langchain 0.0.203 → 0.0.204-rc.1

package/dist/embeddings/tensorflow.cjs

@@ -10,101 +10,8 @@ var __createBinding = (this && this.__createBinding) || (Object.create ? (functi
     if (k2 === undefined) k2 = k;
     o[k2] = m[k];
 }));
-var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
-    Object.defineProperty(o, "default", { enumerable: true, value: v });
-}) : function(o, v) {
-    o["default"] = v;
-});
-var __importStar = (this && this.__importStar) || function (mod) {
-    if (mod && mod.__esModule) return mod;
-    var result = {};
-    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
-    __setModuleDefault(result, mod);
-    return result;
+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 });
-exports.TensorFlowEmbeddings = void 0;
-const universal_sentence_encoder_1 = require("@tensorflow-models/universal-sentence-encoder");
-const tf = __importStar(require("@tensorflow/tfjs-core"));
-const base_js_1 = require("./base.cjs");
-/**
- * Class that extends the Embeddings class and provides methods for
- * generating embeddings using the Universal Sentence Encoder model from
- * TensorFlow.js.
- * @example
- * ```typescript
- * const embeddings = new TensorFlowEmbeddings();
- * const store = new MemoryVectorStore(embeddings);
- *
- * const documents = [
- *   "A document",
- *   "Some other piece of text",
- *   "One more",
- *   "And another",
- * ];
- *
- * await store.addDocuments(
- *   documents.map((pageContent) => new Document({ pageContent }))
- * );
- * ```
- */
-class TensorFlowEmbeddings extends base_js_1.Embeddings {
-    constructor(fields) {
-        super(fields ?? {});
-        Object.defineProperty(this, "_cached", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        try {
-            tf.backend();
-        }
-        catch (e) {
-            throw new Error("No TensorFlow backend found, see instructions at ...");
-        }
-    }
-    /**
-     * Private method that loads the Universal Sentence Encoder model if it
-     * hasn't been loaded already. It returns a promise that resolves to the
-     * loaded model.
-     * @returns Promise that resolves to the loaded Universal Sentence Encoder model.
-     */
-    async load() {
-        if (this._cached === undefined) {
-            this._cached = (0, universal_sentence_encoder_1.load)();
-        }
-        return this._cached;
-    }
-    _embed(texts) {
-        return this.caller.call(async () => {
-            const model = await this.load();
-            return model.embed(texts);
-        });
-    }
-    /**
-     * 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 processes the result to return a
-     * single embedding.
-     * @param document Document to generate an embedding for.
-     * @returns Promise that resolves to an embedding for the input document.
-     */
-    embedQuery(document) {
-        return this._embed([document])
-            .then((embeddings) => embeddings.array())
-            .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 and processes the
-     * result to return the embeddings.
-     * @param documents Array of documents to generate embeddings for.
-     * @returns Promise that resolves to a 2D array of embeddings for each input document.
-     */
-    embedDocuments(documents) {
-        return this._embed(documents).then((embeddings) => embeddings.array());
-    }
-}
-exports.TensorFlowEmbeddings = TensorFlowEmbeddings;
+__exportStar(require("@langchain/community/embeddings/tensorflow"), exports);

package/dist/embeddings/tensorflow.d.ts

@@ -1,59 +1 @@
-import { load } from "@tensorflow-models/universal-sentence-encoder";
-import { Embeddings, EmbeddingsParams } from "./base.js";
-/**
- * Interface that extends EmbeddingsParams and defines additional
- * parameters specific to the TensorFlowEmbeddings class.
- */
-export interface TensorFlowEmbeddingsParams extends EmbeddingsParams {
-}
-/**
- * Class that extends the Embeddings class and provides methods for
- * generating embeddings using the Universal Sentence Encoder model from
- * TensorFlow.js.
- * @example
- * ```typescript
- * const embeddings = new TensorFlowEmbeddings();
- * const store = new MemoryVectorStore(embeddings);
- *
- * const documents = [
- *   "A document",
- *   "Some other piece of text",
- *   "One more",
- *   "And another",
- * ];
- *
- * await store.addDocuments(
- *   documents.map((pageContent) => new Document({ pageContent }))
- * );
- * ```
- */
-export declare class TensorFlowEmbeddings extends Embeddings {
-    constructor(fields?: TensorFlowEmbeddingsParams);
-    _cached: ReturnType<typeof load>;
-    /**
-     * Private method that loads the Universal Sentence Encoder model if it
-     * hasn't been loaded already. It returns a promise that resolves to the
-     * loaded model.
-     * @returns Promise that resolves to the loaded Universal Sentence Encoder model.
-     */
-    private load;
-    private _embed;
-    /**
-     * 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 processes the result to return a
-     * single embedding.
-     * @param document Document to generate an embedding for.
-     * @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 _embed method with the documents as the input and processes the
-     * result to return the embeddings.
-     * @param documents Array of documents to generate embeddings for.
-     * @returns Promise that resolves to a 2D array of embeddings for each input document.
-     */
-    embedDocuments(documents: string[]): Promise<number[][]>;
-}
+export * from "@langchain/community/embeddings/tensorflow";

package/dist/embeddings/tensorflow.js

@@ -1,83 +1 @@
-import { load } from "@tensorflow-models/universal-sentence-encoder";
-import * as tf from "@tensorflow/tfjs-core";
-import { Embeddings } from "./base.js";
-/**
- * Class that extends the Embeddings class and provides methods for
- * generating embeddings using the Universal Sentence Encoder model from
- * TensorFlow.js.
- * @example
- * ```typescript
- * const embeddings = new TensorFlowEmbeddings();
- * const store = new MemoryVectorStore(embeddings);
- *
- * const documents = [
- *   "A document",
- *   "Some other piece of text",
- *   "One more",
- *   "And another",
- * ];
- *
- * await store.addDocuments(
- *   documents.map((pageContent) => new Document({ pageContent }))
- * );
- * ```
- */
-export class TensorFlowEmbeddings extends Embeddings {
-    constructor(fields) {
-        super(fields ?? {});
-        Object.defineProperty(this, "_cached", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        try {
-            tf.backend();
-        }
-        catch (e) {
-            throw new Error("No TensorFlow backend found, see instructions at ...");
-        }
-    }
-    /**
-     * Private method that loads the Universal Sentence Encoder model if it
-     * hasn't been loaded already. It returns a promise that resolves to the
-     * loaded model.
-     * @returns Promise that resolves to the loaded Universal Sentence Encoder model.
-     */
-    async load() {
-        if (this._cached === undefined) {
-            this._cached = load();
-        }
-        return this._cached;
-    }
-    _embed(texts) {
-        return this.caller.call(async () => {
-            const model = await this.load();
-            return model.embed(texts);
-        });
-    }
-    /**
-     * 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 processes the result to return a
-     * single embedding.
-     * @param document Document to generate an embedding for.
-     * @returns Promise that resolves to an embedding for the input document.
-     */
-    embedQuery(document) {
-        return this._embed([document])
-            .then((embeddings) => embeddings.array())
-            .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 and processes the
-     * result to return the embeddings.
-     * @param documents Array of documents to generate embeddings for.
-     * @returns Promise that resolves to a 2D array of embeddings for each input document.
-     */
-    embedDocuments(documents) {
-        return this._embed(documents).then((embeddings) => embeddings.array());
-    }
-}
+export * from "@langchain/community/embeddings/tensorflow";

package/dist/embeddings/voyage.cjs

@@ -1,120 +1,17 @@
 "use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.VoyageEmbeddings = void 0;
-const chunk_js_1 = require("../util/chunk.cjs");
-const env_js_1 = require("../util/env.cjs");
-const base_js_1 = require("./base.cjs");
-/**
- * A class for generating embeddings using the Voyage AI API.
- */
-class VoyageEmbeddings extends base_js_1.Embeddings {
-    /**
-     * Constructor for the VoyageEmbeddings class.
-     * @param fields - An optional object with properties to configure the instance.
-     */
-    constructor(fields) {
-        const fieldsWithDefaults = { ...fields };
-        super(fieldsWithDefaults);
-        Object.defineProperty(this, "modelName", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: "voyage-01"
-        });
-        Object.defineProperty(this, "batchSize", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: 8
-        });
-        Object.defineProperty(this, "apiKey", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "basePath", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: "https://api.voyageai.com/v1"
-        });
-        Object.defineProperty(this, "apiUrl", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "headers", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        const apiKey = fieldsWithDefaults?.apiKey || (0, env_js_1.getEnvironmentVariable)("VOYAGEAI_API_KEY");
-        if (!apiKey) {
-            throw new Error("Voyage AI API key not found");
-        }
-        this.modelName = fieldsWithDefaults?.modelName ?? this.modelName;
-        this.batchSize = fieldsWithDefaults?.batchSize ?? this.batchSize;
-        this.apiKey = apiKey;
-        this.apiUrl = `${this.basePath}/embeddings`;
-    }
-    /**
-     * Generates embeddings for an array of texts.
-     * @param texts - An array of strings to generate embeddings for.
-     * @returns A Promise that resolves to an array of embeddings.
-     */
-    async embedDocuments(texts) {
-        const batches = (0, chunk_js_1.chunkArray)(texts, this.batchSize);
-        const batchRequests = batches.map((batch) => this.embeddingWithRetry({
-            model: this.modelName,
-            input: batch,
-        }));
-        const batchResponses = await Promise.all(batchRequests);
-        const embeddings = [];
-        for (let i = 0; i < batchResponses.length; i += 1) {
-            const batch = batches[i];
-            const { data: batchResponse } = batchResponses[i];
-            for (let j = 0; j < batch.length; j += 1) {
-                embeddings.push(batchResponse[j].embedding);
-            }
-        }
-        return embeddings;
-    }
-    /**
-     * Generates an embedding for a single text.
-     * @param text - A string to generate an embedding for.
-     * @returns A Promise that resolves to an array of numbers representing the embedding.
-     */
-    async embedQuery(text) {
-        const { data } = await this.embeddingWithRetry({
-            model: this.modelName,
-            input: text,
-        });
-        return data[0].embedding;
+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]; } };
     }
-    /**
-     * Makes a request to the Voyage AI API to generate embeddings for an array of texts.
-     * @param request - An object with properties to configure the request.
-     * @returns A Promise that resolves to the response from the Voyage AI API.
-     */
-    async embeddingWithRetry(request) {
-        const makeCompletionRequest = async () => {
-            const url = `${this.apiUrl}`;
-            const response = await fetch(url, {
-                method: "POST",
-                headers: {
-                    "Content-Type": "application/json",
-                    Authorization: `Bearer ${this.apiKey}`,
-                    ...this.headers,
-                },
-                body: JSON.stringify(request),
-            });
-            const json = await response.json();
-            return json;
-        };
-        return this.caller.call(makeCompletionRequest);
-    }
-}
-exports.VoyageEmbeddings = VoyageEmbeddings;
+    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/voyage"), exports);

package/dist/embeddings/voyage.d.ts

@@ -1,66 +1 @@
-import { Embeddings, EmbeddingsParams } from "./base.js";
-/**
- * Interface that extends EmbeddingsParams and defines additional
- * parameters specific to the VoyageEmbeddings class.
- */
-export interface VoyageEmbeddingsParams extends EmbeddingsParams {
-    modelName: string;
-    /**
-     * The maximum number of documents to embed in a single request. This is
-     * limited by the Voyage AI API to a maximum of 8.
-     */
-    batchSize?: number;
-}
-/**
- * Interface for the request body to generate embeddings.
- */
-export interface CreateVoyageEmbeddingRequest {
-    /**
-     * @type {string}
-     * @memberof CreateVoyageEmbeddingRequest
-     */
-    model: string;
-    /**
-     *  Text to generate vector expectation
-     * @type {CreateEmbeddingRequestInput}
-     * @memberof CreateVoyageEmbeddingRequest
-     */
-    input: string | string[];
-}
-/**
- * A class for generating embeddings using the Voyage AI API.
- */
-export declare class VoyageEmbeddings extends Embeddings implements VoyageEmbeddingsParams {
-    modelName: string;
-    batchSize: number;
-    private apiKey;
-    basePath?: string;
-    apiUrl: string;
-    headers?: Record<string, string>;
-    /**
-     * Constructor for the VoyageEmbeddings class.
-     * @param fields - An optional object with properties to configure the instance.
-     */
-    constructor(fields?: Partial<VoyageEmbeddingsParams> & {
-        verbose?: boolean;
-        apiKey?: string;
-    });
-    /**
-     * Generates embeddings for an array of texts.
-     * @param texts - An array of strings to generate embeddings for.
-     * @returns A Promise that resolves to an array of embeddings.
-     */
-    embedDocuments(texts: string[]): Promise<number[][]>;
-    /**
-     * Generates an embedding for a single text.
-     * @param text - A string to generate an embedding for.
-     * @returns A Promise that resolves to an array of numbers representing the embedding.
-     */
-    embedQuery(text: string): Promise<number[]>;
-    /**
-     * Makes a request to the Voyage AI API to generate embeddings for an array of texts.
-     * @param request - An object with properties to configure the request.
-     * @returns A Promise that resolves to the response from the Voyage AI API.
-     */
-    private embeddingWithRetry;
-}
+export * from "@langchain/community/embeddings/voyage";

package/dist/embeddings/voyage.js

@@ -1,116 +1 @@
-import { chunkArray } from "../util/chunk.js";
-import { getEnvironmentVariable } from "../util/env.js";
-import { Embeddings } from "./base.js";
-/**
- * A class for generating embeddings using the Voyage AI API.
- */
-export class VoyageEmbeddings extends Embeddings {
-    /**
-     * Constructor for the VoyageEmbeddings class.
-     * @param fields - An optional object with properties to configure the instance.
-     */
-    constructor(fields) {
-        const fieldsWithDefaults = { ...fields };
-        super(fieldsWithDefaults);
-        Object.defineProperty(this, "modelName", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: "voyage-01"
-        });
-        Object.defineProperty(this, "batchSize", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: 8
-        });
-        Object.defineProperty(this, "apiKey", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "basePath", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: "https://api.voyageai.com/v1"
-        });
-        Object.defineProperty(this, "apiUrl", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "headers", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        const apiKey = fieldsWithDefaults?.apiKey || getEnvironmentVariable("VOYAGEAI_API_KEY");
-        if (!apiKey) {
-            throw new Error("Voyage AI API key not found");
-        }
-        this.modelName = fieldsWithDefaults?.modelName ?? this.modelName;
-        this.batchSize = fieldsWithDefaults?.batchSize ?? this.batchSize;
-        this.apiKey = apiKey;
-        this.apiUrl = `${this.basePath}/embeddings`;
-    }
-    /**
-     * Generates embeddings for an array of texts.
-     * @param texts - An array of strings to generate embeddings for.
-     * @returns A Promise that resolves to an array of embeddings.
-     */
-    async embedDocuments(texts) {
-        const batches = chunkArray(texts, this.batchSize);
-        const batchRequests = batches.map((batch) => this.embeddingWithRetry({
-            model: this.modelName,
-            input: batch,
-        }));
-        const batchResponses = await Promise.all(batchRequests);
-        const embeddings = [];
-        for (let i = 0; i < batchResponses.length; i += 1) {
-            const batch = batches[i];
-            const { data: batchResponse } = batchResponses[i];
-            for (let j = 0; j < batch.length; j += 1) {
-                embeddings.push(batchResponse[j].embedding);
-            }
-        }
-        return embeddings;
-    }
-    /**
-     * Generates an embedding for a single text.
-     * @param text - A string to generate an embedding for.
-     * @returns A Promise that resolves to an array of numbers representing the embedding.
-     */
-    async embedQuery(text) {
-        const { data } = await this.embeddingWithRetry({
-            model: this.modelName,
-            input: text,
-        });
-        return data[0].embedding;
-    }
-    /**
-     * Makes a request to the Voyage AI API to generate embeddings for an array of texts.
-     * @param request - An object with properties to configure the request.
-     * @returns A Promise that resolves to the response from the Voyage AI API.
-     */
-    async embeddingWithRetry(request) {
-        const makeCompletionRequest = async () => {
-            const url = `${this.apiUrl}`;
-            const response = await fetch(url, {
-                method: "POST",
-                headers: {
-                    "Content-Type": "application/json",
-                    Authorization: `Bearer ${this.apiKey}`,
-                    ...this.headers,
-                },
-                body: JSON.stringify(request),
-            });
-            const json = await response.json();
-            return json;
-        };
-        return this.caller.call(makeCompletionRequest);
-    }
-}
+export * from "@langchain/community/embeddings/voyage";

package/dist/experimental/chat_models/ollama_functions.d.ts

@@ -32,7 +32,7 @@ export declare class OllamaFunctions extends BaseChatModel<ChatOllamaFunctionsCa
     constructor(fields?: OllamaFunctionsInput);
     invocationParams(): {
         model: string;
-        format: import("../../util/types.js").StringWithAutocomplete<"json"> | undefined;
+        format: import("@langchain/core/utils/types").StringWithAutocomplete<"json"> | undefined;
         options: {
             embedding_only: boolean | undefined;
             f16_kv: boolean | undefined;

package/dist/experimental/openai_assistant/index.cjs

@@ -1,7 +1,7 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.OpenAIAssistantRunnable = void 0;
-const openai_1 = require("openai");
+const openai_1 = require("@langchain/openai");
 const base_js_1 = require("../../schema/runnable/base.cjs");
 const time_js_1 = require("../../util/time.cjs");
 const base_js_2 = require("../../tools/base.cjs");
@@ -39,7 +39,7 @@ class OpenAIAssistantRunnable extends base_js_1.Runnable {
             writable: true,
             value: void 0
         });
-        this.client = fields.client ?? new openai_1.OpenAI(fields?.clientOptions);
+        this.client = fields.client ?? new openai_1.OpenAIClient(fields?.clientOptions);
         this.assistantId = fields.assistantId;
         this.asAgent = fields.asAgent ?? this.asAgent;
     }
@@ -51,7 +51,7 @@ class OpenAIAssistantRunnable extends base_js_1.Runnable {
             }
             return tool;
         }) ?? [];
-        const oaiClient = client ?? new openai_1.OpenAI(clientOptions);
+        const oaiClient = client ?? new openai_1.OpenAIClient(clientOptions);
         const assistant = await oaiClient.beta.assistants.create({
             name,
             instructions,

package/dist/experimental/openai_assistant/index.d.ts

@@ -1,4 +1,4 @@
-import { type ClientOptions, OpenAI as OpenAIClient } from "openai";
+import { type ClientOptions, OpenAIClient } from "@langchain/openai";
 import { Runnable } from "../../schema/runnable/base.js";
 import type { RunnableConfig } from "../../schema/runnable/config.js";
 import type { OpenAIAssistantFinish, OpenAIAssistantAction, OpenAIToolType } from "./schema.js";

package/dist/experimental/openai_assistant/index.js

@@ -1,4 +1,4 @@
-import { OpenAI as OpenAIClient } from "openai";
+import { OpenAIClient } from "@langchain/openai";
 import { Runnable } from "../../schema/runnable/base.js";
 import { sleep } from "../../util/time.js";
 import { StructuredTool } from "../../tools/base.js";

package/dist/experimental/openai_assistant/schema.d.ts

@@ -1,4 +1,4 @@
-import type { OpenAI as OpenAIClient } from "openai";
+import type { OpenAIClient } from "@langchain/openai";
 import type { AgentFinish, AgentAction } from "../../schema/index.js";
 export type OpenAIAssistantFinish = AgentFinish & {
     runId: string;

package/dist/experimental/openai_files/index.cjs

@@ -1,7 +1,7 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.OpenAIFiles = void 0;
-const openai_1 = require("openai");
+const openai_1 = require("@langchain/openai");
 const serializable_js_1 = require("../../load/serializable.cjs");
 class OpenAIFiles extends serializable_js_1.Serializable {
     constructor(fields) {
@@ -18,7 +18,7 @@ class OpenAIFiles extends serializable_js_1.Serializable {
             writable: true,
             value: void 0
         });
-        this.oaiClient = fields?.client ?? new openai_1.OpenAI(fields?.clientOptions);
+        this.oaiClient = fields?.client ?? new openai_1.OpenAIClient(fields?.clientOptions);
     }
     /**
      * Upload file

package/dist/experimental/openai_files/index.d.ts

@@ -1,4 +1,4 @@
-import { OpenAI as OpenAIClient, type ClientOptions } from "openai";
+import { OpenAIClient, type ClientOptions } from "@langchain/openai";
 import { Serializable } from "../../load/serializable.js";
 export type OpenAIFilesInput = {
     client?: OpenAIClient;

package/dist/experimental/openai_files/index.js

@@ -1,4 +1,4 @@
-import { OpenAI as OpenAIClient } from "openai";
+import { OpenAIClient } from "@langchain/openai";
 import { Serializable } from "../../load/serializable.js";
 export class OpenAIFiles extends Serializable {
     constructor(fields) {