langchain 0.0.192 → 0.0.194

package/dist/prompts/selectors/LengthBasedExampleSelector.js

@@ -9,6 +9,42 @@ function getLengthBased(text) {
  * A specialized example selector that selects examples based on their
  * length, ensuring that the total length of the selected examples does
  * not exceed a specified maximum length.
+ * @example
+ * ```typescript
+ * const exampleSelector = new LengthBasedExampleSelector(
+ *   [
+ *     { input: "happy", output: "sad" },
+ *     { input: "tall", output: "short" },
+ *     { input: "energetic", output: "lethargic" },
+ *     { input: "sunny", output: "gloomy" },
+ *     { input: "windy", output: "calm" },
+ *   ],
+ *   {
+ *     examplePrompt: new PromptTemplate({
+ *       inputVariables: ["input", "output"],
+ *       template: "Input: {input}\nOutput: {output}",
+ *     }),
+ *     maxLength: 25,
+ *   },
+ * );
+ * const dynamicPrompt = new FewShotPromptTemplate({
+ *   exampleSelector,
+ *   examplePrompt: new PromptTemplate({
+ *     inputVariables: ["input", "output"],
+ *     template: "Input: {input}\nOutput: {output}",
+ *   }),
+ *   prefix: "Give the antonym of every input",
+ *   suffix: "Input: {adjective}\nOutput:",
+ *   inputVariables: ["adjective"],
+ * });
+ * console.log(dynamicPrompt.format({ adjective: "big" }));
+ * console.log(
+ *   dynamicPrompt.format({
+ *     adjective:
+ *       "big and huge and massive and large and gigantic and tall and much much much much much bigger than everything else",
+ *   }),
+ * );
+ * ```
  */
 export class LengthBasedExampleSelector extends BaseExampleSelector {
     constructor(data) {

package/dist/prompts/selectors/SemanticSimilarityExampleSelector.cjs

@@ -11,6 +11,31 @@ function sortedValues(values) {
 /**
  * Class that selects examples based on semantic similarity. It extends
  * the BaseExampleSelector class.
+ * @example
+ * ```typescript
+ * const exampleSelector = await SemanticSimilarityExampleSelector.fromExamples(
+ *   [
+ *     { input: "happy", output: "sad" },
+ *     { input: "tall", output: "short" },
+ *     { input: "energetic", output: "lethargic" },
+ *     { input: "sunny", output: "gloomy" },
+ *     { input: "windy", output: "calm" },
+ *   ],
+ *   new OpenAIEmbeddings(),
+ *   HNSWLib,
+ *   { k: 1 },
+ * );
+ * const dynamicPrompt = new FewShotPromptTemplate({
+ *   exampleSelector,
+ *   examplePrompt: PromptTemplate.fromTemplate(
+ *     "Input: {input}\nOutput: {output}",
+ *   ),
+ *   prefix: "Give the antonym of every input",
+ *   suffix: "Input: {adjective}\nOutput:",
+ *   inputVariables: ["adjective"],
+ * });
+ * console.log(await dynamicPrompt.format({ adjective: "rainy" }));
+ * ```
  */
 class SemanticSimilarityExampleSelector extends base_js_1.BaseExampleSelector {
     constructor(data) {

package/dist/prompts/selectors/SemanticSimilarityExampleSelector.d.ts

@@ -24,6 +24,31 @@ export type SemanticSimilarityExampleSelectorInput<V extends VectorStore = Vecto
 /**
  * Class that selects examples based on semantic similarity. It extends
  * the BaseExampleSelector class.
+ * @example
+ * ```typescript
+ * const exampleSelector = await SemanticSimilarityExampleSelector.fromExamples(
+ *   [
+ *     { input: "happy", output: "sad" },
+ *     { input: "tall", output: "short" },
+ *     { input: "energetic", output: "lethargic" },
+ *     { input: "sunny", output: "gloomy" },
+ *     { input: "windy", output: "calm" },
+ *   ],
+ *   new OpenAIEmbeddings(),
+ *   HNSWLib,
+ *   { k: 1 },
+ * );
+ * const dynamicPrompt = new FewShotPromptTemplate({
+ *   exampleSelector,
+ *   examplePrompt: PromptTemplate.fromTemplate(
+ *     "Input: {input}\nOutput: {output}",
+ *   ),
+ *   prefix: "Give the antonym of every input",
+ *   suffix: "Input: {adjective}\nOutput:",
+ *   inputVariables: ["adjective"],
+ * });
+ * console.log(await dynamicPrompt.format({ adjective: "rainy" }));
+ * ```
  */
 export declare class SemanticSimilarityExampleSelector<V extends VectorStore = VectorStore> extends BaseExampleSelector {
     vectorStoreRetriever: VectorStoreRetriever<V>;

package/dist/prompts/selectors/SemanticSimilarityExampleSelector.js

@@ -8,6 +8,31 @@ function sortedValues(values) {
 /**
  * Class that selects examples based on semantic similarity. It extends
  * the BaseExampleSelector class.
+ * @example
+ * ```typescript
+ * const exampleSelector = await SemanticSimilarityExampleSelector.fromExamples(
+ *   [
+ *     { input: "happy", output: "sad" },
+ *     { input: "tall", output: "short" },
+ *     { input: "energetic", output: "lethargic" },
+ *     { input: "sunny", output: "gloomy" },
+ *     { input: "windy", output: "calm" },
+ *   ],
+ *   new OpenAIEmbeddings(),
+ *   HNSWLib,
+ *   { k: 1 },
+ * );
+ * const dynamicPrompt = new FewShotPromptTemplate({
+ *   exampleSelector,
+ *   examplePrompt: PromptTemplate.fromTemplate(
+ *     "Input: {input}\nOutput: {output}",
+ *   ),
+ *   prefix: "Give the antonym of every input",
+ *   suffix: "Input: {adjective}\nOutput:",
+ *   inputVariables: ["adjective"],
+ * });
+ * console.log(await dynamicPrompt.format({ adjective: "rainy" }));
+ * ```
  */
 export class SemanticSimilarityExampleSelector extends BaseExampleSelector {
     constructor(data) {

package/dist/retrievers/amazon_kendra.cjs

@@ -7,6 +7,22 @@ const document_js_1 = require("../document.cjs");
 /**
  * Class for interacting with Amazon Kendra, an intelligent search service
  * provided by AWS. Extends the BaseRetriever class.
+ * @example
+ * ```typescript
+ * const retriever = new AmazonKendraRetriever({
+ *   topK: 10,
+ *   indexId: "YOUR_INDEX_ID",
+ *   region: "us-east-2",
+ *   clientOptions: {
+ *     credentials: {
+ *       accessKeyId: "YOUR_ACCESS_KEY_ID",
+ *       secretAccessKey: "YOUR_SECRET_ACCESS_KEY",
+ *     },
+ *   },
+ * });
+ *
+ * const docs = await retriever.getRelevantDocuments("How are clouds formed?");
+ * ```
  */
 class AmazonKendraRetriever extends retriever_js_1.BaseRetriever {
     static lc_name() {

package/dist/retrievers/amazon_kendra.d.ts

@@ -15,6 +15,22 @@ export interface AmazonKendraRetrieverArgs {
 /**
  * Class for interacting with Amazon Kendra, an intelligent search service
  * provided by AWS. Extends the BaseRetriever class.
+ * @example
+ * ```typescript
+ * const retriever = new AmazonKendraRetriever({
+ *   topK: 10,
+ *   indexId: "YOUR_INDEX_ID",
+ *   region: "us-east-2",
+ *   clientOptions: {
+ *     credentials: {
+ *       accessKeyId: "YOUR_ACCESS_KEY_ID",
+ *       secretAccessKey: "YOUR_SECRET_ACCESS_KEY",
+ *     },
+ *   },
+ * });
+ *
+ * const docs = await retriever.getRelevantDocuments("How are clouds formed?");
+ * ```
  */
 export declare class AmazonKendraRetriever extends BaseRetriever {
     static lc_name(): string;

package/dist/retrievers/amazon_kendra.js

@@ -4,6 +4,22 @@ import { Document } from "../document.js";
 /**
  * Class for interacting with Amazon Kendra, an intelligent search service
  * provided by AWS. Extends the BaseRetriever class.
+ * @example
+ * ```typescript
+ * const retriever = new AmazonKendraRetriever({
+ *   topK: 10,
+ *   indexId: "YOUR_INDEX_ID",
+ *   region: "us-east-2",
+ *   clientOptions: {
+ *     credentials: {
+ *       accessKeyId: "YOUR_ACCESS_KEY_ID",
+ *       secretAccessKey: "YOUR_SECRET_ACCESS_KEY",
+ *     },
+ *   },
+ * });
+ *
+ * const docs = await retriever.getRelevantDocuments("How are clouds formed?");
+ * ```
  */
 export class AmazonKendraRetriever extends BaseRetriever {
     static lc_name() {

package/dist/retrievers/chaindesk.cjs

@@ -4,6 +4,17 @@ exports.ChaindeskRetriever = void 0;
 const retriever_js_1 = require("../schema/retriever.cjs");
 const document_js_1 = require("../document.cjs");
 const async_caller_js_1 = require("../util/async_caller.cjs");
+/**
+ * @example
+ * ```typescript
+ * const retriever = new ChaindeskRetriever({
+ *   datastoreId: "DATASTORE_ID",
+ *   apiKey: "CHAINDESK_API_KEY",
+ *   topK: 8,
+ * });
+ * const docs = await retriever.getRelevantDocuments("hello");
+ * ```
+ */
 class ChaindeskRetriever extends retriever_js_1.BaseRetriever {
     static lc_name() {
         return "ChaindeskRetriever";

package/dist/retrievers/chaindesk.d.ts

@@ -6,6 +6,17 @@ export interface ChaindeskRetrieverArgs extends AsyncCallerParams, BaseRetriever
     topK?: number;
     apiKey?: string;
 }
+/**
+ * @example
+ * ```typescript
+ * const retriever = new ChaindeskRetriever({
+ *   datastoreId: "DATASTORE_ID",
+ *   apiKey: "CHAINDESK_API_KEY",
+ *   topK: 8,
+ * });
+ * const docs = await retriever.getRelevantDocuments("hello");
+ * ```
+ */
 export declare class ChaindeskRetriever extends BaseRetriever {
     static lc_name(): string;
     lc_namespace: string[];

package/dist/retrievers/chaindesk.js

@@ -1,6 +1,17 @@
 import { BaseRetriever } from "../schema/retriever.js";
 import { Document } from "../document.js";
 import { AsyncCaller } from "../util/async_caller.js";
+/**
+ * @example
+ * ```typescript
+ * const retriever = new ChaindeskRetriever({
+ *   datastoreId: "DATASTORE_ID",
+ *   apiKey: "CHAINDESK_API_KEY",
+ *   topK: 8,
+ * });
+ * const docs = await retriever.getRelevantDocuments("hello");
+ * ```
+ */
 export class ChaindeskRetriever extends BaseRetriever {
     static lc_name() {
         return "ChaindeskRetriever";

package/dist/retrievers/contextual_compression.cjs

@@ -6,6 +6,16 @@ const retriever_js_1 = require("../schema/retriever.cjs");
  * A retriever that wraps a base retriever and compresses the results. It
  * retrieves relevant documents based on a given query and then compresses
  * these documents using a specified document compressor.
+ * @example
+ * ```typescript
+ * const retriever = new ContextualCompressionRetriever({
+ *   baseCompressor: new LLMChainExtractor(),
+ *   baseRetriever: new HNSWLib().asRetriever(),
+ * });
+ * const retrievedDocs = await retriever.getRelevantDocuments(
+ *   "What did the speaker say about Justice Breyer?",
+ * );
+ * ```
  */
 class ContextualCompressionRetriever extends retriever_js_1.BaseRetriever {
     static lc_name() {

package/dist/retrievers/contextual_compression.d.ts

@@ -15,6 +15,16 @@ export interface ContextualCompressionRetrieverArgs extends BaseRetrieverInput {
  * A retriever that wraps a base retriever and compresses the results. It
  * retrieves relevant documents based on a given query and then compresses
  * these documents using a specified document compressor.
+ * @example
+ * ```typescript
+ * const retriever = new ContextualCompressionRetriever({
+ *   baseCompressor: new LLMChainExtractor(),
+ *   baseRetriever: new HNSWLib().asRetriever(),
+ * });
+ * const retrievedDocs = await retriever.getRelevantDocuments(
+ *   "What did the speaker say about Justice Breyer?",
+ * );
+ * ```
  */
 export declare class ContextualCompressionRetriever extends BaseRetriever {
     static lc_name(): string;

package/dist/retrievers/contextual_compression.js

@@ -3,6 +3,16 @@ import { BaseRetriever } from "../schema/retriever.js";
  * A retriever that wraps a base retriever and compresses the results. It
  * retrieves relevant documents based on a given query and then compresses
  * these documents using a specified document compressor.
+ * @example
+ * ```typescript
+ * const retriever = new ContextualCompressionRetriever({
+ *   baseCompressor: new LLMChainExtractor(),
+ *   baseRetriever: new HNSWLib().asRetriever(),
+ * });
+ * const retrievedDocs = await retriever.getRelevantDocuments(
+ *   "What did the speaker say about Justice Breyer?",
+ * );
+ * ```
  */
 export class ContextualCompressionRetriever extends BaseRetriever {
     static lc_name() {

package/dist/retrievers/document_compressors/embeddings_filter.cjs

@@ -6,6 +6,19 @@ const math_js_1 = require("../../util/math.cjs");
 /**
  * Class that represents a document compressor that uses embeddings to
  * drop documents unrelated to the query.
+ * @example
+ * ```typescript
+ * const embeddingsFilter = new EmbeddingsFilter({
+ *   embeddings: new OpenAIEmbeddings(),
+ *   similarityThreshold: 0.8,
+ *   k: 5,
+ * });
+ * const retrievedDocs = await embeddingsFilter.filterDocuments(
+ *   getDocuments(),
+ *   "What did the speaker say about Justice Breyer in the 2022 State of the Union?",
+ * );
+ * console.log({ retrievedDocs });
+ * ```
  */
 class EmbeddingsFilter extends index_js_1.BaseDocumentCompressor {
     constructor(params) {

package/dist/retrievers/document_compressors/embeddings_filter.d.ts

@@ -14,6 +14,19 @@ export interface EmbeddingsFilterParams {
 /**
  * Class that represents a document compressor that uses embeddings to
  * drop documents unrelated to the query.
+ * @example
+ * ```typescript
+ * const embeddingsFilter = new EmbeddingsFilter({
+ *   embeddings: new OpenAIEmbeddings(),
+ *   similarityThreshold: 0.8,
+ *   k: 5,
+ * });
+ * const retrievedDocs = await embeddingsFilter.filterDocuments(
+ *   getDocuments(),
+ *   "What did the speaker say about Justice Breyer in the 2022 State of the Union?",
+ * );
+ * console.log({ retrievedDocs });
+ * ```
  */
 export declare class EmbeddingsFilter extends BaseDocumentCompressor {
     /**

package/dist/retrievers/document_compressors/embeddings_filter.js

@@ -3,6 +3,19 @@ import { cosineSimilarity } from "../../util/math.js";
 /**
  * Class that represents a document compressor that uses embeddings to
  * drop documents unrelated to the query.
+ * @example
+ * ```typescript
+ * const embeddingsFilter = new EmbeddingsFilter({
+ *   embeddings: new OpenAIEmbeddings(),
+ *   similarityThreshold: 0.8,
+ *   k: 5,
+ * });
+ * const retrievedDocs = await embeddingsFilter.filterDocuments(
+ *   getDocuments(),
+ *   "What did the speaker say about Justice Breyer in the 2022 State of the Union?",
+ * );
+ * console.log({ retrievedDocs });
+ * ```
  */
 export class EmbeddingsFilter extends BaseDocumentCompressor {
     constructor(params) {

package/dist/retrievers/document_compressors/index.cjs

@@ -13,6 +13,32 @@ class BaseDocumentCompressor {
 exports.BaseDocumentCompressor = BaseDocumentCompressor;
 /**
  * Document compressor that uses a pipeline of Transformers.
+ * @example
+ * ```typescript
+ * const compressorPipeline = new DocumentCompressorPipeline({
+ *   transformers: [
+ *     new RecursiveCharacterTextSplitter({
+ *       chunkSize: 200,
+ *       chunkOverlap: 0,
+ *     }),
+ *     new EmbeddingsFilter({
+ *       embeddings: new OpenAIEmbeddings(),
+ *       similarityThreshold: 0.8,
+ *       k: 5,
+ *     }),
+ *   ],
+ * });
+ * const retriever = new ContextualCompressionRetriever({
+ *   baseCompressor: compressorPipeline,
+ *   baseRetriever: new TavilySearchAPIRetriever({
+ *     includeRawContent: true,
+ *   }),
+ * });
+ * const retrievedDocs = await retriever.getRelevantDocuments(
+ *   "What did the speaker say about Justice Breyer in the 2022 State of the Union?",
+ * );
+ * console.log({ retrievedDocs });
+ * ```
  */
 class DocumentCompressorPipeline extends BaseDocumentCompressor {
     constructor(fields) {

package/dist/retrievers/document_compressors/index.d.ts

@@ -19,6 +19,32 @@ export declare abstract class BaseDocumentCompressor {
 }
 /**
  * Document compressor that uses a pipeline of Transformers.
+ * @example
+ * ```typescript
+ * const compressorPipeline = new DocumentCompressorPipeline({
+ *   transformers: [
+ *     new RecursiveCharacterTextSplitter({
+ *       chunkSize: 200,
+ *       chunkOverlap: 0,
+ *     }),
+ *     new EmbeddingsFilter({
+ *       embeddings: new OpenAIEmbeddings(),
+ *       similarityThreshold: 0.8,
+ *       k: 5,
+ *     }),
+ *   ],
+ * });
+ * const retriever = new ContextualCompressionRetriever({
+ *   baseCompressor: compressorPipeline,
+ *   baseRetriever: new TavilySearchAPIRetriever({
+ *     includeRawContent: true,
+ *   }),
+ * });
+ * const retrievedDocs = await retriever.getRelevantDocuments(
+ *   "What did the speaker say about Justice Breyer in the 2022 State of the Union?",
+ * );
+ * console.log({ retrievedDocs });
+ * ```
  */
 export declare class DocumentCompressorPipeline extends BaseDocumentCompressor {
     transformers: (BaseDocumentTransformer | BaseDocumentCompressor)[];

package/dist/retrievers/document_compressors/index.js

@@ -9,6 +9,32 @@ export class BaseDocumentCompressor {
 }
 /**
  * Document compressor that uses a pipeline of Transformers.
+ * @example
+ * ```typescript
+ * const compressorPipeline = new DocumentCompressorPipeline({
+ *   transformers: [
+ *     new RecursiveCharacterTextSplitter({
+ *       chunkSize: 200,
+ *       chunkOverlap: 0,
+ *     }),
+ *     new EmbeddingsFilter({
+ *       embeddings: new OpenAIEmbeddings(),
+ *       similarityThreshold: 0.8,
+ *       k: 5,
+ *     }),
+ *   ],
+ * });
+ * const retriever = new ContextualCompressionRetriever({
+ *   baseCompressor: compressorPipeline,
+ *   baseRetriever: new TavilySearchAPIRetriever({
+ *     includeRawContent: true,
+ *   }),
+ * });
+ * const retrievedDocs = await retriever.getRelevantDocuments(
+ *   "What did the speaker say about Justice Breyer in the 2022 State of the Union?",
+ * );
+ * console.log({ retrievedDocs });
+ * ```
  */
 export class DocumentCompressorPipeline extends BaseDocumentCompressor {
     constructor(fields) {

package/dist/retrievers/hyde.cjs

@@ -9,6 +9,25 @@ const base_js_2 = require("../vectorstores/base.cjs");
  * extends the VectorStoreRetriever class and uses a BaseLanguageModel to
  * generate a hypothetical answer to the query, which is then used to
  * retrieve relevant documents.
+ * @example
+ * ```typescript
+ * const retriever = new HydeRetriever({
+ *   vectorStore: new MemoryVectorStore(new OpenAIEmbeddings()),
+ *   llm: new ChatOpenAI(),
+ *   k: 1,
+ * });
+ * await vectorStore.addDocuments(
+ *   [
+ *     "My name is John.",
+ *     "My name is Bob.",
+ *     "My favourite food is pizza.",
+ *     "My favourite food is pasta.",
+ *   ].map((pageContent) => new Document({ pageContent })),
+ * );
+ * const results = await retriever.getRelevantDocuments(
+ *   "What is my favourite food?",
+ * );
+ * ```
  */
 class HydeRetriever extends base_js_2.VectorStoreRetriever {
     static lc_name() {

package/dist/retrievers/hyde.d.ts

@@ -21,6 +21,25 @@ export type HydeRetrieverOptions<V extends VectorStore> = VectorStoreRetrieverIn
  * extends the VectorStoreRetriever class and uses a BaseLanguageModel to
  * generate a hypothetical answer to the query, which is then used to
  * retrieve relevant documents.
+ * @example
+ * ```typescript
+ * const retriever = new HydeRetriever({
+ *   vectorStore: new MemoryVectorStore(new OpenAIEmbeddings()),
+ *   llm: new ChatOpenAI(),
+ *   k: 1,
+ * });
+ * await vectorStore.addDocuments(
+ *   [
+ *     "My name is John.",
+ *     "My name is Bob.",
+ *     "My favourite food is pizza.",
+ *     "My favourite food is pasta.",
+ *   ].map((pageContent) => new Document({ pageContent })),
+ * );
+ * const results = await retriever.getRelevantDocuments(
+ *   "What is my favourite food?",
+ * );
+ * ```
  */
 export declare class HydeRetriever<V extends VectorStore = VectorStore> extends VectorStoreRetriever<V> {
     static lc_name(): string;

package/dist/retrievers/hyde.js

@@ -6,6 +6,25 @@ import { VectorStoreRetriever, } from "../vectorstores/base.js";
  * extends the VectorStoreRetriever class and uses a BaseLanguageModel to
  * generate a hypothetical answer to the query, which is then used to
  * retrieve relevant documents.
+ * @example
+ * ```typescript
+ * const retriever = new HydeRetriever({
+ *   vectorStore: new MemoryVectorStore(new OpenAIEmbeddings()),
+ *   llm: new ChatOpenAI(),
+ *   k: 1,
+ * });
+ * await vectorStore.addDocuments(
+ *   [
+ *     "My name is John.",
+ *     "My name is Bob.",
+ *     "My favourite food is pizza.",
+ *     "My favourite food is pasta.",
+ *   ].map((pageContent) => new Document({ pageContent })),
+ * );
+ * const results = await retriever.getRelevantDocuments(
+ *   "What is my favourite food?",
+ * );
+ * ```
  */
 export class HydeRetriever extends VectorStoreRetriever {
     static lc_name() {

package/dist/retrievers/metal.cjs

@@ -9,6 +9,17 @@ const document_js_1 = require("../document.cjs");
  * semantic search and retrieval on it. It extends the `BaseRetriever`
  * class and requires a `Metal` instance and a dictionary of parameters to
  * pass to the Metal API during its initialization.
+ * @example
+ * ```typescript
+ * const retriever = new MetalRetriever({
+ *   client: new Metal(
+ *     process.env.METAL_API_KEY,
+ *     process.env.METAL_CLIENT_ID,
+ *     process.env.METAL_INDEX_ID,
+ *   ),
+ * });
+ * const docs = await retriever.getRelevantDocuments("hello");
+ * ```
  */
 class MetalRetriever extends retriever_js_1.BaseRetriever {
     static lc_name() {

package/dist/retrievers/metal.d.ts

@@ -15,6 +15,17 @@ export interface MetalRetrieverFields extends BaseRetrieverInput {
  * semantic search and retrieval on it. It extends the `BaseRetriever`
  * class and requires a `Metal` instance and a dictionary of parameters to
  * pass to the Metal API during its initialization.
+ * @example
+ * ```typescript
+ * const retriever = new MetalRetriever({
+ *   client: new Metal(
+ *     process.env.METAL_API_KEY,
+ *     process.env.METAL_CLIENT_ID,
+ *     process.env.METAL_INDEX_ID,
+ *   ),
+ * });
+ * const docs = await retriever.getRelevantDocuments("hello");
+ * ```
  */
 export declare class MetalRetriever extends BaseRetriever {
     static lc_name(): string;

package/dist/retrievers/metal.js

@@ -6,6 +6,17 @@ import { Document } from "../document.js";
  * semantic search and retrieval on it. It extends the `BaseRetriever`
  * class and requires a `Metal` instance and a dictionary of parameters to
  * pass to the Metal API during its initialization.
+ * @example
+ * ```typescript
+ * const retriever = new MetalRetriever({
+ *   client: new Metal(
+ *     process.env.METAL_API_KEY,
+ *     process.env.METAL_CLIENT_ID,
+ *     process.env.METAL_INDEX_ID,
+ *   ),
+ * });
+ * const docs = await retriever.getRelevantDocuments("hello");
+ * ```
  */
 export class MetalRetriever extends BaseRetriever {
     static lc_name() {

package/dist/retrievers/multi_query.cjs

@@ -54,7 +54,19 @@ Question 3
 
 Original question: {question}`,
 });
-// Export class
+/**
+ * @example
+ * ```typescript
+ * const retriever = new MultiQueryRetriever.fromLLM({
+ *   llm: new ChatAnthropic({}),
+ *   retriever: new MemoryVectorStore().asRetriever(),
+ *   verbose: true,
+ * });
+ * const retrievedDocs = await retriever.getRelevantDocuments(
+ *   "What are mitochondria made of?",
+ * );
+ * ```
+ */
 class MultiQueryRetriever extends retriever_js_1.BaseRetriever {
     static lc_name() {
         return "MultiQueryRetriever";

package/dist/retrievers/multi_query.d.ts

@@ -13,6 +13,19 @@ export interface MultiQueryRetrieverInput extends BaseRetrieverInput {
     queryCount?: number;
     parserKey?: string;
 }
+/**
+ * @example
+ * ```typescript
+ * const retriever = new MultiQueryRetriever.fromLLM({
+ *   llm: new ChatAnthropic({}),
+ *   retriever: new MemoryVectorStore().asRetriever(),
+ *   verbose: true,
+ * });
+ * const retrievedDocs = await retriever.getRelevantDocuments(
+ *   "What are mitochondria made of?",
+ * );
+ * ```
+ */
 export declare class MultiQueryRetriever extends BaseRetriever {
     static lc_name(): string;
     lc_namespace: string[];