * A transformer that converts HTML content to plain text.
- * @example
- * ```typescript
- * const loader = new CheerioWebBaseLoader("https://example.com/some-page");
- * const docs = await loader.load();
- *
- * const splitter = new RecursiveCharacterTextSplitter({
- *  maxCharacterCount: 1000,
- * });
- * const transformer = new HtmlToTextTransformer();
- *
- * // The sequence of text splitting followed by HTML to text transformation
- * const sequence = splitter.pipe(transformer);
- *
- * // Processing the loaded documents through the sequence
- * const newDocuments = await sequence.invoke(docs);
- *
- * console.log(newDocuments);
- * ```
- */
-export declare class HtmlToTextTransformer extends MappingDocumentTransformer {
-    protected options: HtmlToTextOptions;
-    static lc_name(): string;
-    constructor(options?: HtmlToTextOptions);
-    _transformDocument(document: Document): Promise<Document>;
-}
+export * from "@langchain/community/document_transformers/html_to_text";

package/dist/document_transformers/html_to_text.js

@@ -1,45 +1 @@
-import { htmlToText } from "html-to-text";
-import { Document } from "../document.js";
-import { MappingDocumentTransformer } from "../schema/document.js";
-/**
- * A transformer that converts HTML content to plain text.
- * @example
- * ```typescript
- * const loader = new CheerioWebBaseLoader("https://example.com/some-page");
- * const docs = await loader.load();
- *
- * const splitter = new RecursiveCharacterTextSplitter({
- *  maxCharacterCount: 1000,
- * });
- * const transformer = new HtmlToTextTransformer();
- *
- * // The sequence of text splitting followed by HTML to text transformation
- * const sequence = splitter.pipe(transformer);
- *
- * // Processing the loaded documents through the sequence
- * const newDocuments = await sequence.invoke(docs);
- *
- * console.log(newDocuments);
- * ```
- */
-export class HtmlToTextTransformer extends MappingDocumentTransformer {
-    static lc_name() {
-        return "HtmlToTextTransformer";
-    }
-    constructor(options = {}) {
-        super(options);
-        Object.defineProperty(this, "options", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: options
-        });
-    }
-    async _transformDocument(document) {
-        const extractedContent = htmlToText(document.pageContent, this.options);
-        return new Document({
-            pageContent: extractedContent,
-            metadata: { ...document.metadata },
-        });
-    }
-}
+export * from "@langchain/community/document_transformers/html_to_text";

package/dist/document_transformers/mozilla_readability.cjs

@@ -1,55 +1,17 @@
 "use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.MozillaReadabilityTransformer = void 0;
-const readability_1 = require("@mozilla/readability");
-const jsdom_1 = require("jsdom");
-const document_js_1 = require("../document.cjs");
-const document_js_2 = require("../schema/document.cjs");
-/**
- * A transformer that uses the Mozilla Readability library to extract the
- * main content from a web page.
- * @example
- * ```typescript
- * const loader = new CheerioWebBaseLoader("https://example.com/article");
- * const docs = await loader.load();
- *
- * const splitter = new RecursiveCharacterTextSplitter({
- *  maxCharacterCount: 5000,
- * });
- * const transformer = new MozillaReadabilityTransformer();
- *
- * // The sequence processes the loaded documents through the splitter and then the transformer.
- * const sequence = splitter.pipe(transformer);
- *
- * // Invoke the sequence to transform the documents into a more readable format.
- * const newDocuments = await sequence.invoke(docs);
- *
- * console.log(newDocuments);
- * ```
- */
-class MozillaReadabilityTransformer extends document_js_2.MappingDocumentTransformer {
-    static lc_name() {
-        return "MozillaReadabilityTransformer";
-    }
-    constructor(options = {}) {
-        super(options);
-        Object.defineProperty(this, "options", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: options
-        });
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
     }
-    async _transformDocument(document) {
-        const doc = new jsdom_1.JSDOM(document.pageContent);
-        const readability = new readability_1.Readability(doc.window.document, this.options);
-        const result = readability.parse();
-        return new document_js_1.Document({
-            pageContent: result?.textContent ?? "",
-            metadata: {
-                ...document.metadata,
-            },
-        });
-    }
-}
-exports.MozillaReadabilityTransformer = MozillaReadabilityTransformer;
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __exportStar = (this && this.__exportStar) || function(m, exports) {
+    for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports, p)) __createBinding(exports, m, p);
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+__exportStar(require("@langchain/community/document_transformers/mozilla_readability"), exports);

package/dist/document_transformers/mozilla_readability.d.ts

@@ -1,31 +1 @@
-import { Options } from "mozilla-readability";
-import { Document } from "../document.js";
-import { MappingDocumentTransformer } from "../schema/document.js";
-/**
- * A transformer that uses the Mozilla Readability library to extract the
- * main content from a web page.
- * @example
- * ```typescript
- * const loader = new CheerioWebBaseLoader("https://example.com/article");
- * const docs = await loader.load();
- *
- * const splitter = new RecursiveCharacterTextSplitter({
- *  maxCharacterCount: 5000,
- * });
- * const transformer = new MozillaReadabilityTransformer();
- *
- * // The sequence processes the loaded documents through the splitter and then the transformer.
- * const sequence = splitter.pipe(transformer);
- *
- * // Invoke the sequence to transform the documents into a more readable format.
- * const newDocuments = await sequence.invoke(docs);
- *
- * console.log(newDocuments);
- * ```
- */
-export declare class MozillaReadabilityTransformer extends MappingDocumentTransformer {
-    protected options: Options;
-    static lc_name(): string;
-    constructor(options?: Options);
-    _transformDocument(document: Document): Promise<Document>;
-}
+export * from "@langchain/community/document_transformers/mozilla_readability";

package/dist/document_transformers/mozilla_readability.js

@@ -1,51 +1 @@
-import { Readability } from "@mozilla/readability";
-import { JSDOM } from "jsdom";
-import { Document } from "../document.js";
-import { MappingDocumentTransformer } from "../schema/document.js";
-/**
- * A transformer that uses the Mozilla Readability library to extract the
- * main content from a web page.
- * @example
- * ```typescript
- * const loader = new CheerioWebBaseLoader("https://example.com/article");
- * const docs = await loader.load();
- *
- * const splitter = new RecursiveCharacterTextSplitter({
- *  maxCharacterCount: 5000,
- * });
- * const transformer = new MozillaReadabilityTransformer();
- *
- * // The sequence processes the loaded documents through the splitter and then the transformer.
- * const sequence = splitter.pipe(transformer);
- *
- * // Invoke the sequence to transform the documents into a more readable format.
- * const newDocuments = await sequence.invoke(docs);
- *
- * console.log(newDocuments);
- * ```
- */
-export class MozillaReadabilityTransformer extends MappingDocumentTransformer {
-    static lc_name() {
-        return "MozillaReadabilityTransformer";
-    }
-    constructor(options = {}) {
-        super(options);
-        Object.defineProperty(this, "options", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: options
-        });
-    }
-    async _transformDocument(document) {
-        const doc = new JSDOM(document.pageContent);
-        const readability = new Readability(doc.window.document, this.options);
-        const result = readability.parse();
-        return new Document({
-            pageContent: result?.textContent ?? "",
-            metadata: {
-                ...document.metadata,
-            },
-        });
-    }
-}
+export * from "@langchain/community/document_transformers/mozilla_readability";

package/dist/embeddings/bedrock.cjs

@@ -1,111 +1,17 @@
 "use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.BedrockEmbeddings = void 0;
-const client_bedrock_runtime_1 = require("@aws-sdk/client-bedrock-runtime");
-const base_js_1 = require("./base.cjs");
-/**
- * Class that extends the Embeddings class and provides methods for
- * generating embeddings using the Bedrock API.
- * @example
- * ```typescript
- * const embeddings = new BedrockEmbeddings({
- *   region: "your-aws-region",
- *   credentials: {
- *     accessKeyId: "your-access-key-id",
- *     secretAccessKey: "your-secret-access-key",
- *   },
- *   model: "amazon.titan-embed-text-v1",
- * });
- *
- * // Embed a query and log the result
- * const res = await embeddings.embedQuery(
- *   "What would be a good company name for a company that makes colorful socks?"
- * );
- * console.log({ res });
- * ```
- */
-class BedrockEmbeddings extends base_js_1.Embeddings {
-    constructor(fields) {
-        super(fields ?? {});
-        Object.defineProperty(this, "model", {
-            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, "batchSize", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: 512
-        });
-        this.model = fields?.model ?? "amazon.titan-embed-text-v1";
-        this.client =
-            fields?.client ??
-                new client_bedrock_runtime_1.BedrockRuntimeClient({
-                    region: fields?.region,
-                    credentials: fields?.credentials,
-                });
-    }
-    /**
-     * Protected method to make a request to the Bedrock API to generate
-     * embeddings. Handles the retry logic and returns the response from the
-     * API.
-     * @param request Request to send to the Bedrock API.
-     * @returns Promise that resolves to the response from the API.
-     */
-    async _embedText(text) {
-        return this.caller.call(async () => {
-            try {
-                // replace newlines, which can negatively affect performance.
-                const cleanedText = text.replace(/\n/g, " ");
-                const res = await this.client.send(new client_bedrock_runtime_1.InvokeModelCommand({
-                    modelId: this.model,
-                    body: JSON.stringify({
-                        inputText: cleanedText,
-                    }),
-                    contentType: "application/json",
-                    accept: "application/json",
-                }));
-                const body = new TextDecoder().decode(res.body);
-                return JSON.parse(body).embedding;
-            }
-            catch (e) {
-                console.error({
-                    error: e,
-                });
-                // eslint-disable-next-line no-instanceof/no-instanceof
-                if (e instanceof Error) {
-                    throw new Error(`An error occurred while embedding documents with Bedrock: ${e.message}`);
-                }
-                throw new Error("An error occurred while embedding documents with Bedrock");
-            }
-        });
-    }
-    /**
-     * 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);
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
     }
-    /**
-     * Method to generate embeddings for an array of texts. Calls _embedText
-     * method which batches and handles retry logic when calling the AWS Bedrock API.
-     * @param documents Array of texts for which to generate embeddings.
-     * @returns Promise that resolves to a 2D array of embeddings for each input document.
-     */
-    async embedDocuments(documents) {
-        return Promise.all(documents.map((document) => this._embedText(document)));
-    }
-}
-exports.BedrockEmbeddings = BedrockEmbeddings;
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __exportStar = (this && this.__exportStar) || function(m, exports) {
+    for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports, p)) __createBinding(exports, m, p);
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+__exportStar(require("@langchain/community/embeddings/bedrock"), exports);

package/dist/embeddings/bedrock.d.ts

@@ -1,71 +1 @@
-import { BedrockRuntimeClient } from "@aws-sdk/client-bedrock-runtime";
-import { Embeddings, EmbeddingsParams } from "./base.js";
-import type { CredentialType } from "../util/bedrock.js";
-/**
- * Interface that extends EmbeddingsParams and defines additional
- * parameters specific to the BedrockEmbeddings class.
- */
-export interface BedrockEmbeddingsParams extends EmbeddingsParams {
-    /**
-     * Model Name to use. Defaults to `amazon.titan-embed-text-v1` if not provided
-     *
-     */
-    model?: string;
-    /**
-     * A client provided by the user that allows them to customze any
-     * SDK configuration options.
-     */
-    client?: BedrockRuntimeClient;
-    region?: string;
-    credentials?: CredentialType;
-}
-/**
- * Class that extends the Embeddings class and provides methods for
- * generating embeddings using the Bedrock API.
- * @example
- * ```typescript
- * const embeddings = new BedrockEmbeddings({
- *   region: "your-aws-region",
- *   credentials: {
- *     accessKeyId: "your-access-key-id",
- *     secretAccessKey: "your-secret-access-key",
- *   },
- *   model: "amazon.titan-embed-text-v1",
- * });
- *
- * // Embed a query and log the result
- * const res = await embeddings.embedQuery(
- *   "What would be a good company name for a company that makes colorful socks?"
- * );
- * console.log({ res });
- * ```
- */
-export declare class BedrockEmbeddings extends Embeddings implements BedrockEmbeddingsParams {
-    model: string;
-    client: BedrockRuntimeClient;
-    batchSize: number;
-    constructor(fields?: BedrockEmbeddingsParams);
-    /**
-     * Protected method to make a request to the Bedrock API to generate
-     * embeddings. Handles the retry logic and returns the response from the
-     * API.
-     * @param request Request to send to the Bedrock API.
-     * @returns Promise that resolves to the response from the API.
-     */
-    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 to generate embeddings for an array of texts. Calls _embedText
-     * method which batches and handles retry logic when calling the AWS Bedrock API.
-     * @param documents Array of texts for which to generate embeddings.
-     * @returns Promise that resolves to a 2D array of embeddings for each input document.
-     */
-    embedDocuments(documents: string[]): Promise<number[][]>;
-}
+export * from "@langchain/community/embeddings/bedrock";