langchain 0.0.155 → 0.0.156

package/dist/util/bedrock.d.ts

@@ -0,0 +1,59 @@
+import type { AwsCredentialIdentity, Provider } from "@aws-sdk/types";
+export type CredentialType = AwsCredentialIdentity | Provider<AwsCredentialIdentity>;
+/** Bedrock models.
+    To authenticate, the AWS client uses the following methods to automatically load credentials:
+    https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html
+    If a specific credential profile should be used, you must pass the name of the profile from the ~/.aws/credentials file that is to be used.
+    Make sure the credentials / roles used have the required policies to access the Bedrock service.
+*/
+export interface BaseBedrockInput {
+    /** Model to use.
+        For example, "amazon.titan-tg1-large", this is equivalent to the modelId property in the list-foundation-models api.
+    */
+    model: string;
+    /** The AWS region e.g. `us-west-2`.
+        Fallback to AWS_DEFAULT_REGION env variable or region specified in ~/.aws/config in case it is not provided here.
+    */
+    region?: string;
+    /** AWS Credentials.
+        If no credentials are provided, the default credentials from `@aws-sdk/credential-provider-node` will be used.
+     */
+    credentials?: CredentialType;
+    /** Temperature. */
+    temperature?: number;
+    /** Max tokens. */
+    maxTokens?: number;
+    /** A custom fetch function for low-level access to AWS API. Defaults to fetch(). */
+    fetchFn?: typeof fetch;
+    /** @deprecated Use endpointHost instead Override the default endpoint url. */
+    endpointUrl?: string;
+    /** Override the default endpoint hostname. */
+    endpointHost?: string;
+    /** Optional additional stop sequences to pass to the model. Currently only supported for Anthropic and AI21. */
+    stopSequences?: string[];
+    /** Additional kwargs to pass to the model. */
+    modelKwargs?: Record<string, unknown>;
+}
+type Dict = {
+    [key: string]: unknown;
+};
+/**
+ * A helper class used within the `Bedrock` class. It is responsible for
+ * preparing the input and output for the Bedrock service. It formats the
+ * input prompt based on the provider (e.g., "anthropic", "ai21",
+ * "amazon") and extracts the generated text from the service response.
+ */
+export declare class BedrockLLMInputOutputAdapter {
+    /** Adapter class to prepare the inputs from Langchain to a format
+    that LLM model expects. Also, provides a helper function to extract
+    the generated text from the model response. */
+    static prepareInput(provider: string, prompt: string, maxTokens?: number, temperature?: number, stopSequences?: string[] | undefined, modelKwargs?: Record<string, unknown>): Dict;
+    /**
+     * Extracts the generated text from the service response.
+     * @param provider The provider name.
+     * @param responseBody The response body from the service.
+     * @returns The generated text.
+     */
+    static prepareOutput(provider: string, responseBody: any): string;
+}
+export {};

package/dist/util/bedrock.js

@@ -0,0 +1,50 @@
+/**
+ * A helper class used within the `Bedrock` class. It is responsible for
+ * preparing the input and output for the Bedrock service. It formats the
+ * input prompt based on the provider (e.g., "anthropic", "ai21",
+ * "amazon") and extracts the generated text from the service response.
+ */
+export class BedrockLLMInputOutputAdapter {
+    /** Adapter class to prepare the inputs from Langchain to a format
+    that LLM model expects. Also, provides a helper function to extract
+    the generated text from the model response. */
+    static prepareInput(provider, prompt, maxTokens = 50, temperature = 0, stopSequences = undefined, modelKwargs = {}) {
+        const inputBody = {};
+        if (provider === "anthropic") {
+            inputBody.prompt = prompt;
+            inputBody.max_tokens_to_sample = maxTokens;
+            inputBody.temperature = temperature;
+            inputBody.stop_sequences = stopSequences;
+        }
+        else if (provider === "ai21") {
+            inputBody.prompt = prompt;
+            inputBody.maxTokens = maxTokens;
+            inputBody.temperature = temperature;
+            inputBody.stopSequences = stopSequences;
+        }
+        else if (provider === "amazon") {
+            inputBody.inputText = prompt;
+            inputBody.textGenerationConfig = {
+                maxTokenCount: maxTokens,
+                temperature,
+            };
+        }
+        return { ...inputBody, ...modelKwargs };
+    }
+    /**
+     * Extracts the generated text from the service response.
+     * @param provider The provider name.
+     * @param responseBody The response body from the service.
+     * @returns The generated text.
+     */
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    static prepareOutput(provider, responseBody) {
+        if (provider === "anthropic") {
+            return responseBody.completion;
+        }
+        else if (provider === "ai21") {
+            return responseBody?.completions?.[0]?.data?.text ?? "";
+        }
+        return responseBody.outputText;
+    }
+}

package/dist/vectorstores/cloudflare_vectorize.cjs

@@ -0,0 +1,200 @@
+"use strict";
+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]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    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;
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.CloudflareVectorizeStore = void 0;
+const uuid = __importStar(require("uuid"));
+const base_js_1 = require("./base.cjs");
+const document_js_1 = require("../document.cjs");
+const chunk_js_1 = require("../util/chunk.cjs");
+const async_caller_js_1 = require("../util/async_caller.cjs");
+/**
+ * Class that extends the VectorStore class and provides methods to
+ * interact with the Cloudflare Vectorize vector database.
+ */
+class CloudflareVectorizeStore extends base_js_1.VectorStore {
+    _vectorstoreType() {
+        return "cloudflare_vectorize";
+    }
+    constructor(embeddings, args) {
+        super(embeddings, args);
+        Object.defineProperty(this, "textKey", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: void 0
+        });
+        Object.defineProperty(this, "namespace", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: void 0
+        });
+        Object.defineProperty(this, "index", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: void 0
+        });
+        Object.defineProperty(this, "caller", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: void 0
+        });
+        this.embeddings = embeddings;
+        const { index, textKey, ...asyncCallerArgs } = args;
+        if (!index) {
+            throw new Error("Must supply a Vectorize index binding, eg { index: env.VECTORIZE }");
+        }
+        this.index = index;
+        this.textKey = textKey ?? "text";
+        this.caller = new async_caller_js_1.AsyncCaller({
+            maxConcurrency: 6,
+            maxRetries: 0,
+            ...asyncCallerArgs,
+        });
+    }
+    /**
+     * Method that adds documents to the Vectorize database.
+     * @param documents Array of documents to add.
+     * @param options Optional ids for the documents.
+     * @returns Promise that resolves with the ids of the added documents.
+     */
+    async addDocuments(documents, options) {
+        const texts = documents.map(({ pageContent }) => pageContent);
+        return this.addVectors(await this.embeddings.embedDocuments(texts), documents, options);
+    }
+    /**
+     * Method that adds vectors to the Vectorize database.
+     * @param vectors Array of vectors to add.
+     * @param documents Array of documents associated with the vectors.
+     * @param options Optional ids for the vectors.
+     * @returns Promise that resolves with the ids of the added vectors.
+     */
+    async addVectors(vectors, documents, options) {
+        const ids = Array.isArray(options) ? options : options?.ids;
+        const documentIds = ids == null ? documents.map(() => uuid.v4()) : ids;
+        const vectorizeVectors = vectors.map((values, idx) => {
+            const metadata = {
+                ...documents[idx].metadata,
+                [this.textKey]: documents[idx].pageContent,
+            };
+            return {
+                id: documentIds[idx],
+                metadata,
+                values,
+            };
+        });
+        // Stick to a limit of 500 vectors per upsert request
+        const chunkSize = 500;
+        const chunkedVectors = (0, chunk_js_1.chunkArray)(vectorizeVectors, chunkSize);
+        const batchRequests = chunkedVectors.map((chunk) => this.caller.call(async () => this.index.upsert(chunk)));
+        await Promise.all(batchRequests);
+        return documentIds;
+    }
+    /**
+     * Method that deletes vectors from the Vectorize database.
+     * @param params Parameters for the delete operation.
+     * @returns Promise that resolves when the delete operation is complete.
+     */
+    async delete(params) {
+        const batchSize = 1000;
+        const batchedIds = (0, chunk_js_1.chunkArray)(params.ids, batchSize);
+        const batchRequests = batchedIds.map((batchIds) => this.caller.call(async () => this.index.deleteByIds(batchIds)));
+        await Promise.all(batchRequests);
+    }
+    /**
+     * Method that performs a similarity search in the Vectorize database and
+     * returns the results along with their scores.
+     * @param query Query vector for the similarity search.
+     * @param k Number of top results to return.
+     * @returns Promise that resolves with an array of documents and their scores.
+     */
+    async similaritySearchVectorWithScore(query, k) {
+        const results = await this.index.query(query, {
+            returnVectors: true,
+            topK: k,
+        });
+        const result = [];
+        if (results.matches) {
+            for (const res of results.matches) {
+                const { [this.textKey]: pageContent, ...metadata } = res.vector?.metadata ?? {};
+                result.push([
+                    new document_js_1.Document({ metadata, pageContent: pageContent }),
+                    res.score,
+                ]);
+            }
+        }
+        return result;
+    }
+    /**
+     * Static method that creates a new instance of the CloudflareVectorizeStore class
+     * from texts.
+     * @param texts Array of texts to add to the Vectorize database.
+     * @param metadatas Metadata associated with the texts.
+     * @param embeddings Embeddings to use for the texts.
+     * @param dbConfig Configuration for the Vectorize database.
+     * @param options Optional ids for the vectors.
+     * @returns Promise that resolves with a new instance of the CloudflareVectorizeStore class.
+     */
+    static async fromTexts(texts, metadatas, embeddings, dbConfig) {
+        const docs = [];
+        for (let i = 0; i < texts.length; i += 1) {
+            const metadata = Array.isArray(metadatas) ? metadatas[i] : metadatas;
+            const newDoc = new document_js_1.Document({
+                pageContent: texts[i],
+                metadata,
+            });
+            docs.push(newDoc);
+        }
+        return CloudflareVectorizeStore.fromDocuments(docs, embeddings, dbConfig);
+    }
+    /**
+     * Static method that creates a new instance of the CloudflareVectorizeStore class
+     * from documents.
+     * @param docs Array of documents to add to the Vectorize database.
+     * @param embeddings Embeddings to use for the documents.
+     * @param dbConfig Configuration for the Vectorize database.
+     * @param options Optional ids for the vectors.
+     * @returns Promise that resolves with a new instance of the CloudflareVectorizeStore class.
+     */
+    static async fromDocuments(docs, embeddings, dbConfig) {
+        const instance = new this(embeddings, dbConfig);
+        await instance.addDocuments(docs);
+        return instance;
+    }
+    /**
+     * Static method that creates a new instance of the CloudflareVectorizeStore class
+     * from an existing index.
+     * @param embeddings Embeddings to use for the documents.
+     * @param dbConfig Configuration for the Vectorize database.
+     * @returns Promise that resolves with a new instance of the CloudflareVectorizeStore class.
+     */
+    static async fromExistingIndex(embeddings, dbConfig) {
+        const instance = new this(embeddings, dbConfig);
+        return instance;
+    }
+}
+exports.CloudflareVectorizeStore = CloudflareVectorizeStore;

package/dist/vectorstores/cloudflare_vectorize.d.ts

@@ -0,0 +1,90 @@
+import { VectorizeIndex, VectorizeVectorMetadata } from "@cloudflare/workers-types";
+import { VectorStore } from "./base.js";
+import { Embeddings } from "../embeddings/base.js";
+import { Document } from "../document.js";
+import { AsyncCaller, type AsyncCallerParams } from "../util/async_caller.js";
+export interface VectorizeLibArgs extends AsyncCallerParams {
+    index: VectorizeIndex;
+    textKey?: string;
+}
+/**
+ * Type that defines the parameters for the delete operation in the
+ * CloudflareVectorizeStore class. It includes ids, deleteAll flag, and namespace.
+ */
+export type VectorizeDeleteParams = {
+    ids: string[];
+};
+/**
+ * Class that extends the VectorStore class and provides methods to
+ * interact with the Cloudflare Vectorize vector database.
+ */
+export declare class CloudflareVectorizeStore extends VectorStore {
+    textKey: string;
+    namespace?: string;
+    index: VectorizeIndex;
+    caller: AsyncCaller;
+    _vectorstoreType(): string;
+    constructor(embeddings: Embeddings, args: VectorizeLibArgs);
+    /**
+     * Method that adds documents to the Vectorize database.
+     * @param documents Array of documents to add.
+     * @param options Optional ids for the documents.
+     * @returns Promise that resolves with the ids of the added documents.
+     */
+    addDocuments(documents: Document[], options?: {
+        ids?: string[];
+    } | string[]): Promise<string[]>;
+    /**
+     * Method that adds vectors to the Vectorize database.
+     * @param vectors Array of vectors to add.
+     * @param documents Array of documents associated with the vectors.
+     * @param options Optional ids for the vectors.
+     * @returns Promise that resolves with the ids of the added vectors.
+     */
+    addVectors(vectors: number[][], documents: Document[], options?: {
+        ids?: string[];
+    } | string[]): Promise<string[]>;
+    /**
+     * Method that deletes vectors from the Vectorize database.
+     * @param params Parameters for the delete operation.
+     * @returns Promise that resolves when the delete operation is complete.
+     */
+    delete(params: VectorizeDeleteParams): Promise<void>;
+    /**
+     * Method that performs a similarity search in the Vectorize database and
+     * returns the results along with their scores.
+     * @param query Query vector for the similarity search.
+     * @param k Number of top results to return.
+     * @returns Promise that resolves with an array of documents and their scores.
+     */
+    similaritySearchVectorWithScore(query: number[], k: number): Promise<[Document, number][]>;
+    /**
+     * Static method that creates a new instance of the CloudflareVectorizeStore class
+     * from texts.
+     * @param texts Array of texts to add to the Vectorize database.
+     * @param metadatas Metadata associated with the texts.
+     * @param embeddings Embeddings to use for the texts.
+     * @param dbConfig Configuration for the Vectorize database.
+     * @param options Optional ids for the vectors.
+     * @returns Promise that resolves with a new instance of the CloudflareVectorizeStore class.
+     */
+    static fromTexts(texts: string[], metadatas: Record<string, VectorizeVectorMetadata>[] | Record<string, VectorizeVectorMetadata>, embeddings: Embeddings, dbConfig: VectorizeLibArgs): Promise<CloudflareVectorizeStore>;
+    /**
+     * Static method that creates a new instance of the CloudflareVectorizeStore class
+     * from documents.
+     * @param docs Array of documents to add to the Vectorize database.
+     * @param embeddings Embeddings to use for the documents.
+     * @param dbConfig Configuration for the Vectorize database.
+     * @param options Optional ids for the vectors.
+     * @returns Promise that resolves with a new instance of the CloudflareVectorizeStore class.
+     */
+    static fromDocuments(docs: Document[], embeddings: Embeddings, dbConfig: VectorizeLibArgs): Promise<CloudflareVectorizeStore>;
+    /**
+     * Static method that creates a new instance of the CloudflareVectorizeStore class
+     * from an existing index.
+     * @param embeddings Embeddings to use for the documents.
+     * @param dbConfig Configuration for the Vectorize database.
+     * @returns Promise that resolves with a new instance of the CloudflareVectorizeStore class.
+     */
+    static fromExistingIndex(embeddings: Embeddings, dbConfig: VectorizeLibArgs): Promise<CloudflareVectorizeStore>;
+}

package/dist/vectorstores/cloudflare_vectorize.js

@@ -0,0 +1,173 @@
+import * as uuid from "uuid";
+import { VectorStore } from "./base.js";
+import { Document } from "../document.js";
+import { chunkArray } from "../util/chunk.js";
+import { AsyncCaller } from "../util/async_caller.js";
+/**
+ * Class that extends the VectorStore class and provides methods to
+ * interact with the Cloudflare Vectorize vector database.
+ */
+export class CloudflareVectorizeStore extends VectorStore {
+    _vectorstoreType() {
+        return "cloudflare_vectorize";
+    }
+    constructor(embeddings, args) {
+        super(embeddings, args);
+        Object.defineProperty(this, "textKey", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: void 0
+        });
+        Object.defineProperty(this, "namespace", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: void 0
+        });
+        Object.defineProperty(this, "index", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: void 0
+        });
+        Object.defineProperty(this, "caller", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: void 0
+        });
+        this.embeddings = embeddings;
+        const { index, textKey, ...asyncCallerArgs } = args;
+        if (!index) {
+            throw new Error("Must supply a Vectorize index binding, eg { index: env.VECTORIZE }");
+        }
+        this.index = index;
+        this.textKey = textKey ?? "text";
+        this.caller = new AsyncCaller({
+            maxConcurrency: 6,
+            maxRetries: 0,
+            ...asyncCallerArgs,
+        });
+    }
+    /**
+     * Method that adds documents to the Vectorize database.
+     * @param documents Array of documents to add.
+     * @param options Optional ids for the documents.
+     * @returns Promise that resolves with the ids of the added documents.
+     */
+    async addDocuments(documents, options) {
+        const texts = documents.map(({ pageContent }) => pageContent);
+        return this.addVectors(await this.embeddings.embedDocuments(texts), documents, options);
+    }
+    /**
+     * Method that adds vectors to the Vectorize database.
+     * @param vectors Array of vectors to add.
+     * @param documents Array of documents associated with the vectors.
+     * @param options Optional ids for the vectors.
+     * @returns Promise that resolves with the ids of the added vectors.
+     */
+    async addVectors(vectors, documents, options) {
+        const ids = Array.isArray(options) ? options : options?.ids;
+        const documentIds = ids == null ? documents.map(() => uuid.v4()) : ids;
+        const vectorizeVectors = vectors.map((values, idx) => {
+            const metadata = {
+                ...documents[idx].metadata,
+                [this.textKey]: documents[idx].pageContent,
+            };
+            return {
+                id: documentIds[idx],
+                metadata,
+                values,
+            };
+        });
+        // Stick to a limit of 500 vectors per upsert request
+        const chunkSize = 500;
+        const chunkedVectors = chunkArray(vectorizeVectors, chunkSize);
+        const batchRequests = chunkedVectors.map((chunk) => this.caller.call(async () => this.index.upsert(chunk)));
+        await Promise.all(batchRequests);
+        return documentIds;
+    }
+    /**
+     * Method that deletes vectors from the Vectorize database.
+     * @param params Parameters for the delete operation.
+     * @returns Promise that resolves when the delete operation is complete.
+     */
+    async delete(params) {
+        const batchSize = 1000;
+        const batchedIds = chunkArray(params.ids, batchSize);
+        const batchRequests = batchedIds.map((batchIds) => this.caller.call(async () => this.index.deleteByIds(batchIds)));
+        await Promise.all(batchRequests);
+    }
+    /**
+     * Method that performs a similarity search in the Vectorize database and
+     * returns the results along with their scores.
+     * @param query Query vector for the similarity search.
+     * @param k Number of top results to return.
+     * @returns Promise that resolves with an array of documents and their scores.
+     */
+    async similaritySearchVectorWithScore(query, k) {
+        const results = await this.index.query(query, {
+            returnVectors: true,
+            topK: k,
+        });
+        const result = [];
+        if (results.matches) {
+            for (const res of results.matches) {
+                const { [this.textKey]: pageContent, ...metadata } = res.vector?.metadata ?? {};
+                result.push([
+                    new Document({ metadata, pageContent: pageContent }),
+                    res.score,
+                ]);
+            }
+        }
+        return result;
+    }
+    /**
+     * Static method that creates a new instance of the CloudflareVectorizeStore class
+     * from texts.
+     * @param texts Array of texts to add to the Vectorize database.
+     * @param metadatas Metadata associated with the texts.
+     * @param embeddings Embeddings to use for the texts.
+     * @param dbConfig Configuration for the Vectorize database.
+     * @param options Optional ids for the vectors.
+     * @returns Promise that resolves with a new instance of the CloudflareVectorizeStore class.
+     */
+    static async fromTexts(texts, metadatas, embeddings, dbConfig) {
+        const docs = [];
+        for (let i = 0; i < texts.length; i += 1) {
+            const metadata = Array.isArray(metadatas) ? metadatas[i] : metadatas;
+            const newDoc = new Document({
+                pageContent: texts[i],
+                metadata,
+            });
+            docs.push(newDoc);
+        }
+        return CloudflareVectorizeStore.fromDocuments(docs, embeddings, dbConfig);
+    }
+    /**
+     * Static method that creates a new instance of the CloudflareVectorizeStore class
+     * from documents.
+     * @param docs Array of documents to add to the Vectorize database.
+     * @param embeddings Embeddings to use for the documents.
+     * @param dbConfig Configuration for the Vectorize database.
+     * @param options Optional ids for the vectors.
+     * @returns Promise that resolves with a new instance of the CloudflareVectorizeStore class.
+     */
+    static async fromDocuments(docs, embeddings, dbConfig) {
+        const instance = new this(embeddings, dbConfig);
+        await instance.addDocuments(docs);
+        return instance;
+    }
+    /**
+     * Static method that creates a new instance of the CloudflareVectorizeStore class
+     * from an existing index.
+     * @param embeddings Embeddings to use for the documents.
+     * @param dbConfig Configuration for the Vectorize database.
+     * @returns Promise that resolves with a new instance of the CloudflareVectorizeStore class.
+     */
+    static async fromExistingIndex(embeddings, dbConfig) {
+        const instance = new this(embeddings, dbConfig);
+        return instance;
+    }
+}

package/dist/vectorstores/supabase.d.ts

@@ -54,7 +54,7 @@ export declare class SupabaseVectorStore extends VectorStore {
      * @returns A promise that resolves when the vectors have been deleted.
      */
     delete(params: {
-        ids: string[];
+        ids: string[] | number[];
     }): Promise<void>;
     /**
      * Performs a similarity search on the vector store.

package/embeddings/cloudflare_workersai.cjs

@@ -0,0 +1 @@
+module.exports = require('../dist/embeddings/cloudflare_workersai.cjs');

package/embeddings/cloudflare_workersai.d.ts

@@ -0,0 +1 @@
+export * from '../dist/embeddings/cloudflare_workersai.js'

package/embeddings/cloudflare_workersai.js

@@ -0,0 +1 @@
+export * from '../dist/embeddings/cloudflare_workersai.js'