Class MemoryVectorStore

In-memory, ephemeral vector store.

Setup: Install langchain:

npm install langchain

Constructor args

Instantiate 
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);

Add documents 
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);

Similarity search 
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"}]

Similarity search with filter 
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"}]

Similarity search with score 
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"}]

As a retriever 
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" })]

Hierarchy

  • VectorStore
    • MemoryVectorStore

Constructors

constructor

Properties

FilterType embeddings memoryVectors similarity

Methods

addDocuments addVectors asRetriever delete maxMarginalRelevanceSearch similaritySearch similaritySearchVectorWithScore similaritySearchWithScore toJSON toJSONNotImplemented fromDocuments fromExistingIndex fromTexts

Constructors

constructor

Properties

FilterType

FilterType: ((doc: Document<Record<string, any>>) => boolean)

embeddings

embeddings: EmbeddingsInterface<number[]>

Embeddings interface for generating vector embeddings from text queries, enabling vector-based similarity searches.

memoryVectors

memoryVectors: MemoryVector[] = []

similarity

similarity: ((a: number[], b: number[]) => number)

Type declaration

    • (a, b): number

    • Returns the average of cosine distances between vectors a and b

      Parameters

      • a: number[]

        first vector

      • b: number[]

        second vector

      Returns number

Methods

addDocuments

  • addDocuments(documents): Promise<void>

  • 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.

    Parameters

    • documents: Document<Record<string, any>>[]

      Array of Document instances to be added to the store.

    Returns Promise<void>

    Promise that resolves when all documents have been added.

addVectors

  • addVectors(vectors, documents): 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.

    Parameters

    • vectors: number[][]

      Array of vectors to be added to the store.

    • documents: Document<Record<string, any>>[]

      Array of Document instances corresponding to the vectors.

    Returns Promise<void>

    Promise that resolves when all vectors have been added.

asRetriever

  • asRetriever(kOrFields?, filter?, callbacks?, tags?, metadata?, verbose?): VectorStoreRetriever<MemoryVectorStore>

  • Creates a VectorStoreRetriever instance with flexible configuration options.

    Parameters

    • OptionalkOrFields: number | Partial<VectorStoreRetrieverInput<MemoryVectorStore>>

      If a number is provided, it sets the k parameter (number of items to retrieve).

      • If an object is provided, it should contain various configuration options.
    • Optionalfilter: ((doc: Document<Record<string, any>>) => boolean)

      Optional filter criteria to limit the items retrieved based on the specified filter type.

        • (doc): boolean

        • Parameters

          • doc: Document<Record<string, any>>

          Returns boolean

    • Optionalcallbacks: Callbacks

      Optional callbacks that may be triggered at specific stages of the retrieval process.

    • Optionaltags: string[]

      Tags to categorize or label the VectorStoreRetriever. Defaults to an empty array if not provided.

    • Optionalmetadata: Record<string, unknown>

      Additional metadata as key-value pairs to add contextual information for the retrieval process.

    • Optionalverbose: boolean

      If true, enables detailed logging for the retrieval process. Defaults to false.

    Returns VectorStoreRetriever<MemoryVectorStore>

    • A configured VectorStoreRetriever instance based on the provided parameters.

    Example

    Basic usage with a k value:

    const retriever = myVectorStore.asRetriever(5);

    Usage with a configuration object:

    const retriever = myVectorStore.asRetriever({
      k: 10,
      filter: myFilter,
      tags: ['example', 'test'],
      verbose: true,
      searchType: 'mmr',
      searchKwargs: { alpha: 0.5 },
    });

delete

  • delete(_params?): Promise<void>

  • Deletes documents from the vector store based on the specified parameters.

    Parameters

    • Optional_params: Record<string, any>

      Flexible key-value pairs defining conditions for document deletion.

    Returns Promise<void>

    A promise that resolves once the deletion is complete.

maxMarginalRelevanceSearch

  • maxMarginalRelevanceSearch(query, options): Promise<DocumentInterface<Record<string, any>>[]>

  • Return documents selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to the query AND diversity among selected documents.

    Parameters

    • query: string

      Text to look up documents similar to.

    • options: MaxMarginalRelevanceSearchOptions<((doc: Document<Record<string, any>>) => boolean)>

    Returns Promise<DocumentInterface<Record<string, any>>[]>

    • List of documents selected by maximal marginal relevance.

similaritySearch

  • similaritySearch(query, k?, filter?, _callbacks?): Promise<DocumentInterface<Record<string, any>>[]>

  • Searches for documents similar to a text query by embedding the query and performing a similarity search on the resulting vector.

    Parameters

    • query: string

      Text query for finding similar documents.

    • Optionalk: number

      Number of similar results to return. Defaults to 4.

    • Optionalfilter: ((doc: Document<Record<string, any>>) => boolean)

      Optional filter based on FilterType.

        • (doc): boolean

        • Parameters

          • doc: Document<Record<string, any>>

          Returns boolean

    • Optional_callbacks: Callbacks

      Optional callbacks for monitoring search progress

    Returns Promise<DocumentInterface<Record<string, any>>[]>

    A promise resolving to an array of DocumentInterface instances representing similar documents.

similaritySearchVectorWithScore

  • similaritySearchVectorWithScore(query, k, filter?): Promise<[Document<Record<string, any>>, number][]>

  • 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.

    Parameters

    • query: number[]

      Query vector to compare against the vectors in the store.

    • k: number

      Number of top results to return.

    • Optionalfilter: ((doc: Document<Record<string, any>>) => boolean)

      Optional filter function to apply to the vectors before performing the search.

        • (doc): boolean

        • Parameters

          • doc: Document<Record<string, any>>

          Returns boolean

    Returns Promise<[Document<Record<string, any>>, number][]>

    Promise that resolves with an array of tuples, each containing a Document and its similarity score.

similaritySearchWithScore

  • similaritySearchWithScore(query, k?, filter?, _callbacks?): Promise<[DocumentInterface<Record<string, any>>, number][]>

  • Searches for documents similar to a text query by embedding the query, and returns results with similarity scores.

    Parameters

    • query: string

      Text query for finding similar documents.

    • Optionalk: number

      Number of similar results to return. Defaults to 4.

    • Optionalfilter: ((doc: Document<Record<string, any>>) => boolean)

      Optional filter based on FilterType.

        • (doc): boolean

        • Parameters

          • doc: Document<Record<string, any>>

          Returns boolean

    • Optional_callbacks: Callbacks

      Optional callbacks for monitoring search progress

    Returns Promise<[DocumentInterface<Record<string, any>>, number][]>

    A promise resolving to an array of tuples, each containing a document and its similarity score.

toJSON

  • toJSON(): Serialized

  • Returns Serialized

toJSONNotImplemented

StaticfromDocuments

  • fromDocuments(docs, embeddings, dbConfig?): Promise<MemoryVectorStore>

  • Static method to create a MemoryVectorStore instance from an array of Document instances. It adds the documents to the store.

    Parameters

    • docs: Document<Record<string, any>>[]

      Array of Document instances to be added to the store.

    • embeddings: EmbeddingsInterface<number[]>

      Embeddings instance used to generate embeddings for the documents.

    • OptionaldbConfig: MemoryVectorStoreArgs

      Optional MemoryVectorStoreArgs to configure the MemoryVectorStore instance.

    Returns Promise<MemoryVectorStore>

    Promise that resolves with a new MemoryVectorStore instance.

StaticfromExistingIndex

  • fromExistingIndex(embeddings, dbConfig?): Promise<MemoryVectorStore>

  • Static method to create a MemoryVectorStore instance from an existing index. It creates a new MemoryVectorStore instance without adding any documents or vectors.

    Parameters

    • embeddings: EmbeddingsInterface<number[]>

      Embeddings instance used to generate embeddings for the documents.

    • OptionaldbConfig: MemoryVectorStoreArgs

      Optional MemoryVectorStoreArgs to configure the MemoryVectorStore instance.

    Returns Promise<MemoryVectorStore>

    Promise that resolves with a new MemoryVectorStore instance.

StaticfromTexts

  • fromTexts(texts, metadatas, embeddings, dbConfig?): Promise<MemoryVectorStore>

  • Static method to create a MemoryVectorStore instance from an array of texts. It creates a Document for each text and metadata pair, and adds them to the store.

    Parameters

    • texts: string[]

      Array of texts to be added to the store.

    • metadatas: object | object[]

      Array or single object of metadata corresponding to the texts.

    • embeddings: EmbeddingsInterface<number[]>

      Embeddings instance used to generate embeddings for the texts.

    • OptionaldbConfig: MemoryVectorStoreArgs

      Optional MemoryVectorStoreArgs to configure the MemoryVectorStore instance.

    Returns Promise<MemoryVectorStore>

    Promise that resolves with a new MemoryVectorStore instance.

Settings

Member Visibility

On This Page

Constructor args
Constructors
Properties
Methods