Class SupabaseVectorStore

Supabase vector store integration.

Setup: Install @langchain/community and @supabase/supabase-js.

npm install @langchain/community @supabase/supabase-js

See https://js.langchain.com/docs/integrations/vectorstores/supabase for instructions on how to set up your Supabase instance.

Constructor args

Instantiate 
import { SupabaseVectorStore } from "@langchain/community/vectorstores/supabase";
import { OpenAIEmbeddings } from "@langchain/openai";

import { createClient } from "@supabase/supabase-js";

const embeddings = new OpenAIEmbeddings({
  model: "text-embedding-3-small",
});

const supabaseClient = createClient(
  process.env.SUPABASE_URL,
  process.env.SUPABASE_PRIVATE_KEY
);

const vectorStore = new SupabaseVectorStore(embeddings, {
  client: supabaseClient,
  tableName: "documents",
  queryName: "match_documents",
});

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];
const ids = ["1", "2", "3"];
await vectorStore.addDocuments(documents, { ids });

Delete documents 
await vectorStore.delete({ ids: ["3"] });

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
    • SupabaseVectorStore

Constructors

constructor

Properties

FilterType client embeddings filter? queryName tableName upsertBatchSize

Methods

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

Constructors

constructor

Properties

FilterType

FilterType: SupabaseMetadata | SupabaseFilterRPCCall

client

client: SupabaseClient<any, "public", any>

embeddings

embeddings: EmbeddingsInterface

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

Optionalfilter

filter?: SupabaseMetadata | SupabaseFilterRPCCall

queryName

queryName: string

tableName

tableName: string

upsertBatchSize

upsertBatchSize: number = 500

Methods

addDocuments

  • addDocuments(documents, options?): Promise<string[]>

  • Adds documents to the vector store.

    Parameters

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

      The documents to add.

    • Optionaloptions: {
          ids?: string[] | number[];
      }

      Optional parameters for adding the documents.

      • Optionalids?: string[] | number[]

    Returns Promise<string[]>

    A promise that resolves when the documents have been added.

addVectors

  • addVectors(vectors, documents, options?): Promise<string[]>

  • Adds vectors to the vector store.

    Parameters

    • vectors: number[][]

      The vectors to add.

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

      The documents associated with the vectors.

    • Optionaloptions: {
          ids?: string[] | number[];
      }

      Optional parameters for adding the vectors.

      • Optionalids?: string[] | number[]

    Returns Promise<string[]>

    A promise that resolves with the IDs of the added vectors when the vectors have been added.

asRetriever

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

  • Creates a VectorStoreRetriever instance with flexible configuration options.

    Parameters

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

      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: SupabaseMetadata | SupabaseFilterRPCCall

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

    • 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<SupabaseVectorStore>

    • 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 vectors from the vector store.

    Parameters

    • params: {
          ids: string[] | number[];
      }

      The parameters for deleting vectors.

      • ids: string[] | number[]

    Returns Promise<void>

    A promise that resolves when the vectors have been deleted.

maxMarginalRelevanceSearch

  • maxMarginalRelevanceSearch(query, options): Promise<Document<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

    Returns Promise<Document<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: SupabaseMetadata | SupabaseFilterRPCCall

      Optional filter based on FilterType.

    • 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][]>

  • Performs a similarity search on the vector store.

    Parameters

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

    A promise that resolves with the search results when the search is complete.

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: SupabaseMetadata | SupabaseFilterRPCCall

      Optional filter based on FilterType.

    • 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<SupabaseVectorStore>

  • Creates a new SupabaseVectorStore instance from an array of documents.

    Parameters

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

      The documents to create the instance from.

    • embeddings: EmbeddingsInterface

      The embeddings to use.

    • dbConfig: SupabaseLibArgs

      The configuration for the Supabase database.

    Returns Promise<SupabaseVectorStore>

    A promise that resolves with a new SupabaseVectorStore instance when the instance has been created.

StaticfromExistingIndex

StaticfromTexts

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

  • Creates a new SupabaseVectorStore instance from an array of texts.

    Parameters

    • texts: string[]

      The texts to create documents from.

    • metadatas: object | object[]

      The metadata for the documents.

    • embeddings: EmbeddingsInterface

      The embeddings to use.

    • dbConfig: SupabaseLibArgs

      The configuration for the Supabase database.

    Returns Promise<SupabaseVectorStore>

    A promise that resolves with a new SupabaseVectorStore instance when the instance has been created.

Settings

Member Visibility

On This Page

Constructor args
Constructors
Properties
Methods