langchain 0.2.16 → 0.2.17

package/dist/vectorstores/memory.cjs

@@ -6,9 +6,114 @@ const documents_1 = require("@langchain/core/documents");
 const similarities_js_1 = require("../util/ml-distance/similarities.cjs");
 const math_js_1 = require("../util/math.cjs");
 /**
- * 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.
+ * In-memory, ephemeral vector store.
+ *
+ * Setup:
+ * Install `langchain`:
+ *
+ * ```bash
+ * npm install langchain
+ * ```
+ *
+ * ## [Constructor args](https://api.js.langchain.com/classes/langchain.vectorstores_memory.MemoryVectorStore.html#constructor)
+ *
+ * <details open>
+ * <summary><strong>Instantiate</strong></summary>
+ *
+ * ```typescript
+ * import { MemoryVectorStore } from 'langchain/vectorstores/memory';
+ * // Or other embeddings
+ * import { OpenAIEmbeddings } from '@langchain/openai';
+ *
+ * const embeddings = new OpenAIEmbeddings({
+ *   model: "text-embedding-3-small",
+ * });
+ *
+ * const vectorStore = new MemoryVectorStore(embeddings);
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Add documents</strong></summary>
+ *
+ * ```typescript
+ * import type { Document } from '@langchain/core/documents';
+ *
+ * const document1 = { pageContent: "foo", metadata: { baz: "bar" } };
+ * const document2 = { pageContent: "thud", metadata: { bar: "baz" } };
+ * const document3 = { pageContent: "i will be deleted :(", metadata: {} };
+ *
+ * const documents: Document[] = [document1, document2, document3];
+ *
+ * await vectorStore.addDocuments(documents);
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Similarity search</strong></summary>
+ *
+ * ```typescript
+ * const results = await vectorStore.similaritySearch("thud", 1);
+ * for (const doc of results) {
+ *   console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * thud [{"baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ *
+ * <details>
+ * <summary><strong>Similarity search with filter</strong></summary>
+ *
+ * ```typescript
+ * const resultsWithFilter = await vectorStore.similaritySearch("thud", 1, { baz: "bar" });
+ *
+ * for (const doc of resultsWithFilter) {
+ *   console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * foo [{"baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ *
+ * <details>
+ * <summary><strong>Similarity search with score</strong></summary>
+ *
+ * ```typescript
+ * const resultsWithScore = await vectorStore.similaritySearchWithScore("qux", 1);
+ * for (const [doc, score] of resultsWithScore) {
+ *   console.log(`* [SIM=${score.toFixed(6)}] ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * [SIM=0.000000] qux [{"bar":"baz","baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>As a retriever</strong></summary>
+ *
+ * ```typescript
+ * const retriever = vectorStore.asRetriever({
+ *   searchType: "mmr", // Leave blank for standard similarity search
+ *   k: 1,
+ * });
+ * const resultAsRetriever = await retriever.invoke("thud");
+ * console.log(resultAsRetriever);
+ *
+ * // Output: [Document({ metadata: { "baz":"bar" }, pageContent: "thud" })]
+ * ```
+ * </details>
+ *
+ * <br />
  */
 class MemoryVectorStore extends vectorstores_1.VectorStore {
     _vectorstoreType() {
@@ -54,6 +159,7 @@ class MemoryVectorStore extends vectorstores_1.VectorStore {
             content: documents[idx].pageContent,
             embedding,
             metadata: documents[idx].metadata,
+            id: documents[idx].id,
         }));
         this.memoryVectors = this.memoryVectors.concat(memoryVectors);
     }
@@ -65,6 +171,7 @@ class MemoryVectorStore extends vectorstores_1.VectorStore {
             const doc = new documents_1.Document({
                 metadata: memoryVector.metadata,
                 pageContent: memoryVector.content,
+                id: memoryVector.id,
             });
             return filter(doc);
         };
@@ -76,6 +183,7 @@ class MemoryVectorStore extends vectorstores_1.VectorStore {
             metadata: vector.metadata,
             content: vector.content,
             embedding: vector.embedding,
+            id: vector.id,
         }))
             .sort((a, b) => (a.similarity > b.similarity ? -1 : 0))
             .slice(0, k);
@@ -96,6 +204,7 @@ class MemoryVectorStore extends vectorstores_1.VectorStore {
             new documents_1.Document({
                 metadata: search.metadata,
                 pageContent: search.content,
+                id: search.id,
             }),
             search.similarity,
         ]);
@@ -109,6 +218,7 @@ class MemoryVectorStore extends vectorstores_1.VectorStore {
         return mmrIndexes.map((idx) => new documents_1.Document({
             metadata: searches[idx].metadata,
             pageContent: searches[idx].content,
+            id: searches[idx].id,
         }));
     }
     /**

package/dist/vectorstores/memory.d.ts

@@ -11,6 +11,7 @@ interface MemoryVector {
     content: string;
     embedding: number[];
     metadata: Record<string, any>;
+    id?: string;
 }
 /**
  * Interface for the arguments that can be passed to the
@@ -21,9 +22,114 @@ export interface MemoryVectorStoreArgs {
     similarity?: typeof 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.
+ * In-memory, ephemeral vector store.
+ *
+ * Setup:
+ * Install `langchain`:
+ *
+ * ```bash
+ * npm install langchain
+ * ```
+ *
+ * ## [Constructor args](https://api.js.langchain.com/classes/langchain.vectorstores_memory.MemoryVectorStore.html#constructor)
+ *
+ * <details open>
+ * <summary><strong>Instantiate</strong></summary>
+ *
+ * ```typescript
+ * import { MemoryVectorStore } from 'langchain/vectorstores/memory';
+ * // Or other embeddings
+ * import { OpenAIEmbeddings } from '@langchain/openai';
+ *
+ * const embeddings = new OpenAIEmbeddings({
+ *   model: "text-embedding-3-small",
+ * });
+ *
+ * const vectorStore = new MemoryVectorStore(embeddings);
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Add documents</strong></summary>
+ *
+ * ```typescript
+ * import type { Document } from '@langchain/core/documents';
+ *
+ * const document1 = { pageContent: "foo", metadata: { baz: "bar" } };
+ * const document2 = { pageContent: "thud", metadata: { bar: "baz" } };
+ * const document3 = { pageContent: "i will be deleted :(", metadata: {} };
+ *
+ * const documents: Document[] = [document1, document2, document3];
+ *
+ * await vectorStore.addDocuments(documents);
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Similarity search</strong></summary>
+ *
+ * ```typescript
+ * const results = await vectorStore.similaritySearch("thud", 1);
+ * for (const doc of results) {
+ *   console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * thud [{"baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ *
+ * <details>
+ * <summary><strong>Similarity search with filter</strong></summary>
+ *
+ * ```typescript
+ * const resultsWithFilter = await vectorStore.similaritySearch("thud", 1, { baz: "bar" });
+ *
+ * for (const doc of resultsWithFilter) {
+ *   console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * foo [{"baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ *
+ * <details>
+ * <summary><strong>Similarity search with score</strong></summary>
+ *
+ * ```typescript
+ * const resultsWithScore = await vectorStore.similaritySearchWithScore("qux", 1);
+ * for (const [doc, score] of resultsWithScore) {
+ *   console.log(`* [SIM=${score.toFixed(6)}] ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * [SIM=0.000000] qux [{"bar":"baz","baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>As a retriever</strong></summary>
+ *
+ * ```typescript
+ * const retriever = vectorStore.asRetriever({
+ *   searchType: "mmr", // Leave blank for standard similarity search
+ *   k: 1,
+ * });
+ * const resultAsRetriever = await retriever.invoke("thud");
+ * console.log(resultAsRetriever);
+ *
+ * // Output: [Document({ metadata: { "baz":"bar" }, pageContent: "thud" })]
+ * ```
+ * </details>
+ *
+ * <br />
  */
 export declare class MemoryVectorStore extends VectorStore {
     FilterType: (doc: Document) => boolean;
@@ -54,6 +160,7 @@ export declare class MemoryVectorStore extends VectorStore {
         metadata: Record<string, any>;
         content: string;
         embedding: number[];
+        id: string | undefined;
     }[]>;
     /**
      * Method to perform a similarity search in the memory vector store. It

package/dist/vectorstores/memory.js

@@ -3,9 +3,114 @@ import { Document } from "@langchain/core/documents";
 import { cosine } from "../util/ml-distance/similarities.js";
 import { maximalMarginalRelevance } from "../util/math.js";
 /**
- * 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.
+ * In-memory, ephemeral vector store.
+ *
+ * Setup:
+ * Install `langchain`:
+ *
+ * ```bash
+ * npm install langchain
+ * ```
+ *
+ * ## [Constructor args](https://api.js.langchain.com/classes/langchain.vectorstores_memory.MemoryVectorStore.html#constructor)
+ *
+ * <details open>
+ * <summary><strong>Instantiate</strong></summary>
+ *
+ * ```typescript
+ * import { MemoryVectorStore } from 'langchain/vectorstores/memory';
+ * // Or other embeddings
+ * import { OpenAIEmbeddings } from '@langchain/openai';
+ *
+ * const embeddings = new OpenAIEmbeddings({
+ *   model: "text-embedding-3-small",
+ * });
+ *
+ * const vectorStore = new MemoryVectorStore(embeddings);
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Add documents</strong></summary>
+ *
+ * ```typescript
+ * import type { Document } from '@langchain/core/documents';
+ *
+ * const document1 = { pageContent: "foo", metadata: { baz: "bar" } };
+ * const document2 = { pageContent: "thud", metadata: { bar: "baz" } };
+ * const document3 = { pageContent: "i will be deleted :(", metadata: {} };
+ *
+ * const documents: Document[] = [document1, document2, document3];
+ *
+ * await vectorStore.addDocuments(documents);
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Similarity search</strong></summary>
+ *
+ * ```typescript
+ * const results = await vectorStore.similaritySearch("thud", 1);
+ * for (const doc of results) {
+ *   console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * thud [{"baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ *
+ * <details>
+ * <summary><strong>Similarity search with filter</strong></summary>
+ *
+ * ```typescript
+ * const resultsWithFilter = await vectorStore.similaritySearch("thud", 1, { baz: "bar" });
+ *
+ * for (const doc of resultsWithFilter) {
+ *   console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * foo [{"baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ *
+ * <details>
+ * <summary><strong>Similarity search with score</strong></summary>
+ *
+ * ```typescript
+ * const resultsWithScore = await vectorStore.similaritySearchWithScore("qux", 1);
+ * for (const [doc, score] of resultsWithScore) {
+ *   console.log(`* [SIM=${score.toFixed(6)}] ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * [SIM=0.000000] qux [{"bar":"baz","baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>As a retriever</strong></summary>
+ *
+ * ```typescript
+ * const retriever = vectorStore.asRetriever({
+ *   searchType: "mmr", // Leave blank for standard similarity search
+ *   k: 1,
+ * });
+ * const resultAsRetriever = await retriever.invoke("thud");
+ * console.log(resultAsRetriever);
+ *
+ * // Output: [Document({ metadata: { "baz":"bar" }, pageContent: "thud" })]
+ * ```
+ * </details>
+ *
+ * <br />
  */
 export class MemoryVectorStore extends VectorStore {
     _vectorstoreType() {
@@ -51,6 +156,7 @@ export class MemoryVectorStore extends VectorStore {
             content: documents[idx].pageContent,
             embedding,
             metadata: documents[idx].metadata,
+            id: documents[idx].id,
         }));
         this.memoryVectors = this.memoryVectors.concat(memoryVectors);
     }
@@ -62,6 +168,7 @@ export class MemoryVectorStore extends VectorStore {
             const doc = new Document({
                 metadata: memoryVector.metadata,
                 pageContent: memoryVector.content,
+                id: memoryVector.id,
             });
             return filter(doc);
         };
@@ -73,6 +180,7 @@ export class MemoryVectorStore extends VectorStore {
             metadata: vector.metadata,
             content: vector.content,
             embedding: vector.embedding,
+            id: vector.id,
         }))
             .sort((a, b) => (a.similarity > b.similarity ? -1 : 0))
             .slice(0, k);
@@ -93,6 +201,7 @@ export class MemoryVectorStore extends VectorStore {
             new Document({
                 metadata: search.metadata,
                 pageContent: search.content,
+                id: search.id,
             }),
             search.similarity,
         ]);
@@ -106,6 +215,7 @@ export class MemoryVectorStore extends VectorStore {
         return mmrIndexes.map((idx) => new Document({
             metadata: searches[idx].metadata,
             pageContent: searches[idx].content,
+            id: searches[idx].id,
         }));
     }
     /**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "langchain",
-  "version": "0.2.16",
+  "version": "0.2.17",
   "description": "Typescript bindings for langchain",
   "type": "module",
   "engines": {
@@ -574,12 +574,7 @@
   "homepage": "https://github.com/langchain-ai/langchainjs/tree/main/langchain/",
   "scripts": {
     "build": "yarn turbo:command build:internal --filter=langchain",
-    "build:internal": "yarn lc_build_v2 --create-entrypoints --pre --tree-shaking --gen-maps",
-    "build:deps": "yarn run turbo:command build --filter=@langchain/openai --filter=@langchain/textsplitters --filter=@langchain/cohere --concurrency=1",
-    "build:esm": "NODE_OPTIONS=--max-old-space-size=4096 tsc --outDir dist/ && rimraf dist/tests dist/**/tests",
-    "build:cjs": "NODE_OPTIONS=--max-old-space-size=4096 tsc --outDir dist-cjs/ -p tsconfig.cjs.json && yarn move-cjs-to-dist && rimraf dist-cjs",
-    "build:watch": "yarn create-entrypoints && tsc --outDir dist/ --watch",
-    "build:scripts": "yarn create-entrypoints && yarn check-tree-shaking",
+    "build:internal": "yarn lc_build --create-entrypoints --pre --tree-shaking --gen-maps",
     "lint:eslint": "NODE_OPTIONS=--max-old-space-size=4096 eslint --cache --ext .ts,.js src/",
     "lint:dpdm": "dpdm --exit-code circular:1 --no-warning --no-tree src/*.ts src/**/*.ts",
     "lint": "yarn lint:eslint && yarn lint:dpdm",
@@ -593,10 +588,7 @@
     "test:integration": "yarn run build:deps && NODE_OPTIONS=--experimental-vm-modules jest --testPathPattern=\\.int\\.test.ts --testTimeout 100000 --maxWorkers=50%",
     "test:single": "yarn run build:deps && NODE_OPTIONS=--experimental-vm-modules yarn run jest --config jest.config.cjs --testTimeout 100000",
     "format": "prettier --config .prettierrc --write \"src\"",
-    "format:check": "prettier --config .prettierrc --check \"src\"",
-    "move-cjs-to-dist": "yarn lc-build --config ./langchain.config.js --move-cjs-dist",
-    "create-entrypoints": "yarn lc-build --config ./langchain.config.js --create-entrypoints",
-    "check-tree-shaking": "yarn lc-build --config ./langchain.config.js --tree-shaking"
+    "format:check": "prettier --config .prettierrc --check \"src\""
   },
   "author": "LangChain",
   "license": "MIT",
@@ -616,12 +608,12 @@
     "@langchain/anthropic": "^0.2.8",
     "@langchain/aws": "^0.0.5",
     "@langchain/cohere": "^0.2.1",
-    "@langchain/google-genai": "^0.0.25",
-    "@langchain/google-vertexai": "^0.0.25",
+    "@langchain/google-genai": "^0.0.26",
+    "@langchain/google-vertexai": "^0.0.26",
     "@langchain/groq": "^0.0.15",
     "@langchain/mistralai": "^0.0.26",
     "@langchain/ollama": "^0.0.2",
-    "@langchain/scripts": "~0.0.20",
+    "@langchain/scripts": ">=0.1.0 <0.2.0",
     "@mendable/firecrawl-js": "^0.0.13",
     "@notionhq/client": "^2.2.10",
     "@pinecone-database/pinecone": "^1.1.0",