@langchain/core 0.2.18 → 0.2.19

package/dist/utils/testing/index.d.ts

@@ -1,3 +1,4 @@
+import { similarity as ml_distance_similarity } from "ml-distance";
 import { z } from "zod";
 import { BaseCallbackConfig, CallbackManagerForLLMRun, CallbackManagerForToolRun } from "../../callbacks/manager.js";
 import { BaseChatMessageHistory, BaseListChatMessageHistory } from "../../chat_history.js";
@@ -11,8 +12,9 @@ import { BaseRetriever } from "../../retrievers/index.js";
 import { Runnable } from "../../runnables/base.js";
 import { StructuredTool, ToolParams } from "../../tools/index.js";
 import { BaseTracer, Run } from "../../tracers/base.js";
-import { Embeddings, EmbeddingsParams } from "../../embeddings.js";
+import { Embeddings, EmbeddingsInterface, EmbeddingsParams } from "../../embeddings.js";
 import { StructuredOutputMethodParams, BaseLanguageModelInput, StructuredOutputMethodOptions } from "../../language_models/base.js";
+import { VectorStore } from "../../vectorstores.js";
 /**
  * Parser for comma-separated values. It splits the input text by commas
  * and trims the resulting values.
@@ -87,6 +89,7 @@ export interface FakeChatInput extends BaseChatModelParams {
     responses: string[];
     /** Time to sleep in milliseconds between responses */
     sleep?: number;
+    emitCustomEvent?: boolean;
 }
 /**
  * A fake Chat Model that returns a predefined list of responses. It can be used
@@ -113,10 +116,11 @@ export declare class FakeListChatModel extends BaseChatModel {
     responses: string[];
     i: number;
     sleep?: number;
-    constructor({ responses, sleep }: FakeChatInput);
+    emitCustomEvent: boolean;
+    constructor({ responses, sleep, emitCustomEvent }: FakeChatInput);
     _combineLLMOutput(): never[];
     _llmType(): string;
-    _generate(_messages: BaseMessage[], options?: this["ParsedCallOptions"]): Promise<ChatResult>;
+    _generate(_messages: BaseMessage[], options?: this["ParsedCallOptions"], runManager?: CallbackManagerForLLMRun): Promise<ChatResult>;
     _formatGeneration(text: string): {
         message: AIMessage;
         text: string;
@@ -228,4 +232,91 @@ export declare class SingleRunExtractor extends BaseTracer {
     persistRun(run: Run): Promise<void>;
     extract(): Promise<Run>;
 }
+/**
+ * Interface representing a vector in memory. It includes the content
+ * (text), the corresponding embedding (vector), and any associated
+ * metadata.
+ */
+interface MemoryVector {
+    content: string;
+    embedding: number[];
+    metadata: Record<string, any>;
+}
+/**
+ * Interface for the arguments that can be passed to the
+ * `FakeVectorStore` constructor. It includes an optional `similarity`
+ * function.
+ */
+export interface FakeVectorStoreArgs {
+    similarity?: typeof ml_distance_similarity.cosine;
+}
+/**
+ * Class that extends `VectorStore` to store vectors in memory. Provides
+ * methods for adding documents, performing similarity searches, and
+ * creating instances from texts, documents, or an existing index.
+ */
+export declare class FakeVectorStore extends VectorStore {
+    FilterType: (doc: Document) => boolean;
+    memoryVectors: MemoryVector[];
+    similarity: typeof ml_distance_similarity.cosine;
+    _vectorstoreType(): string;
+    constructor(embeddings: EmbeddingsInterface, { similarity, ...rest }?: FakeVectorStoreArgs);
+    /**
+     * Method to add documents to the memory vector store. It extracts the
+     * text from each document, generates embeddings for them, and adds the
+     * resulting vectors to the store.
+     * @param documents Array of `Document` instances to be added to the store.
+     * @returns Promise that resolves when all documents have been added.
+     */
+    addDocuments(documents: Document[]): Promise<void>;
+    /**
+     * Method to add vectors to the memory vector store. It creates
+     * `MemoryVector` instances for each vector and document pair and adds
+     * them to the store.
+     * @param vectors Array of vectors to be added to the store.
+     * @param documents Array of `Document` instances corresponding to the vectors.
+     * @returns Promise that resolves when all vectors have been added.
+     */
+    addVectors(vectors: number[][], documents: Document[]): Promise<void>;
+    /**
+     * Method to perform a similarity search in the memory vector store. It
+     * calculates the similarity between the query vector and each vector in
+     * the store, sorts the results by similarity, and returns the top `k`
+     * results along with their scores.
+     * @param query Query vector to compare against the vectors in the store.
+     * @param k Number of top results to return.
+     * @param filter Optional filter function to apply to the vectors before performing the search.
+     * @returns Promise that resolves with an array of tuples, each containing a `Document` and its similarity score.
+     */
+    similaritySearchVectorWithScore(query: number[], k: number, filter?: this["FilterType"]): Promise<[Document, number][]>;
+    /**
+     * Static method to create a `FakeVectorStore` instance from an array of
+     * texts. It creates a `Document` for each text and metadata pair, and
+     * adds them to the store.
+     * @param texts Array of texts to be added to the store.
+     * @param metadatas Array or single object of metadata corresponding to the texts.
+     * @param embeddings `Embeddings` instance used to generate embeddings for the texts.
+     * @param dbConfig Optional `FakeVectorStoreArgs` to configure the `FakeVectorStore` instance.
+     * @returns Promise that resolves with a new `FakeVectorStore` instance.
+     */
+    static fromTexts(texts: string[], metadatas: object[] | object, embeddings: EmbeddingsInterface, dbConfig?: FakeVectorStoreArgs): Promise<FakeVectorStore>;
+    /**
+     * Static method to create a `FakeVectorStore` instance from an array of
+     * `Document` instances. It adds the documents to the store.
+     * @param docs Array of `Document` instances to be added to the store.
+     * @param embeddings `Embeddings` instance used to generate embeddings for the documents.
+     * @param dbConfig Optional `FakeVectorStoreArgs` to configure the `FakeVectorStore` instance.
+     * @returns Promise that resolves with a new `FakeVectorStore` instance.
+     */
+    static fromDocuments(docs: Document[], embeddings: EmbeddingsInterface, dbConfig?: FakeVectorStoreArgs): Promise<FakeVectorStore>;
+    /**
+     * Static method to create a `FakeVectorStore` instance from an existing
+     * index. It creates a new `FakeVectorStore` instance without adding any
+     * documents or vectors.
+     * @param embeddings `Embeddings` instance used to generate embeddings for the documents.
+     * @param dbConfig Optional `FakeVectorStoreArgs` to configure the `FakeVectorStore` instance.
+     * @returns Promise that resolves with a new `FakeVectorStore` instance.
+     */
+    static fromExistingIndex(embeddings: EmbeddingsInterface, dbConfig?: FakeVectorStoreArgs): Promise<FakeVectorStore>;
+}
 export {};

package/dist/utils/testing/index.js

@@ -1,6 +1,7 @@
 /* eslint-disable no-promise-executor-return */
 /* eslint-disable @typescript-eslint/no-explicit-any */
 /* eslint-disable @typescript-eslint/no-unused-vars */
+import { similarity as ml_distance_similarity } from "ml-distance";
 import { BaseChatMessageHistory, BaseListChatMessageHistory, } from "../../chat_history.js";
 import { Document } from "../../documents/document.js";
 import { BaseChatModel, } from "../../language_models/chat_models.js";
@@ -12,7 +13,8 @@ import { BaseRetriever } from "../../retrievers/index.js";
 import { Runnable, RunnableLambda } from "../../runnables/base.js";
 import { StructuredTool } from "../../tools/index.js";
 import { BaseTracer } from "../../tracers/base.js";
-import { Embeddings } from "../../embeddings.js";
+import { Embeddings, } from "../../embeddings.js";
+import { VectorStore } from "../../vectorstores.js";
 /**
  * Parser for comma-separated values. It splits the input text by commas
  * and trims the resulting values.
@@ -297,7 +299,7 @@ export class FakeListChatModel extends BaseChatModel {
     static lc_name() {
         return "FakeListChatModel";
     }
-    constructor({ responses, sleep }) {
+    constructor({ responses, sleep, emitCustomEvent }) {
         super({});
         Object.defineProperty(this, "responses", {
             enumerable: true,
@@ -317,8 +319,15 @@ export class FakeListChatModel extends BaseChatModel {
             writable: true,
             value: void 0
         });
+        Object.defineProperty(this, "emitCustomEvent", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: false
+        });
         this.responses = responses;
         this.sleep = sleep;
+        this.emitCustomEvent = emitCustomEvent ?? this.emitCustomEvent;
     }
     _combineLLMOutput() {
         return [];
@@ -326,8 +335,13 @@ export class FakeListChatModel extends BaseChatModel {
     _llmType() {
         return "fake-list";
     }
-    async _generate(_messages, options) {
+    async _generate(_messages, options, runManager) {
         await this._sleepIfRequested();
+        if (this.emitCustomEvent) {
+            await runManager?.handleCustomEvent("some_test_event", {
+                someval: true,
+            });
+        }
         if (options?.stop?.length) {
             return {
                 generations: [this._formatGeneration(options.stop[0])],
@@ -351,6 +365,11 @@ export class FakeListChatModel extends BaseChatModel {
     async *_streamResponseChunks(_messages, _options, runManager) {
         const response = this._currentResponse();
         this._incrementResponse();
+        if (this.emitCustomEvent) {
+            await runManager?.handleCustomEvent("some_test_event", {
+                someval: true,
+            });
+        }
         for await (const text of response) {
             await this._sleepIfRequested();
             const chunk = this._createResponseChunk(text);
@@ -618,3 +637,141 @@ export class SingleRunExtractor extends BaseTracer {
         return this.runPromise;
     }
 }
+/**
+ * Class that extends `VectorStore` to store vectors in memory. Provides
+ * methods for adding documents, performing similarity searches, and
+ * creating instances from texts, documents, or an existing index.
+ */
+export class FakeVectorStore extends VectorStore {
+    _vectorstoreType() {
+        return "memory";
+    }
+    constructor(embeddings, { similarity, ...rest } = {}) {
+        super(embeddings, rest);
+        Object.defineProperty(this, "memoryVectors", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: []
+        });
+        Object.defineProperty(this, "similarity", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: void 0
+        });
+        this.similarity = similarity ?? ml_distance_similarity.cosine;
+    }
+    /**
+     * Method to add documents to the memory vector store. It extracts the
+     * text from each document, generates embeddings for them, and adds the
+     * resulting vectors to the store.
+     * @param documents Array of `Document` instances to be added to the store.
+     * @returns Promise that resolves when all documents have been added.
+     */
+    async addDocuments(documents) {
+        const texts = documents.map(({ pageContent }) => pageContent);
+        return this.addVectors(await this.embeddings.embedDocuments(texts), documents);
+    }
+    /**
+     * Method to add vectors to the memory vector store. It creates
+     * `MemoryVector` instances for each vector and document pair and adds
+     * them to the store.
+     * @param vectors Array of vectors to be added to the store.
+     * @param documents Array of `Document` instances corresponding to the vectors.
+     * @returns Promise that resolves when all vectors have been added.
+     */
+    async addVectors(vectors, documents) {
+        const memoryVectors = vectors.map((embedding, idx) => ({
+            content: documents[idx].pageContent,
+            embedding,
+            metadata: documents[idx].metadata,
+        }));
+        this.memoryVectors = this.memoryVectors.concat(memoryVectors);
+    }
+    /**
+     * Method to perform a similarity search in the memory vector store. It
+     * calculates the similarity between the query vector and each vector in
+     * the store, sorts the results by similarity, and returns the top `k`
+     * results along with their scores.
+     * @param query Query vector to compare against the vectors in the store.
+     * @param k Number of top results to return.
+     * @param filter Optional filter function to apply to the vectors before performing the search.
+     * @returns Promise that resolves with an array of tuples, each containing a `Document` and its similarity score.
+     */
+    async similaritySearchVectorWithScore(query, k, filter) {
+        const filterFunction = (memoryVector) => {
+            if (!filter) {
+                return true;
+            }
+            const doc = new Document({
+                metadata: memoryVector.metadata,
+                pageContent: memoryVector.content,
+            });
+            return filter(doc);
+        };
+        const filteredMemoryVectors = this.memoryVectors.filter(filterFunction);
+        const searches = filteredMemoryVectors
+            .map((vector, index) => ({
+            similarity: this.similarity(query, vector.embedding),
+            index,
+        }))
+            .sort((a, b) => (a.similarity > b.similarity ? -1 : 0))
+            .slice(0, k);
+        const result = searches.map((search) => [
+            new Document({
+                metadata: filteredMemoryVectors[search.index].metadata,
+                pageContent: filteredMemoryVectors[search.index].content,
+            }),
+            search.similarity,
+        ]);
+        return result;
+    }
+    /**
+     * Static method to create a `FakeVectorStore` instance from an array of
+     * texts. It creates a `Document` for each text and metadata pair, and
+     * adds them to the store.
+     * @param texts Array of texts to be added to the store.
+     * @param metadatas Array or single object of metadata corresponding to the texts.
+     * @param embeddings `Embeddings` instance used to generate embeddings for the texts.
+     * @param dbConfig Optional `FakeVectorStoreArgs` to configure the `FakeVectorStore` instance.
+     * @returns Promise that resolves with a new `FakeVectorStore` instance.
+     */
+    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 FakeVectorStore.fromDocuments(docs, embeddings, dbConfig);
+    }
+    /**
+     * Static method to create a `FakeVectorStore` instance from an array of
+     * `Document` instances. It adds the documents to the store.
+     * @param docs Array of `Document` instances to be added to the store.
+     * @param embeddings `Embeddings` instance used to generate embeddings for the documents.
+     * @param dbConfig Optional `FakeVectorStoreArgs` to configure the `FakeVectorStore` instance.
+     * @returns Promise that resolves with a new `FakeVectorStore` instance.
+     */
+    static async fromDocuments(docs, embeddings, dbConfig) {
+        const instance = new this(embeddings, dbConfig);
+        await instance.addDocuments(docs);
+        return instance;
+    }
+    /**
+     * Static method to create a `FakeVectorStore` instance from an existing
+     * index. It creates a new `FakeVectorStore` instance without adding any
+     * documents or vectors.
+     * @param embeddings `Embeddings` instance used to generate embeddings for the documents.
+     * @param dbConfig Optional `FakeVectorStoreArgs` to configure the `FakeVectorStore` instance.
+     * @returns Promise that resolves with a new `FakeVectorStore` instance.
+     */
+    static async fromExistingIndex(embeddings, dbConfig) {
+        const instance = new this(embeddings, dbConfig);
+        return instance;
+    }
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@langchain/core",
-  "version": "0.2.18",
+  "version": "0.2.19",
   "description": "Core LangChain.js abstractions and schemas",
   "type": "module",
   "engines": {
@@ -15,7 +15,7 @@
   "homepage": "https://github.com/langchain-ai/langchainjs/tree/main/langchain-core/",
   "scripts": {
     "build": "yarn turbo:command build:internal --filter=@langchain/core",
-    "build:internal": "yarn lc-build:v2 --create-entrypoints --pre --tree-shaking",
+    "build:internal": "yarn lc_build_v2 --create-entrypoints --pre --tree-shaking",
     "clean": "rm -rf .turbo dist/",
     "build:deps": "yarn turbo build",
     "build:esm": "NODE_OPTIONS=--max-old-space-size=4096 tsc --outDir dist/ && rimraf dist/tests dist/**/tests",
@@ -56,9 +56,10 @@
   },
   "devDependencies": {
     "@jest/globals": "^29.5.0",
-    "@langchain/scripts": "~0.0.14",
+    "@langchain/scripts": "~0.0.20",
     "@swc/core": "^1.3.90",
     "@swc/jest": "^0.2.29",
+    "@types/decamelize": "^1.2.0",
     "@types/mustache": "^4",
     "dpdm": "^3.12.0",
     "eslint": "^8.33.0",

package/dist/caches/tests/in_memory_cache.test.d.ts

@@ -1 +0,0 @@
-export {};

package/dist/caches/tests/in_memory_cache.test.js

@@ -1,33 +0,0 @@
-import { InMemoryCache } from "../base.js";
-test("InMemoryCache works", async () => {
-    const cache = new InMemoryCache();
-    await cache.update("prompt", "key1", [
-        {
-            text: "text1",
-        },
-    ]);
-    const result = await cache.lookup("prompt", "key1");
-    expect(result).toBeDefined();
-    if (!result) {
-        return;
-    }
-    expect(result[0].text).toBe("text1");
-});
-test("InMemoryCache works with complex message types", async () => {
-    const cache = new InMemoryCache();
-    await cache.update("prompt", "key1", [
-        {
-            type: "text",
-            text: "text1",
-        },
-    ]);
-    const result = await cache.lookup("prompt", "key1");
-    expect(result).toBeDefined();
-    if (!result) {
-        return;
-    }
-    expect(result[0]).toEqual({
-        type: "text",
-        text: "text1",
-    });
-});

package/dist/callbacks/tests/callbacks.test.d.ts

@@ -1 +0,0 @@
-export {};