langchain 0.0.128 → 0.0.129

package/dist/storage/ioredis.d.ts

@@ -0,0 +1,22 @@
+/// <reference types="node" resolution-mode="require"/>
+import type { Redis } from "ioredis";
+import { BaseStore } from "../schema/storage.js";
+export declare class RedisByteStore extends BaseStore<string, Uint8Array> {
+    lc_namespace: string[];
+    protected client: Redis;
+    protected ttl?: number;
+    protected namespace?: string;
+    protected yieldKeysScanBatchSize: number;
+    constructor(fields: {
+        client: Redis;
+        ttl?: number;
+        namespace?: string;
+        yieldKeysScanBatchSize?: number;
+    });
+    _getPrefixedKey(key: string): string;
+    _getDeprefixedKey(key: string): string;
+    mget(keys: string[]): Promise<(Buffer | undefined)[]>;
+    mset(keyValuePairs: [string, Uint8Array][]): Promise<void>;
+    mdelete(keys: string[]): Promise<void>;
+    yieldKeys(prefix?: string): AsyncGenerator<string>;
+}

package/dist/storage/ioredis.js

@@ -0,0 +1,106 @@
+import { BaseStore } from "../schema/storage.js";
+export class RedisByteStore extends BaseStore {
+    constructor(fields) {
+        super(fields);
+        Object.defineProperty(this, "lc_namespace", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: ["langchain", "storage", "ioredis"]
+        });
+        Object.defineProperty(this, "client", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: void 0
+        });
+        Object.defineProperty(this, "ttl", {
+            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, "yieldKeysScanBatchSize", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: 1000
+        });
+        this.client = fields.client;
+        this.ttl = fields.ttl;
+        this.namespace = fields.namespace;
+        this.yieldKeysScanBatchSize =
+            fields.yieldKeysScanBatchSize ?? this.yieldKeysScanBatchSize;
+    }
+    _getPrefixedKey(key) {
+        if (this.namespace) {
+            const delimiter = "/";
+            return `${this.namespace}${delimiter}${key}`;
+        }
+        return key;
+    }
+    _getDeprefixedKey(key) {
+        if (this.namespace) {
+            const delimiter = "/";
+            return key.slice(this.namespace.length + delimiter.length);
+        }
+        return key;
+    }
+    async mget(keys) {
+        const prefixedKeys = keys.map(this._getPrefixedKey.bind(this));
+        const retrievedValues = await this.client.mgetBuffer(prefixedKeys);
+        return retrievedValues.map((key) => {
+            if (!key) {
+                return undefined;
+            }
+            else {
+                return key;
+            }
+        });
+    }
+    async mset(keyValuePairs) {
+        const decoder = new TextDecoder();
+        const encodedKeyValuePairs = keyValuePairs.map(([key, value]) => [
+            this._getPrefixedKey(key),
+            decoder.decode(value),
+        ]);
+        const pipeline = this.client.pipeline();
+        for (const [key, value] of encodedKeyValuePairs) {
+            if (this.ttl) {
+                pipeline.set(key, value, "EX", this.ttl);
+            }
+            else {
+                pipeline.set(key, value);
+            }
+        }
+        await pipeline.exec();
+    }
+    async mdelete(keys) {
+        await this.client.del(...keys.map(this._getPrefixedKey.bind(this)));
+    }
+    async *yieldKeys(prefix) {
+        let pattern;
+        if (prefix) {
+            pattern = this._getPrefixedKey(prefix);
+        }
+        else {
+            pattern = this._getPrefixedKey("*");
+        }
+        let [cursor, batch] = await this.client.scan(0, "MATCH", pattern, "COUNT", this.yieldKeysScanBatchSize);
+        for (const key of batch) {
+            yield this._getDeprefixedKey(key);
+        }
+        while (cursor !== "0") {
+            [cursor, batch] = await this.client.scan(cursor, "MATCH", pattern, "COUNT", this.yieldKeysScanBatchSize);
+            for (const key of batch) {
+                yield this._getDeprefixedKey(key);
+            }
+        }
+    }
+}

package/dist/vectorstores/zep.cjs

@@ -5,6 +5,7 @@ const zep_js_1 = require("@getzep/zep-js");
 const base_js_1 = require("./base.cjs");
 const document_js_1 = require("../document.cjs");
 const fake_js_1 = require("../embeddings/fake.cjs");
+const math_js_1 = require("../util/math.cjs");
 /**
  * ZepVectorStore is a VectorStore implementation that uses the Zep long-term memory store as a backend.
  *
@@ -52,7 +53,8 @@ class ZepVectorStore extends base_js_1.VectorStore {
             this.autoEmbed = true;
         }
         this.initPromise = this.initCollection(args).catch((err) => {
-            console.error("Error retrieving collection:", err);
+            console.error("Error initializing collection:", err);
+            throw err;
         });
     }
     /**
@@ -160,13 +162,6 @@ class ZepVectorStore extends base_js_1.VectorStore {
             await this.collection.deleteDocument(uuid);
         }
     }
-    isRecord(value) {
-        return (typeof value === "object" &&
-            value !== null &&
-            !Array.isArray(value) &&
-            // eslint-disable-next-line no-instanceof/no-instanceof
-            !(value instanceof Function));
-    }
     /**
      * Performs a similarity search in the collection and returns the results with their scores.
      *
@@ -176,25 +171,90 @@ class ZepVectorStore extends base_js_1.VectorStore {
      * @returns {Promise<[Document, number][]>} - A promise that resolves with the search results and their scores.
      */
     async similaritySearchVectorWithScore(query, k, filter) {
-        if (filter && !this.isRecord(filter)) {
-            throw new Error(`Filter must be a record, got ${filter}`);
-        }
         await this.initPromise;
         const results = await this.collection.search({
             embedding: new Float32Array(query),
-            metadata: filter,
+            metadata: assignMetadata(filter),
         }, k);
-        const docsAndScore = [];
-        results.forEach((d) => {
-            docsAndScore.push([
-                new document_js_1.Document({
-                    pageContent: d.content,
-                    metadata: d.metadata,
-                }),
-                d.score ? d.score : 0,
-            ]);
-        });
-        return docsAndScore;
+        return zepDocsToDocumentsAndScore(results);
+    }
+    async _similaritySearchWithScore(query, k, filter) {
+        await this.initPromise;
+        const results = await this.collection.search({
+            text: query,
+            metadata: assignMetadata(filter),
+        }, k);
+        return zepDocsToDocumentsAndScore(results);
+    }
+    async similaritySearchWithScore(query, k = 4, filter = undefined, _callbacks = undefined // implement passing to embedQuery later
+    ) {
+        if (this.autoEmbed) {
+            return this._similaritySearchWithScore(query, k, filter);
+        }
+        else {
+            return this.similaritySearchVectorWithScore(await this.embeddings.embedQuery(query), k, filter);
+        }
+    }
+    /**
+     * Performs a similarity search on the Zep collection.
+     *
+     * @param {string} query - The query string to search for.
+     * @param {number} [k=4] - The number of results to return. Defaults to 4.
+     * @param {this["FilterType"] | undefined} [filter=undefined] - An optional set of JSONPath filters to apply to the search.
+     * @param {Callbacks | undefined} [_callbacks=undefined] - Optional callbacks. Currently not implemented.
+     * @returns {Promise<Document[]>} - A promise that resolves to an array of Documents that are similar to the query.
+     *
+     * @async
+     */
+    async similaritySearch(query, k = 4, filter = undefined, _callbacks = undefined // implement passing to embedQuery later
+    ) {
+        await this.initPromise;
+        let results;
+        if (this.autoEmbed) {
+            const zepResults = await this.collection.search({ text: query, metadata: assignMetadata(filter) }, k);
+            results = zepDocsToDocumentsAndScore(zepResults);
+        }
+        else {
+            results = await this.similaritySearchVectorWithScore(await this.embeddings.embedQuery(query), k, assignMetadata(filter));
+        }
+        return results.map((result) => result[0]);
+    }
+    /**
+     * Return documents selected using the maximal marginal relevance.
+     * Maximal marginal relevance optimizes for similarity to the query AND diversity
+     * among selected documents.
+     *
+     * @param {string} query - Text to look up documents similar to.
+     * @param options
+     * @param {number} options.k - Number of documents to return.
+     * @param {number} options.fetchK=20- Number of documents to fetch before passing to the MMR algorithm.
+     * @param {number} options.lambda=0.5 - Number between 0 and 1 that determines the degree of diversity among the results,
+     *                 where 0 corresponds to maximum diversity and 1 to minimum diversity.
+     * @param {Record<string, any>} options.filter - Optional Zep JSONPath query to pre-filter on document metadata field
+     *
+     * @returns {Promise<Document[]>} - List of documents selected by maximal marginal relevance.
+     */
+    async maxMarginalRelevanceSearch(query, options) {
+        const { k, fetchK = 20, lambda = 0.5, filter } = options;
+        let queryEmbedding;
+        let zepResults;
+        if (!this.autoEmbed) {
+            queryEmbedding = await this.embeddings.embedQuery(query);
+            zepResults = await this.collection.search({
+                embedding: new Float32Array(queryEmbedding),
+                metadata: assignMetadata(filter),
+            }, fetchK);
+        }
+        else {
+            let queryEmbeddingArray;
+            [zepResults, queryEmbeddingArray] =
+                await this.collection.searchReturnQueryVector({ text: query, metadata: assignMetadata(filter) }, fetchK);
+            queryEmbedding = Array.from(queryEmbeddingArray);
+        }
+        const results = zepDocsToDocumentsAndScore(zepResults);
+        const embeddingList = zepResults.map((doc) => Array.from(doc.embedding ? doc.embedding : []));
+        const mmrIndexes = (0, math_js_1.maximalMarginalRelevance)(queryEmbedding, embeddingList, lambda, k);
+        return mmrIndexes.filter((idx) => idx !== -1).map((idx) => results[idx][0]);
     }
     /**
      * Creates a new ZepVectorStore instance from an array of texts. Each text is converted into a Document and added to the collection.
@@ -234,3 +294,21 @@ class ZepVectorStore extends base_js_1.VectorStore {
     }
 }
 exports.ZepVectorStore = ZepVectorStore;
+function zepDocsToDocumentsAndScore(results) {
+    return results.map((d) => [
+        new document_js_1.Document({
+            pageContent: d.content,
+            metadata: d.metadata,
+        }),
+        d.score ? d.score : 0,
+    ]);
+}
+function assignMetadata(value) {
+    if (typeof value === "object" && value !== null) {
+        return value;
+    }
+    if (value !== undefined) {
+        console.warn("Metadata filters must be an object, Record, or undefined.");
+    }
+    return undefined;
+}

package/dist/vectorstores/zep.d.ts

@@ -1,7 +1,8 @@
 import { DocumentCollection, ZepClient } from "@getzep/zep-js";
-import { VectorStore } from "./base.js";
+import { MaxMarginalRelevanceSearchOptions, VectorStore } from "./base.js";
 import { Embeddings } from "../embeddings/base.js";
 import { Document } from "../document.js";
+import { Callbacks } from "../callbacks/index.js";
 export interface IZepArgs {
     collection: DocumentCollection;
 }
@@ -73,7 +74,6 @@ export declare class ZepVectorStore extends VectorStore {
      * @returns {Promise<void>}
      */
     delete(params: IZepDeleteParams): Promise<void>;
-    private isRecord;
     /**
      * Performs a similarity search in the collection and returns the results with their scores.
      *
@@ -83,6 +83,36 @@ export declare class ZepVectorStore extends VectorStore {
      * @returns {Promise<[Document, number][]>} - A promise that resolves with the search results and their scores.
      */
     similaritySearchVectorWithScore(query: number[], k: number, filter?: Record<string, unknown> | undefined): Promise<[Document, number][]>;
+    _similaritySearchWithScore(query: string, k: number, filter?: Record<string, unknown> | undefined): Promise<[Document, number][]>;
+    similaritySearchWithScore(query: string, k?: number, filter?: Record<string, unknown> | undefined, _callbacks?: undefined): Promise<[Document, number][]>;
+    /**
+     * Performs a similarity search on the Zep collection.
+     *
+     * @param {string} query - The query string to search for.
+     * @param {number} [k=4] - The number of results to return. Defaults to 4.
+     * @param {this["FilterType"] | undefined} [filter=undefined] - An optional set of JSONPath filters to apply to the search.
+     * @param {Callbacks | undefined} [_callbacks=undefined] - Optional callbacks. Currently not implemented.
+     * @returns {Promise<Document[]>} - A promise that resolves to an array of Documents that are similar to the query.
+     *
+     * @async
+     */
+    similaritySearch(query: string, k?: number, filter?: this["FilterType"] | undefined, _callbacks?: Callbacks | undefined): Promise<Document[]>;
+    /**
+     * Return documents selected using the maximal marginal relevance.
+     * Maximal marginal relevance optimizes for similarity to the query AND diversity
+     * among selected documents.
+     *
+     * @param {string} query - Text to look up documents similar to.
+     * @param options
+     * @param {number} options.k - Number of documents to return.
+     * @param {number} options.fetchK=20- Number of documents to fetch before passing to the MMR algorithm.
+     * @param {number} options.lambda=0.5 - Number between 0 and 1 that determines the degree of diversity among the results,
+     *                 where 0 corresponds to maximum diversity and 1 to minimum diversity.
+     * @param {Record<string, any>} options.filter - Optional Zep JSONPath query to pre-filter on document metadata field
+     *
+     * @returns {Promise<Document[]>} - List of documents selected by maximal marginal relevance.
+     */
+    maxMarginalRelevanceSearch(query: string, options: MaxMarginalRelevanceSearchOptions<this["FilterType"]>): Promise<Document[]>;
     /**
      * Creates a new ZepVectorStore instance from an array of texts. Each text is converted into a Document and added to the collection.
      *

package/dist/vectorstores/zep.js

@@ -2,6 +2,7 @@ import { ZepClient } from "@getzep/zep-js";
 import { VectorStore } from "./base.js";
 import { Document } from "../document.js";
 import { FakeEmbeddings } from "../embeddings/fake.js";
+import { maximalMarginalRelevance } from "../util/math.js";
 /**
  * ZepVectorStore is a VectorStore implementation that uses the Zep long-term memory store as a backend.
  *
@@ -49,7 +50,8 @@ export class ZepVectorStore extends VectorStore {
             this.autoEmbed = true;
         }
         this.initPromise = this.initCollection(args).catch((err) => {
-            console.error("Error retrieving collection:", err);
+            console.error("Error initializing collection:", err);
+            throw err;
         });
     }
     /**
@@ -157,13 +159,6 @@ export class ZepVectorStore extends VectorStore {
             await this.collection.deleteDocument(uuid);
         }
     }
-    isRecord(value) {
-        return (typeof value === "object" &&
-            value !== null &&
-            !Array.isArray(value) &&
-            // eslint-disable-next-line no-instanceof/no-instanceof
-            !(value instanceof Function));
-    }
     /**
      * Performs a similarity search in the collection and returns the results with their scores.
      *
@@ -173,25 +168,90 @@ export class ZepVectorStore extends VectorStore {
      * @returns {Promise<[Document, number][]>} - A promise that resolves with the search results and their scores.
      */
     async similaritySearchVectorWithScore(query, k, filter) {
-        if (filter && !this.isRecord(filter)) {
-            throw new Error(`Filter must be a record, got ${filter}`);
-        }
         await this.initPromise;
         const results = await this.collection.search({
             embedding: new Float32Array(query),
-            metadata: filter,
+            metadata: assignMetadata(filter),
         }, k);
-        const docsAndScore = [];
-        results.forEach((d) => {
-            docsAndScore.push([
-                new Document({
-                    pageContent: d.content,
-                    metadata: d.metadata,
-                }),
-                d.score ? d.score : 0,
-            ]);
-        });
-        return docsAndScore;
+        return zepDocsToDocumentsAndScore(results);
+    }
+    async _similaritySearchWithScore(query, k, filter) {
+        await this.initPromise;
+        const results = await this.collection.search({
+            text: query,
+            metadata: assignMetadata(filter),
+        }, k);
+        return zepDocsToDocumentsAndScore(results);
+    }
+    async similaritySearchWithScore(query, k = 4, filter = undefined, _callbacks = undefined // implement passing to embedQuery later
+    ) {
+        if (this.autoEmbed) {
+            return this._similaritySearchWithScore(query, k, filter);
+        }
+        else {
+            return this.similaritySearchVectorWithScore(await this.embeddings.embedQuery(query), k, filter);
+        }
+    }
+    /**
+     * Performs a similarity search on the Zep collection.
+     *
+     * @param {string} query - The query string to search for.
+     * @param {number} [k=4] - The number of results to return. Defaults to 4.
+     * @param {this["FilterType"] | undefined} [filter=undefined] - An optional set of JSONPath filters to apply to the search.
+     * @param {Callbacks | undefined} [_callbacks=undefined] - Optional callbacks. Currently not implemented.
+     * @returns {Promise<Document[]>} - A promise that resolves to an array of Documents that are similar to the query.
+     *
+     * @async
+     */
+    async similaritySearch(query, k = 4, filter = undefined, _callbacks = undefined // implement passing to embedQuery later
+    ) {
+        await this.initPromise;
+        let results;
+        if (this.autoEmbed) {
+            const zepResults = await this.collection.search({ text: query, metadata: assignMetadata(filter) }, k);
+            results = zepDocsToDocumentsAndScore(zepResults);
+        }
+        else {
+            results = await this.similaritySearchVectorWithScore(await this.embeddings.embedQuery(query), k, assignMetadata(filter));
+        }
+        return results.map((result) => result[0]);
+    }
+    /**
+     * Return documents selected using the maximal marginal relevance.
+     * Maximal marginal relevance optimizes for similarity to the query AND diversity
+     * among selected documents.
+     *
+     * @param {string} query - Text to look up documents similar to.
+     * @param options
+     * @param {number} options.k - Number of documents to return.
+     * @param {number} options.fetchK=20- Number of documents to fetch before passing to the MMR algorithm.
+     * @param {number} options.lambda=0.5 - Number between 0 and 1 that determines the degree of diversity among the results,
+     *                 where 0 corresponds to maximum diversity and 1 to minimum diversity.
+     * @param {Record<string, any>} options.filter - Optional Zep JSONPath query to pre-filter on document metadata field
+     *
+     * @returns {Promise<Document[]>} - List of documents selected by maximal marginal relevance.
+     */
+    async maxMarginalRelevanceSearch(query, options) {
+        const { k, fetchK = 20, lambda = 0.5, filter } = options;
+        let queryEmbedding;
+        let zepResults;
+        if (!this.autoEmbed) {
+            queryEmbedding = await this.embeddings.embedQuery(query);
+            zepResults = await this.collection.search({
+                embedding: new Float32Array(queryEmbedding),
+                metadata: assignMetadata(filter),
+            }, fetchK);
+        }
+        else {
+            let queryEmbeddingArray;
+            [zepResults, queryEmbeddingArray] =
+                await this.collection.searchReturnQueryVector({ text: query, metadata: assignMetadata(filter) }, fetchK);
+            queryEmbedding = Array.from(queryEmbeddingArray);
+        }
+        const results = zepDocsToDocumentsAndScore(zepResults);
+        const embeddingList = zepResults.map((doc) => Array.from(doc.embedding ? doc.embedding : []));
+        const mmrIndexes = maximalMarginalRelevance(queryEmbedding, embeddingList, lambda, k);
+        return mmrIndexes.filter((idx) => idx !== -1).map((idx) => results[idx][0]);
     }
     /**
      * Creates a new ZepVectorStore instance from an array of texts. Each text is converted into a Document and added to the collection.
@@ -230,3 +290,21 @@ export class ZepVectorStore extends VectorStore {
         return instance;
     }
 }
+function zepDocsToDocumentsAndScore(results) {
+    return results.map((d) => [
+        new Document({
+            pageContent: d.content,
+            metadata: d.metadata,
+        }),
+        d.score ? d.score : 0,
+    ]);
+}
+function assignMetadata(value) {
+    if (typeof value === "object" && value !== null) {
+        return value;
+    }
+    if (value !== undefined) {
+        console.warn("Metadata filters must be an object, Record, or undefined.");
+    }
+    return undefined;
+}

package/embeddings/cache_backed.cjs

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

package/embeddings/cache_backed.d.ts

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

package/embeddings/cache_backed.js

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

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "langchain",
-  "version": "0.0.128",
+  "version": "0.0.129",
   "description": "Typescript bindings for langchain",
   "type": "module",
   "engines": {
@@ -76,6 +76,9 @@
     "embeddings/base.cjs",
     "embeddings/base.js",
     "embeddings/base.d.ts",
+    "embeddings/cache_backed.cjs",
+    "embeddings/cache_backed.js",
+    "embeddings/cache_backed.d.ts",
     "embeddings/fake.cjs",
     "embeddings/fake.js",
     "embeddings/fake.d.ts",
@@ -391,6 +394,9 @@
     "schema/runnable.cjs",
     "schema/runnable.js",
     "schema/runnable.d.ts",
+    "schema/storage.cjs",
+    "schema/storage.js",
+    "schema/storage.d.ts",
     "sql_db.cjs",
     "sql_db.js",
     "sql_db.d.ts",
@@ -517,6 +523,12 @@
     "stores/message/xata.cjs",
     "stores/message/xata.js",
     "stores/message/xata.d.ts",
+    "storage/in_memory.cjs",
+    "storage/in_memory.js",
+    "storage/in_memory.d.ts",
+    "storage/ioredis.cjs",
+    "storage/ioredis.js",
+    "storage/ioredis.d.ts",
     "util/math.cjs",
     "util/math.js",
     "util/math.d.ts",
@@ -1111,6 +1123,11 @@
       "import": "./embeddings/base.js",
       "require": "./embeddings/base.cjs"
     },
+    "./embeddings/cache_backed": {
+      "types": "./embeddings/cache_backed.d.ts",
+      "import": "./embeddings/cache_backed.js",
+      "require": "./embeddings/cache_backed.cjs"
+    },
     "./embeddings/fake": {
       "types": "./embeddings/fake.d.ts",
       "import": "./embeddings/fake.js",
@@ -1644,6 +1661,11 @@
       "import": "./schema/runnable.js",
       "require": "./schema/runnable.cjs"
     },
+    "./schema/storage": {
+      "types": "./schema/storage.d.ts",
+      "import": "./schema/storage.js",
+      "require": "./schema/storage.cjs"
+    },
     "./sql_db": {
       "types": "./sql_db.d.ts",
       "import": "./sql_db.js",
@@ -1856,6 +1878,16 @@
       "import": "./stores/message/xata.js",
       "require": "./stores/message/xata.cjs"
     },
+    "./storage/in_memory": {
+      "types": "./storage/in_memory.d.ts",
+      "import": "./storage/in_memory.js",
+      "require": "./storage/in_memory.cjs"
+    },
+    "./storage/ioredis": {
+      "types": "./storage/ioredis.d.ts",
+      "import": "./storage/ioredis.js",
+      "require": "./storage/ioredis.cjs"
+    },
     "./util/math": {
       "types": "./util/math.d.ts",
       "import": "./util/math.js",

package/schema/storage.cjs

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

package/schema/storage.d.ts

@@ -0,0 +1 @@
+export * from '../dist/schema/storage.js'

package/schema/storage.js

@@ -0,0 +1 @@
+export * from '../dist/schema/storage.js'

package/storage/in_memory.cjs

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

package/storage/in_memory.d.ts

@@ -0,0 +1 @@
+export * from '../dist/storage/in_memory.js'

package/storage/in_memory.js

@@ -0,0 +1 @@
+export * from '../dist/storage/in_memory.js'

package/storage/ioredis.cjs

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

package/storage/ioredis.d.ts

@@ -0,0 +1 @@
+export * from '../dist/storage/ioredis.js'

package/storage/ioredis.js

@@ -0,0 +1 @@
+export * from '../dist/storage/ioredis.js'